Awesome AI Agents

Multi-Agent Collaboration Systems

Orchestration Frameworks

Cognitive Architecture Frameworks

Prompt Libraries

• arcee-ai/mergekit ⭐ 7107 Python - mergekit is a toolkit for efficiently merging pre-trained large language models using various algorithms, supporting CPU and GPU execution, and enabling creation of versatile merged models with maintained inference costs.
• dottxt-ai/outlines ⭐ 13339 Python - Outlines is an open-source tool that enables structured text generation with large language models, ensuring predictable and schema-compliant outputs for various applications.
• dzhng/deep-research ⭐ 19018 TypeScript - Open Deep Research is an AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models to generate comprehensive markdown reports.
• HKUDS/RAG-Anything ⭐ 20817 Python - RAG-Anything is a next-generation all-in-one multimodal Retrieval-Augmented Generation system that processes and queries diverse document content including text, images, tables, and equations within a unified framework.
• microsoft/RD-Agent ⭐ 13285 Python - RD-Agent is an open-source R&D automation tool by Microsoft designed to automate and enhance industrial research and development processes focused on data and models using AI.
• serenakeyitan/awesome-notebookLM-prompts ⭐ 3583 - A curated collection of NotebookLM and Kael.im slide prompts designed to generate professional and visually striking presentations across various styles.

↑ Back to TOC

Reasoning Frameworks

• bytedance/deer-flow ⭐ 70130 TypeScript - DeerFlow is a community-driven deep research framework that integrates language models with web search, crawling, and Python execution tools to facilitate comprehensive AI-powered research workflows.
• friuns2/BlackFriday-GPTs-Prompts ⭐ 9484 - A curated repository of free GPT prompts and jailbreaks across various domains, enabling users to utilize GPT models without a subscription to GPT Plus.
• guidance-ai/guidance ⭐ 21485 Jupyter Notebook - Guidance is a programming paradigm and library that enables efficient and fine-grained control over large language models to produce structured, high-quality outputs with reduced latency and cost.
• mongodb-developer/GenAI-Showcase ⭐ 4209 Jupyter Notebook - MongoDB's GenAI Showcase is a comprehensive repository offering examples and applications that integrate MongoDB with advanced Generative AI techniques like Retrieval-Augmented Generation and AI Agents to support AI development and innovation.
• refly-ai/refly ⭐ 7344 TypeScript - Refly is an open-source AI-native creation engine that combines multi-threaded dialogues, multimodal inputs, knowledge base integration, and AI-powered tools to transform ideas into production-ready interactive content and web applications.
• VectifyAI/PageIndex ⭐ 32379 Jupyter Notebook - PageIndex is a reasoning-based document indexing and retrieval system that uses a hierarchical tree structure to enable human-like, vectorless retrieval and multi-step reasoning over long professional documents.

↑ Back to TOC

Programming Languages

• developersdigest/llm-answer-engine ⭐ 5026 TypeScript - A Perplexity-inspired answer engine built with Next.js and multiple AI and search technologies to provide rich, context-aware responses including sources, images, videos, and follow-up questions.
• Fosowl/agenticSeek ⭐ 26440 Python - AgenticSeek is a fully local, autonomous AI assistant powered by Deepseek R1 agents that can code, browse the web, and manage files without relying on cloud services, ensuring user data privacy and eliminating ongoing costs.
• HKUDS/AI-Researcher ⭐ 5404 Python - AI-Researcher is a fully automated scientific discovery platform powered by large language models that autonomously conducts research from idea generation to manuscript creation.
• InternLM/xtuner ⭐ 5140 Python - XTuner is a comprehensive and efficient toolkit for fine-tuning large language and vision-language models, supporting a wide range of models and training algorithms with scalability and flexibility.
• killop/anything_about_game ⭐ 3918 - A comprehensive curated list of resources for game development, covering topics from game engines and physics to computer graphics, AI programming, and various development tools.
• MODSetter/SurfSense ⭐ 12713 TypeScript - SurfSense is a highly customizable AI research agent that integrates with personal knowledge bases and external sources to provide advanced, privacy-conscious research and knowledge management capabilities.

↑ Back to TOC

AI Assistants

• agent0ai/agent-zero ⭐ 14004 Python - Agent Zero is a dynamic, customizable AI framework that acts as a personal assistant capable of learning, creating tools, and cooperating with multiple agents to accomplish diverse tasks.
• agentscope-ai/QwenPaw ⭐ 17122 Python - QwenPaw is a personal AI assistant that provides under-your-control local or cloud deployment, multi-agent collaboration, extensible skills, multi-layer security, and multi-channel connectivity, wi...
• Alibaba-NLP/WebAgent ⭐ 19057 Python - Alibaba-NLP/WebAgent is a research project by Alibaba's Tongyi Lab featuring WebWalker and WebDancer models for autonomous information seeking and web traversal using large language models with advanced training paradigms and benchmarks.
• assafelovic/gpt-researcher ⭐ 27423 Python - GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.
• cloudflare/moltworker ⭐ 9907 TypeScript - Moltworker is a proof-of-concept project that runs the OpenClaw personal AI assistant within Cloudflare Workers using sandbox containers, providing secure, multi-channel AI assistant deployment with persistent storage and managed infrastructure.
• DearVa/Everywhere ⭐ 5335 C# - Everywhere is a context-aware AI desktop assistant that integrates multiple large language models and tools to provide seamless, intelligent help directly on your screen without switching apps.
• ghuntley/how-to-build-a-coding-agent ⭐ 5629 Go - A step-by-step workshop to build an AI-powered coding assistant that evolves from a basic chatbot to a multi-functional developer tool using the Anthropic Claude API.
• HKUDS/DeepTutor ⭐ 24452 Python - DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.
• leon-ai/leon ⭐ 17283 TypeScript - Leon is an open-source, privacy-aware personal AI assistant focused on agentic execution, tools, context, and memory, designed to operate locally and adapt to user environments.
• Mirix-AI/MIRIX ⭐ 3505 Python - Mirix is a multi-agent personal assistant that captures and consolidates on-screen activities into structured memories, providing intelligent, privacy-focused, and adaptive user interaction through advanced multi-modal data processing and search capabilities.
• nanocoai/nanoclaw ⭐ 29574 TypeScript - NanoClaw is a lightweight, secure AI assistant platform that leverages Anthropic's Agents SDK to run Claude agents in isolated containers, offering customizable multi-channel messaging and schedule...
• nickjvandyke/opencode.nvim ⭐ 3517 Lua - opencode.nvim integrates the opencode AI assistant into Neovim to provide context-aware code research, reviews, and requests directly within the editor.
• screenpipe/screenpipe ⭐ 19014 Rust - Screenpipe is a personal AI system that records, searches, and automates computer activities locally and privately, turning your computer into a knowledge base.
• sickn33/antigravity-awesome-skills ⭐ 39302 Python - Antigravity Awesome Skills is a curated collection of over 625 high-performance agentic skills designed to enhance AI coding assistants across multiple platforms, transforming them into full-stack digital agencies capable of handling diverse software development and operational tasks.
• volcengine/MineContext ⭐ 4849 Python - MineContext is a proactive context-aware AI partner that collects and processes multimodal digital context to deliver insights, summaries, and to-dos, enhancing productivity and creativity while prioritizing user privacy.
• VoltAgent/awesome-claude-skills ⭐ 23788 - A curated collection of Claude Skills and resources that extend the AI assistant Claude's capabilities through modular, dynamically loaded skills for various tasks including document creation, creative design, development, and collaboration.
• zeroclaw-labs/zeroclaw ⭐ 31670 Rust - ZeroClaw is a fast, small, and fully autonomous AI personal assistant infrastructure built in Rust, designed for multi-channel interaction, provider agnosticism, and on-premises execution with stro...

↑ Back to TOC

Stateful Serverless Frameworks

• BerriAI/litellm ⭐ 48881 Python - LiteLLM is a Python SDK and proxy server that provides a unified OpenAI-compatible interface to call over 100 large language model APIs from multiple providers, featuring consistent output, retry logic, budget controls, and extensive observability integrations.
• emcie-co/parlant ⭐ 17645 Python - Parlant is a Conversation Modeling engine that enables precise, consistent, and reliable control over GenAI-driven conversational agents by enforcing structured behavioral guidelines and adapting dynamically to user interactions.
• FlowiseAI/Flowise ⭐ 53239 TypeScript - Flowise is an open-source drag-and-drop platform that enables users to easily build and deploy customized Large Language Model (LLM) application workflows with a user-friendly interface and flexible deployment options.
• OpenBMB/ToolBench ⭐ 5653 Python - ToolBench is an open platform for training, serving, and evaluating large language models with advanced tool-use capabilities using a large-scale, richly annotated dataset of real-world APIs.

↑ Back to TOC

AI Agent Development

• adenhq/hive ⭐ 10471 Python - Hive is an outcome-driven agent development framework that builds, evolves, and operates self-improving AI agents through natural language goals, dynamic node graphs, and real-time monitoring for reliable business process automation.
• agent-infra/sandbox ⭐ 4872 Python - agent-infra/sandbox is an all-in-one sandbox environment combining browser, shell, file system, MCP services, and VSCode Server in a single Docker container to provide a unified, secure, and versatile platform for AI agents and developers.
• Alibaba-NLP/DeepResearch ⭐ 18114 Python - Tongyi DeepResearch is an advanced open-source large language model by Alibaba designed for deep, long-horizon information-seeking tasks with state-of-the-art agentic search performance.
• areal-project/AReaL ⭐ 5239 Python - AReaL is an asynchronous reinforcement learning infrastructure for training large-scale reasoning and agentic models, making AI agent development accessible, efficient, and cost-effective.
• bytedance/trae-agent ⭐ 10696 Python - Trae Agent is an LLM-based agent with a modular, research-friendly architecture designed to execute complex software engineering tasks via a natural language CLI interface using multiple LLM providers.
• CaviraOSS/OpenMemory ⭐ 4172 TypeScript - OpenMemory is an open-source, self-hosted long-term memory system that enhances AI by providing persistent, multi-sector, and explainable memory capabilities with high performance and user isolation.
• codelion/optillm ⭐ 4075 Python - OptiLLM is an OpenAI API compatible optimizing inference proxy that enhances the accuracy and performance of large language models by applying advanced reasoning and decoding techniques during inference.
• coze-dev/coze-loop ⭐ 5294 Go - Coze Loop is an open-source AI agent optimization platform providing full-lifecycle management from prompt development and debugging to evaluation and monitoring, enabling efficient AI agent development and operation.
• coze-dev/coze-studio ⭐ 19730 TypeScript - Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.
• crynta/terax-ai ⭐ 6134 TypeScript - Terax is a lightweight, AI-native development workspace built with Tauri 2, Rust, and React, offering a terminal, code editor, source control, and agentic AI features.
• FareedKhan-dev/all-agentic-architectures ⭐ 3418 Jupyter Notebook - All Agentic Architectures is a comprehensive repository offering practical implementations of over 17 advanced AI agentic architectures, designed to educate and empower developers in building intelligent, adaptive, and collaborative AI systems.
• Gitlawb/openclaude ⭐ 28129 TypeScript - OpenClaude is an open-source command-line interface designed for coding agents, supporting both cloud and local model providers, offering a unified workflow for various AI models.
• google/adk-go ⭐ 6805 Go - An open-source Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and cloud-native support.
• hiyouga/LLaMA-Factory ⭐ 71747 Python - LLaMA Factory is a unified and efficient platform for fine-tuning over 100 large language and vision-language models, offering scalable training methods, advanced optimization algorithms, and versatile deployment options.
• huggingface/smolagents ⭐ 27627 Python - Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.
• inclusionAI/AReaL ⭐ 3470 Python - AReaL is an open-source, fully asynchronous reinforcement learning system designed for large reasoning and agentic models, offering flexibility, scalability, and state-of-the-art performance for building advanced AI agents.
• instructor-ai/instructor ⭐ 13077 Python - Instructor is a popular Python library that enables structured output handling and validation for large language models, supporting multiple LLM providers and offering features like retry management and streaming support.
• JCodesMore/ai-website-cloner-template ⭐ 15847 TypeScript - This project provides a reusable template for using AI coding agents to reverse-engineer any website into a modern Next.js codebase, facilitating platform migration or source code recovery.
• JoshuaC215/agent-service-toolkit ⭐ 4297 Python - AI Agent Service Toolkit is a comprehensive framework for building, deploying, and interacting with AI agents using LangGraph, FastAPI, and Streamlit, featuring multi-agent support, streaming, content moderation, and a user-friendly chat interface.
• MemMachine/MemMachine ⭐ 4304 Python - MemMachine is an open-source universal memory layer that enables AI agents to store, recall, and manage multiple types of memory to create personalized, context-aware AI assistants for various applications.
• microsoft/agent-lightning ⭐ 12482 Python - Agent Lightning is a flexible server-client framework that enables training and optimization of AI agents using reinforcement learning and other algorithms with minimal code changes.
• MiroMindAI/MiroThinker ⭐ 8215 Python - MiroThinker is an open-source research agent model designed for advanced tool-augmented reasoning and complex information-seeking tasks, achieving state-of-the-art performance across multiple benchmarks.
• NVIDIA-NeMo/Guardrails ⭐ 5585 Python - NeMo Guardrails is an open-source toolkit by NVIDIA for adding programmable guardrails to large language model-based conversational systems to ensure safer, controlled, and trustworthy interactions.
• OpenPipe/ART ⭐ 8488 Python - OpenPipe/ART is an open-source reinforcement learning framework that trains multi-step agents for real-world tasks using GRPO and innovative zero-shot reward scoring with LLMs.
• pguso/ai-agents-from-scratch ⭐ 4187 JavaScript - AI Agents From Scratch is an educational repository that teaches users to build AI agents locally using local LLMs and node-llama-cpp, focusing on understanding agent architectures, function calling, memory, and the ReAct pattern through progressive, hands-on examples.
• pinpoint-apm/pinpoint ⭐ 13803 Java - Pinpoint is an APM tool for large-scale distributed systems that provides real-time monitoring, transaction tracing, and detailed performance analysis with minimal impact on application performance.
• plastic-labs/honcho ⭐ 4583 Python - Honcho is a memory infrastructure for building stateful agents that understand and adapt to changing entities over time, providing reasoning-first memory and multi-peer perspectives.
• TaskingAI/TaskingAI ⭐ 5377 Python - TaskingAI is an open-source BaaS platform for developing, managing, and deploying AI-native applications using large language models with unified APIs, customizable tools, and multi-tenant support.
• Tencent/TencentDB-Agent-Memory ⭐ 4502 TypeScript - TencentDB Agent Memory provides a local, 4-tier progressive memory pipeline for AI Agents, optimizing token usage and improving task success without external API dependencies.
• transitive-bullshit/agentic ⭐ 18121 TypeScript - Agentic is a versatile AI agent standard library that integrates with any large language model and TypeScript AI SDK, providing a comprehensive set of AI functions and tools for building intelligent applications.
• UnicomAI/wanwu ⭐ 4096 Go - Wanwu is an enterprise-grade, multi-tenant AI agent development platform by China Unicom that supports intelligent agents, workflows, model management, and integrates large language models with business process automation for digital transformation and business innovation.
• volcengine/OpenViking ⭐ 24975 Python - OpenViking is an open-source context database designed specifically for AI Agents, using a file system paradigm for hierarchical context management and self-evolving capabilities.
• walkinglabs/learn-harness-engineering ⭐ 7342 TypeScript - Learn Harness Engineering is a project-based course teaching how to build robust environments for AI coding agents, ensuring reliability and effective operation.
• zai-org/GLM-4.5 ⭐ 4080 Python - GLM-4.5 is an open-source large language model designed for intelligent agents, featuring hybrid reasoning capabilities and high performance across industry benchmarks.

↑ Back to TOC

AI Agent Orchestration

• BloopAI/vibe-kanban ⭐ 19924 Rust - Vibe Kanban is a Kanban board tool designed to manage and orchestrate AI coding agents, enabling efficient task tracking and workflow optimization in AI-assisted software development.
• code-yeongyu/oh-my-opencode ⭐ 60482 TypeScript - Oh My OpenCode is a powerful, agent-driven coding assistant platform that enhances software development by orchestrating asynchronous AI subagents, integrating multiple LLM models, and providing advanced tools like LSP and AST for a seamless and efficient coding experience.
• elizaOS/eliza ⭐ 18491 TypeScript - Eliza is a versatile AI agent operating system that enables the creation and deployment of autonomous agents across multiple platforms with extensible features and document interaction capabilities.
• langchain-ai/open-swe ⭐ 5216 TypeScript - Open SWE is an open-source asynchronous coding agent that autonomously plans and executes code changes across repositories with human-in-the-loop support and GitHub integration.
• LazyAGI/LazyLLM ⭐ 3839 Python - LazyLLM is a low-code development tool that simplifies building, deploying, and optimizing multi-agent large language model applications through an iterative development workflow.
• NirDiamant/agents-towards-production ⭐ 20565 Jupyter Notebook - Agents Towards Production is an open-source repository offering end-to-end tutorials and blueprints for building scalable, production-grade Generative AI agents from concept to deployment.
• ruvnet/claude-flow ⭐ 13403 JavaScript - Claude-Flow is an enterprise-grade AI orchestration platform that enables deployment and coordination of intelligent multi-agent swarms and autonomous workflows for building advanced conversational AI systems.
• steveyegge/beads ⭐ 24248 Go - Beads is a graph-based issue tracker that upgrades AI coding agents' memory and task management capabilities by organizing complex workstreams into interconnected issues for improved long-term planning and execution.
• strands-agents/sdk-python ⭐ 5988 Python - Strands Agents is a Python SDK that enables building and deploying AI agents using a model-driven approach, supporting multiple AI models and advanced features like multi-agent systems and MCP integration.
• superset-sh/superset ⭐ 11473 TypeScript - Superset is a desktop application (macOS) designed to orchestrate and manage multiple CLI-based AI coding agents in parallel, using Git worktrees for isolated task execution.
• tambo-ai/tambo ⭐ 10978 TypeScript - Tambo AI is a React library that simplifies building AI-powered assistants and agents with features like thread management, state persistence, and AI-generated components for creating generative and personalized user experiences.
• ValueCell-ai/ClawX ⭐ 7342 TypeScript - ClawX is a desktop application that provides a graphical user interface for managing and orchestrating OpenClaw AI agents, eliminating the need for command-line interaction.
• YaoApp/yao ⭐ 7542 Go - Yao is an open-source engine for building autonomous, proactive agents that self-schedule tasks and collaborate dynamically using event-driven triggers and integrated knowledge systems.
• Yeachan-Heo/oh-my-claudecode ⭐ 35447 TypeScript - Oh-my-claudecode is a multi-agent orchestration framework for Claude Code that enables complex autonomous workflows with multiple execution modes, specialized agents, and a natural language interface for zero learning curve and optimized performance.

↑ Back to TOC

LLM Framework Tools

• 567-labs/instructor ⭐ 12443 Python - Instructor is a popular Python library that simplifies working with structured outputs from large language models by providing validation, retries, and streaming support across multiple LLM providers.
• google/adk-samples ⭐ 9550 Python - A collection of sample agents built with the Agent Development Kit (ADK) to accelerate development of conversational and multi-agent workflows, designed for customization and integration with Google Cloud services.
• langfuse/langfuse ⭐ 28283 TypeScript - Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features.
• modelscope/modelscope-agent ⭐ 4283 Python - ModelScope-Agent is a customizable and scalable agent framework that connects large language models with real-world applications, enabling role-playing, tool usage, planning, and memory functionalities through a unified and extensible interface.
• shroominic/codeinterpreter-api ⭐ 3865 Python - An open-source API that implements the ChatGPT Code Interpreter for sandboxed Python code execution, enabling data analysis, visualization, and interactive AI-driven computational tasks with local execution and scalable production deployment.
• TEN-framework/ten_framework ⭐ 10622 C - TEN is a high-performance AI agent framework for creating real-time conversational and multimodal AI agents with edge-cloud integration and cross-platform support.
• TEN-framework/ten-framework ⭐ 10084 C - TEN Framework is a real-time, distributed, cloud-edge collaborative multimodal AI agent framework supporting multiple programming languages for building high-performance AI applications.
• truefoundry/cognita ⭐ 4411 Python - Cognita is an open-source, modular, and production-ready RAG framework by TrueFoundry that simplifies building, customizing, and deploying scalable Retrieval Augmented Generation applications with a no-code UI and extensive integration features.

↑ Back to TOC

AI Agent Deployment

• alibaba/nacos ⭐ 32992 Java - Nacos is a dynamic service discovery, configuration, and service management platform designed to simplify building and managing cloud-native applications and microservices.
• alibaba/OpenSandbox ⭐ 10903 Python - OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for secure and isolated execution in variou...
• e2b-dev/E2B ⭐ 10706 MDX - E2B is an open-source secure cloud runtime infrastructure that enables safe execution of AI-generated code in isolated sandboxes for AI applications and agents.
• firebase/genkit ⭐ 6076 TypeScript - Genkit is an open-source framework that enables developers to build, integrate, and test AI-powered applications with a unified API, plugin architecture, and tools for observability and evaluation across various AI models and platforms.
• GoogleCloudPlatform/agent-starter-pack ⭐ 5621 Python - A collection of production-ready Generative AI Agent templates for Google Cloud that accelerates development by addressing deployment, evaluation, customization, and observability challenges.
• ollama/ollama ⭐ 172766 Go - Ollama is a versatile platform that enables easy deployment, customization, and management of large language models locally across multiple operating systems with support for various model formats and a REST API.
• TencentCloud/CubeSandbox ⭐ 6028 Rust - Cube Sandbox is a secure, high-performance, and lightweight sandbox service for AI agents, built on RustVMM and KVM, offering instant cold starts and hardware-level isolation.
• zebbern/claude-code-guide ⭐ 4219 - Claude Code Guide is a comprehensive and authoritative resource providing detailed instructions, tips, and references for using the Claude Code CLI tool to interact with the Claude AI model, including advanced features and MCP integration.

↑ Back to TOC

AI Application Development

• 0xPlaygrounds/rig ⭐ 7475 Rust - Rig is a Rust library for building scalable, modular, and ergonomic fullstack agents powered by large language models, supporting multiple LLM providers and vector stores for AI integration.
• crestalnetwork/intentkit ⭐ 6489 Python - IntentKit is an open-source autonomous agent framework that enables the creation and management of AI agents with blockchain and social media integrations, featuring an extensible skill and plugin system.
• daytonaio/daytona ⭐ 61148 TypeScript - Daytona is a secure and elastic infrastructure platform designed for safely running AI-generated code with high performance and scalability.
• e2b-dev/awesome-ai-agents ⭐ 25523 - A curated and comprehensive list of AI autonomous agents categorized into open-source and closed-source projects, serving as a valuable resource for exploring, building, and contributing to AI agent development.
• GoogleCloudPlatform/generative-ai ⭐ 12593 Jupyter Notebook - A comprehensive repository of sample code, notebooks, and resources for developing and managing generative AI workflows on Google Cloud using Gemini models on Vertex AI.
• langgenius/dify ⭐ 128252 TypeScript - Dify is an open-source platform for developing and deploying AI applications using large language models, featuring workflow building, model management, agent capabilities, and observability tools.
• microsandbox/microsandbox ⭐ 6369 Rust - Microsandbox is a self-hosted platform that enables secure, fast, and isolated execution of untrusted user or AI-generated code using hardware-level microVMs and supports multiple programming languages through SDKs.
• mlflow/mlflow ⭐ 23916 Python - MLflow is an open-source platform that manages the full machine learning lifecycle, providing tools for experiment tracking, model packaging, deployment, evaluation, and observability in one integrated solution.
• mnfst/manifest ⭐ 6712 TypeScript - Manifest is an open-source components library built on shadcn/ui for creating customizable and production-ready UI components to develop ChatGPT and conversational AI applications efficiently.
• Nixtla/nixtla ⭐ 3892 Jupyter Notebook - TimeGPT-1 by Nixtla is a production-ready generative pretrained transformer model designed for accurate time series forecasting and anomaly detection across multiple domains with zero-shot inference and fine-tuning capabilities.
• opactorai/Claudable ⭐ 3972 TypeScript - Claudable is an open-source AI-powered web app builder that converts natural language descriptions into production-ready Next.js applications with instant preview and one-click deployment to Vercel.
• openinterpreter/open-interpreter ⭐ 63754 Python - Open Interpreter is an open-source natural language interface that enables users to run code locally and interact with their computers through conversational commands, combining the power of large language models with local computing flexibility.
• purocean/yn ⭐ 6622 TypeScript - Yank Note is a highly extensible Markdown editor featuring AI assistance, version control, encryption, code execution, and rich multimedia embedding for enhanced productivity.
• pydantic/pydantic-ai ⭐ 13789 Python - PydanticAI is a Python agent framework that simplifies building production-grade Generative AI applications by providing type-safe, structured, and model-agnostic integration with multiple LLMs, along with features like dependency injection and real-time debugging.
• zenml-io/zenml ⭐ 5427 Python - ZenML is a comprehensive AI platform that enables the creation, deployment, and management of machine learning and AI workflows across diverse infrastructure backends with integrated tracking, containerization, and tool interoperability.

↑ Back to TOC

AI Developer Toolkit

• agiresearch/AIOS ⭐ 4859 Python - AIOS is an AI Agent Operating System that integrates large language models into an OS environment to facilitate the development, deployment, and management of AI agents with robust resource and tool management.
• GaiaNet-AI/gaianet-node ⭐ 5004 Shell - GaiaNet Node is a decentralized AI agent platform that enables users to install, run, and deploy their own AI nodes with customizable models and configurations.
• google/adk-python ⭐ 19943 Python - An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.
• googleworkspace/cli ⭐ 26710 Rust - gws is a command-line interface for Google Workspace APIs, dynamically built from the Google Discovery Service, offering automation and AI agent skills integration.
• kyrolabs/awesome-langchain ⭐ 9387 - A curated and comprehensive list of tools, projects, and resources centered around the LangChain framework for developing and deploying large language model applications.
• max-sixty/worktrunk ⭐ 5282 Rust - Worktrunk is a CLI tool that simplifies Git worktree management, particularly for parallel AI agent workflows, by making worktrees as easy to use as branches.
• pietrozullo/mcp-use ⭐ 10018 Python - MCP-Use is an open-source client library that enables seamless integration of any large language model with MCP servers to build custom agents with tool access and dynamic server management.
• ragapp/ragapp ⭐ 4404 TypeScript - RAGapp is an enterprise-ready platform that simplifies deploying and managing Agentic Retrieval-Augmented Generation systems using Docker and LlamaIndex, enabling secure and customizable AI model integration on private cloud infrastructure.
• reworkd/AgentGPT ⭐ 36156 TypeScript - AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.
• unslothai/unsloth ⭐ 51421 Python - Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.
• x-cmd/x-cmd ⭐ 4434 Shell - X-CMD is a compact, AI-powered command-line toolkit that bootstraps over 1000 CLI tools, offers extensive environment management, secure sandboxing, and a stylish terminal experience to enhance productivity and streamline development workflows.

↑ Back to TOC

AI Agent Operating System

• Arindam200/awesome-ai-apps ⭐ 12555 Jupyter Notebook - A comprehensive repository showcasing practical examples, tutorials, and tools for building powerful AI applications using large language models and various AI agent frameworks.
• HKUDS/AutoAgent ⭐ 8501 Python - AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language, featuring top GAIA benchmark performance and broad LLM support.
• mcp-use/mcp-use ⭐ 9293 Python - mcp-use is an open-source unified client library that enables seamless integration of any LangChain-supported LLM with MCP servers to build custom agents with tool access.
• MemTensor/MemOS ⭐ 4846 Python - MemOS is an operating system for Large Language Models that enhances their capabilities with long-term memory, enabling more context-aware, consistent, and personalized AI interactions through a modular and extensible memory architecture.
• PySpur-Dev/pyspur ⭐ 5735 TypeScript - PySpur is a visual playground that enables AI engineers to rapidly build, debug, and deploy AI agents with enhanced visibility, human-in-the-loop workflows, and multimodal support.
• Q00/ouroboros ⭐ 4381 Python - Ouroboros is an Agent OS for AI coding, providing a local-first runtime for replayable, specification-first AI coding workflows across multiple LLM CLIs.
• RightNow-AI/openfang ⭐ 17695 Rust - OpenFang is an open-source agent operating system powered by Rust, designed to provide a robust framework for developing and managing AI agents.

↑ Back to TOC

AI Agent Gateway

• Arize-ai/phoenix ⭐ 9932 Jupyter Notebook - Phoenix is an open-source AI observability platform that enables tracing, evaluation, and optimization of large language model applications across various deployment environments.
• casdoor/casdoor ⭐ 13697 Go - Casdoor is an open-source, AI-first Identity and Access Management (IAM) and AI Model Context Protocol (MCP) gateway with a web UI supporting various authentication and authorization standards.
• cloudflare/agents ⭐ 5014 TypeScript - Cloudflare Agents is a framework for building and deploying intelligent, stateful AI agents that operate autonomously at the edge of the network with real-time communication and persistent memory.
• decolua/9router ⭐ 15458 JavaScript - 9Router is an AI router and token saver that connects various AI coding tools to over 40 providers and 100+ models, optimizing costs and ensuring continuous coding access through auto-fallback and ...
• e2b-dev/fragments ⭐ 6301 TypeScript - Fragments by E2B is an open-source Next.js template for building AI-generated applications with secure code execution, multi-stack support, and integration with various large language model providers.
• mastra-ai/mastra ⭐ 20630 TypeScript - Mastra is a TypeScript AI agent framework that enables rapid development of AI applications with support for multiple LLMs, advanced agents, workflows, RAG, integrations, and automated evaluations.
• simstudioai/sim ⭐ 26287 TypeScript - Sim Studio is an open-source platform for building, testing, and optimizing AI agent workflows with flexible deployment options including cloud and self-hosting.
• superagent-ai/superagent ⭐ 6614 TypeScript - Superagent is an open-source AI assistant framework and API that enables developers to build and integrate powerful AI agents into applications using large language models and generative AI technologies.
• TransformerOptimus/SuperAGI ⭐ 17553 Python - SuperAGI is an open-source autonomous AI agent framework that enables developers to build, manage, and deploy scalable and efficient autonomous AI agents with extensible capabilities through toolkits and a user-friendly interface.
• Upsonic/Upsonic ⭐ 7866 Python - Upsonic is a reliability-focused AI agent framework that supports Model Context Protocol (MCP) and provides advanced features for trustworthy, production-ready AI agent workflows with integrated tool use and secure runtime environments.
• xlang-ai/OpenAgents ⭐ 4690 Python - OpenAgents is an open platform providing versatile language agents for data analysis, plugin integration, and autonomous web browsing, designed for real-world applications and easy deployment.

↑ Back to TOC

MCP Server Framework

• AgentOps-AI/agentops ⭐ 5586 Python - AgentOps is a Python SDK providing observability, cost tracking, benchmarking, and security tools for AI agents and large language models, integrating with major agent frameworks to support developers from prototype to production.
• aipotheosis-labs/aci ⭐ 4724 Python - ACI.dev is an open-source platform that connects AI agents to over 600 tool integrations with multi-tenant authentication, granular permissions, and access via direct function calls or a unified MCP server, enabling production-ready AI agent development without infrastructure complexity.
• campfirein/cipher ⭐ 3479 TypeScript - Cipher is an open-source memory layer designed for AI coding agents, enabling seamless memory and context management across multiple IDEs and AI assistants with MCP integration.
• casibase/casibase ⭐ 5107 Go - Casibase is an open-source enterprise-level AI Cloud OS that provides a knowledge base and agent management platform with admin UI, user management, Single-Sign-On, and support for multiple AI models including ChatGPT and Claude.
• googleapis/genai-toolbox ⭐ 12682 Go - MCP Toolbox for Databases is an open-source MCP server that simplifies and secures the development and management of AI tools interacting with databases, enabling natural language queries, automation, and enhanced observability.
• googleapis/mcp-toolbox ⭐ 15414 Go - MCP Toolbox for Databases is an open-source MCP server that connects AI agents, IDEs, and applications directly to enterprise databases, providing prebuilt tools and a framework for custom tool dev...
• grab/cursor-talk-to-figma-mcp ⭐ 6803 JavaScript - Cursor Talk to Figma MCP is an integration that enables Cursor AI to communicate with Figma programmatically for reading and modifying designs, automating and enhancing the design workflow.
• Helicone/helicone ⭐ 5765 TypeScript - Helicone is an open-source LLM observability platform that enables developers to monitor, evaluate, and experiment with large language model applications through easy integration and comprehensive tools.
• Klavis-AI/klavis ⭐ 5750 TypeScript - Klavis AI is an open-source project offering production-ready MCP integration and scalable infrastructure for AI applications across multiple platforms with built-in authentication and extensive tool support.
• nukeop/nuclear ⭐ 17707 TypeScript - Nuclear is a free, open-source, de-centralized music player that streams from various sources, includes a plugin system for expanded functionality, and offers an MCP server for AI agent integration.
• PrefectHQ/fastmcp ⭐ 25415 Python - FastMCP is a Pythonic framework for building Model Context Protocol (MCP) servers and clients, designed to simplify interactions with LLMs and other AI models.
• thedaviddias/Front-End-Checklist ⭐ 72769 MDX - Front-End Checklist is an open-source quality system for web development, providing a comprehensive checklist for modern front-end best practices, available as a website, MCP server, and a direct R...
• trycua/cua ⭐ 12197 Python - c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.

↑ Back to TOC

Image Processing & Analysis Agents

• 11cafe/jaaz ⭐ 6316 TypeScript - Jaaz is a local and free AI design agent that enables users to design, edit, and generate images, posters, and storyboards with advanced AI-powered tools and a creative canvas for fast iterations.
• apple/ml-ferret ⭐ 8685 Python - Ferret is an end-to-end multimodal large language model developed by Apple that excels in fine-grained referring and grounding tasks with open vocabulary, supported by a large-scale dataset and evaluation benchmark for research purposes.
• THUDM/CogVLM ⭐ 6741 Python - CogVLM and CogAgent are state-of-the-art open-source visual language models designed for advanced image understanding, multi-turn dialogue, and GUI agent capabilities, achieving top performance on multiple cross-modal benchmarks.

↑ Back to TOC

Video Processing Agents

• GetStream/Vision-Agents ⭐ 7869 Python - Open Vision Agents by Stream is a platform for building real-time, low-latency multi-modal AI agents that understand and interact with video content using advanced models and Stream's edge network.
• RayVentura/ShortGPT ⭐ 7372 Python - ShortGPT is an AI-powered framework that automates video content creation and editing for platforms like YouTube Shorts and TikTok, supporting multi-language voiceovers and automated footage sourcing.
• showlab/Awesome-Video-Diffusion ⭐ 5285 - A curated list of recent diffusion models and resources for video generation, editing, restoration, and various AI-driven video applications.

↑ Back to TOC

Job Automation Tools

• activepieces/activepieces ⭐ 22498 TypeScript - Activepieces is an open-source AI automation platform that provides an extensible, no-code builder framework with over 280 MCP servers for AI agents, enabling seamless AI workflows and integrations.
• feder-cr/Jobs_Applier_AI_Agent_AIHawk ⭐ 29308 Python - AIHawk is an AI-powered tool that automates and streamlines the job application process to help job seekers efficiently apply to multiple jobs with tailored applications.
• huginn/huginn ⭐ 49382 Ruby - Huginn is an open-source platform that enables users to create customizable agents to automate online tasks, monitor events, and perform actions securely on their own server.
• microsoft/magentic-ui ⭐ 9877 Python - Magentic-UI is a human-centered research prototype featuring a multi-agent system that automates complex web tasks with user collaboration, transparency, and control.
• qax-os/excelize ⭐ 20254 Go - Excelize is a Go library for reading, writing, and manipulating Microsoft Excel spreadsheet files with support for charts, images, and large datasets.

↑ Back to TOC

Inventory Automation Agents

• FellouAI/eko ⭐ 4848 TypeScript - Eko is a production-ready JavaScript framework that enables developers to build reliable, multi-step agentic workflows using natural language commands across computer and browser environments.
• firerpa/lamda ⭐ 7589 Python - FIRERPA/lamda is a robust and versatile Android RPA framework designed for next-generation mobile automation, supporting a wide range of Android versions and environments with extensive APIs and Python SDK for seamless AI integration and device control.
• microsoft/UFO ⭐ 8051 Python - UFO is a UI-Focused multi-agent framework that automates and navigates Windows OS applications using AI agents powered by GPT-4V to fulfill complex user requests across multiple applications.
• OpenInterpreter/open-interpreter ⭐ 62442 Python - Open Interpreter is an open-source natural language interface that enables users to run code locally on their computers through a chat-based system, facilitating tasks like multimedia editing, browser control, and data analysis with full user approval and flexibility beyond hosted solutions.
• sigoden/aichat ⭐ 9179 Rust - AIChat is an all-in-one command-line interface tool that integrates multiple large language models and provides features like Shell Assistant, Chat-REPL, RAG, AI Tools, and Agents for enhanced AI-driven command-line productivity.

↑ Back to TOC

Workflow Automation Assistants

• AIDC-AI/ComfyUI-Copilot ⭐ 4465 TypeScript - ComfyUI-Copilot is an AI-powered intelligent assistant for the Comfy-UI framework that enhances workflow automation, provides natural language node recommendations, and offers real-time development support to simplify AI algorithm debugging and deployment.
• dtyq/magic ⭐ 4832 PHP - Magic is the first open-source all-in-one AI productivity platform offering a comprehensive product matrix to help enterprises build and deploy intelligent AI applications for enhanced productivity.
• enescingoz/awesome-n8n-templates ⭐ 22622 - A comprehensive open-source collection of over 280 free n8n automation templates for various services, including AI agents, RAG chatbots, email, social media, and DevOps.
• n8n-io/self-hosted-ai-starter-kit ⭐ 13974 - The Self-hosted AI Starter Kit by n8n is an open-source Docker Compose template that quickly sets up a secure, local AI and low-code development environment integrating n8n, Ollama, Qdrant, and PostgreSQL for building self-hosted AI workflows.
• Significant-Gravitas/AutoGPT ⭐ 184683 Python - AutoGPT is a powerful AI platform that enables users to create, deploy, and manage continuous AI agents to automate complex workflows with options for self-hosting and cloud deployment.

↑ Back to TOC

AI Platform Configurators

• 1Panel-dev/1Panel ⭐ 35695 Go - 1Panel is a web-based server management panel designed for Linux/VPS, simplifying the administration of OpenClaw agents, local LLMs, websites, databases, containers, files, and scheduled tasks.
• ashishpatel26/500-AI-Agents-Projects ⭐ 23435 - A curated collection of over 500 AI agent use cases across multiple industries, showcasing practical applications and linking to open-source projects for implementation.
• calcom/cal.com ⭐ 44895 TypeScript - Cal.com is an open-source, customizable scheduling platform that offers full control over scheduling data and workflows, serving as a versatile alternative to Calendly.
• OpenBMB/XAgent ⭐ 8530 Python - XAgent is an open-source autonomous LLM-driven agent designed to automatically solve complex tasks with safety, extensibility, and human collaboration features.

↑ Back to TOC

IDE Integrations

• coder/coder ⭐ 12110 Go - Coder is a platform for creating secure, self-hosted cloud development environments that streamline developer onboarding and optimize resource usage through automation and integrations.
• continuedev/continue ⭐ 33477 TypeScript - Continue is an open-source platform that enables developers to create, share, and use custom AI code assistants within popular IDEs, enhancing coding productivity and collaboration through features like Chat, Autocomplete, Edit, and Agent.
• eth-sri/lmql ⭐ 4185 Python - LMQL is a Python-superset programming language designed for constraint-guided and efficient interaction with large language models, enabling advanced control flow, decoding, and integration with multiple LLM providers.
• sweepai/sweep ⭐ 7708 Jupyter Notebook - Sweep is an AI-powered coding assistant plugin designed to enhance productivity and coding efficiency within JetBrains IDEs.

↑ Back to TOC

Code Generation & Refactoring

Documentation & Testing Assistants

• idosal/git-mcp ⭐ 8120 TypeScript - GitMCP is a free, open-source remote MCP server that transforms any GitHub project into an AI-accessible documentation hub to eliminate code hallucinations and provide accurate, up-to-date project information.
• steipete/agent-rules ⭐ 5686 Shell - Agent Rules is a repository of reusable rules and knowledge documents designed to improve the effectiveness of AI coding assistants like Claude Code and Cursor in software development workflows.

↑ Back to TOC

Desktop Automation

• asweigart/pyautogui ⭐ 12142 Python - PyAutoGUI is a cross-platform Python module that enables programmatic control of the mouse and keyboard for GUI automation, including features like screen capture and image recognition.
• bytebot-ai/bytebot ⭐ 11040 TypeScript - Bytebot is a containerized Linux desktop environment that enables programmatic control and remote access for automation, scraping, CI tasks, and remote work through a unified REST API and VNC interfaces.
• bytedance/UI-TARS-desktop ⭐ 25080 TypeScript - UI-TARS Desktop is a GUI Agent application that uses a Vision-Language Model to enable natural language control of computers across multiple platforms with real-time visual recognition and automation capabilities.
• iflytek/astron-rpa ⭐ 6135 Python - AstronRPA is an enterprise-grade open-source Robotic Process Automation desktop application that enables low-code/no-code workflow automation for desktop and web applications with strong enterprise security, collaboration, and AI agent integration.
• jacklandrin/OnlySwitch ⭐ 5694 Swift - OnlySwitch is a customizable all-in-one macOS menu bar app that consolidates system toggles, shortcuts, and AI-powered controls to enhance user productivity and convenience.
• mediar-ai/screenpipe ⭐ 16619 TypeScript - Screenpipe is an open-source AI app store that continuously records and indexes 24/7 desktop and microphone activity locally, enabling developers to build highly contextual AI-powered desktop applications called pipes, which can be shared, monetized, and run securely in a sandboxed environment.
• OthersideAI/self-operating-computer ⭐ 10248 Python - The Self-Operating Computer Framework enables multimodal AI models to autonomously operate a computer by interpreting screen visuals and executing mouse and keyboard actions to achieve user-defined objectives.
• wonderwhy-er/DesktopCommanderMCP ⭐ 6093 TypeScript - Desktop Commander MCP is a server that integrates with the Claude desktop app to provide terminal control, file system search, and diff-based file editing capabilities, enabling advanced AI-assisted desktop management.
• yuruotong1/autoMate ⭐ 3919 Python - autoMate is an AI-driven local automation assistant that uses natural language commands to enable users to automate complex computer tasks without programming, supporting local deployment and full interface control for enhanced privacy and flexibility.

↑ Back to TOC

Browser & Web Automation

NL AI Frameworks

• apache/doris ⭐ 15413 Java - Apache Doris is a high-performance, real-time analytical database with a storage-compute integrated architecture, designed for sub-second query response and high concurrency in diverse data analysis scenarios.
• business-science/ai-data-science-team ⭐ 4644 Python - AI Data Science Team is a Python library featuring AI-powered agents that automate and accelerate common data science tasks, including data cleaning, feature engineering, machine learning, and exploratory data analysis, to improve productivity and efficiency.
• infiniflow/ragflow ⭐ 81615 TypeScript - RAGFlow is an open-source Retrieval-Augmented Generation engine that leverages deep document understanding and Large Language Models to provide accurate, citation-backed question-answering from complex and diverse data sources.
• pydantic/pydantic ⭐ 27906 Python - Pydantic is a Python library for fast and extensible data validation using Python type hints, enabling developers to define and validate data models efficiently.
• ScrapeGraphAI/Scrapegraph-ai ⭐ 22445 Python - ScrapeGraphAI is an AI-powered Python library that creates intelligent web scraping pipelines using large language models to extract structured data from websites and local documents efficiently.
• ucbepic/docetl ⭐ 3503 Python - DocETL is a system for creating and executing complex document processing and data transformation pipelines powered by large language models, featuring an interactive UI playground and a Python package for production use.

↑ Back to TOC

Document Analytics Platforms

• Tencent/WeKnora ⭐ 12700 Go - WeKnora is an LLM-powered modular framework for deep document understanding, semantic retrieval, and context-aware question answering using the Retrieval-Augmented Generation paradigm.

↑ Back to TOC

Financial & Trading Systems

• brokermr810/QuantDinger ⭐ 7052 JavaScript - QuantDinger is an open-source, self-hosted AI quantitative trading platform that bridges AI research with live trading execution, offering tools for strategy development, backtesting, and monitoring.
• Fincept-Corporation/FinceptTerminal ⭐ 24845 C++ - FinceptTerminal is a sophisticated C++20 desktop application leveraging Qt6 and embedded Python for comprehensive financial market analysis, investment research, and algorithmic trading, offering e...
• HKUDS/Vibe-Trading ⭐ 9210 Python - Vibe-Trading is an AI-powered personal trading agent designed for algorithmic trading, backtesting, and automated financial operations.
• TauricResearch/TradingAgents ⭐ 81322 Python - TradingAgents is an open-source multi-agent financial trading framework leveraging large language models to simulate real-world trading firm dynamics and collaboratively make informed trading decisions.
• ValueCell-ai/valuecell ⭐ 10763 Python - ValueCell is a community-driven, multi-agent platform that leverages AI to provide comprehensive financial applications including stock research, automated trading, and market analysis across multiple global markets.

↑ Back to TOC

Educational & Learning Agents

• ashishps1/learn-ai-engineering ⭐ 5656 - A comprehensive collection of free resources to learn AI, machine learning, large language models, and AI agents from scratch.
• microsoft/ai-agents-for-beginners ⭐ 66107 Jupyter Notebook - AI Agents for Beginners is a Microsoft educational course with 10 lessons teaching the fundamentals and practical skills to build AI agents using Azure AI and GitHub models, supported by multi-language resources and community engagement.

↑ Back to TOC

Generative Agents Simulation

• joonspk-research/generative_agents ⭐ 21435 - This project provides a simulation framework for generative agents that mimic believable human behaviors within an interactive game environment, enabling running, saving, replaying, and demonstrating agent-based simulations.
• linyiLYi/street-fighter-ai ⭐ 6523 Python - SFighterAI is a deep reinforcement learning-based AI agent designed to master and beat the final boss in Street Fighter II: Special Champion Edition using only game screen pixel data.
• MineDojo/Voyager ⭐ 6943 JavaScript - Voyager is an open-ended embodied agent powered by large language models that autonomously explores and learns diverse skills in Minecraft through lifelong learning and an evolving skill library.

↑ Back to TOC

Virtual Town AI

• a16z-infra/ai-town ⭐ 9042 TypeScript - AI Town is a deployable starter kit for building and customizing a virtual town where AI characters live, chat, and socialize, featuring a robust backend and support for multiple LLMs and deployment options.

↑ Back to TOC

Multi-Agent Platforms

• a2aproject/A2A ⭐ 24081 TypeScript - Agent2Agent (A2A) is an open protocol enabling secure communication and interoperability between diverse generative AI agents to foster collaboration and innovation in the AI ecosystem.
• IBM/mcp-context-forge ⭐ 3796 Python - IBM MCP Context Forge is a production-grade Model Context Protocol Gateway that unifies REST and MCP services into a single secure, scalable endpoint for AI clients with federation, virtualization, multi-protocol support, and an optional Admin UI.
• jlowin/fastmcp ⭐ 25415 Python - FastMCP is a Python framework that simplifies building MCP servers and clients, enabling standardized and efficient interactions with large language models through tools, resources, and prompts.
• sonnylazuardi/cursor-talk-to-figma-mcp ⭐ 6803 JavaScript - Cursor Talk to Figma MCP is a project that integrates Cursor AI with Figma using a Model Context Protocol to enable programmatic reading and modification of Figma designs for enhanced design automation and workflow efficiency.

↑ Back to TOC

Communication Protocols

• novuhq/novu ⭐ 39055 TypeScript - Novu is an open-source notification infrastructure providing a unified API for multi-channel communication like in-app, email, SMS, push, and chat, aiming to simplify notification delivery for deve...

↑ Back to TOC

Multimodal Model Benchmarks

• google-deepmind/acme ⭐ 3990 Python - Acme is a flexible and scalable research framework providing modular reinforcement learning components and agents for developing and benchmarking RL algorithms.

↑ Back to TOC

Sensor Fusion Agents

• Alibaba-NLP/WebWalker ⭐ 18296 Python - WebWalker is a benchmarking project by Alibaba-NLP that evaluates large language models' capabilities in web traversal tasks using the WebWalkerQA dataset and a multi-agent framework for effective memory management.

↑ Back to TOC

Browser Automation

UI Interaction

Chatbots

Virtual Assistants

• CherryHQ/cherry-studio ⭐ 46675 TypeScript - Cherry Studio is a cross-platform desktop client that supports multiple large language model providers, offering extensive AI assistant features, document processing, and practical productivity tools in an open-source environment.
• gptme/gptme ⭐ 4315 Python - gptme is a versatile personal AI assistant that operates in your terminal, equipped with tools for coding, file editing, web browsing, and vision, providing a powerful local alternative to popular AI agents for diverse knowledge work.
• khoj-ai/khoj ⭐ 34788 Python - Khoj is a self-hostable personal AI platform that transforms any local or online large language model into a customizable, autonomous AI assistant for research, automation, and document retrieval.
• kortix-ai/suna ⭐ 19423 TypeScript - Suna is an open-source generalist AI assistant that automates real-world tasks through natural conversation, combining browser automation, file management, web crawling, and API integrations in a secure, modular architecture.
• mem0ai/mem0 ⭐ 57237 Python - Mem0 is an open-source memory layer that enhances AI agents and assistants with personalized, adaptive memory capabilities for improved context-aware interactions across various applications.
• menloresearch/jan ⭐ 38287 TypeScript - Jan is an open-source offline AI assistant that serves as a ChatGPT alternative, running locally on various hardware platforms to provide privacy and full user control.

↑ Back to TOC

Human-in-the-Loop Agents

• humanlayer/humanlayer ⭐ 10931 Python - HumanLayer is an API and SDK that enables AI agents to safely interact with humans for feedback and approvals, ensuring human oversight in high-stakes function calls across various communication platforms.

↑ Back to TOC

Runtime Analysis Tools

• fortra/impacket ⭐ 15777 Python - Impacket is a Python library offering low-level programmatic access and implementations for various network protocols, focusing on security research and educational use.
• FunnyWolf/Viper ⭐ 4936 Batchfile - VIPER is a versatile and powerful red team platform that supports adversary simulation and cybersecurity assessments across multiple operating systems, enhanced with AI-driven automation and extensive post-exploitation capabilities.
• vxcontrol/pentagi ⭐ 17358 Go - PentAGI is a fully autonomous AI-driven penetration testing system that integrates professional security tools, multi-agent AI collaboration, and scalable microservices architecture to deliver comprehensive and automated security assessments.
• zylon-ai/private-gpt ⭐ 57220 Python - PrivateGPT is a fully private, offline-capable AI platform that enables users to interact with their documents using Large Language Models through a comprehensive API and user-friendly interface, ensuring data never leaves the user's environment.

↑ Back to TOC

Post-Exploitation Agents

• CyberAlbSecOP/Awesome_GPT_Super_Prompting ⭐ 3609 - A comprehensive curated repository focused on GPT prompt engineering, security vulnerabilities, jailbreak techniques, prompt leaks, injections, and adversarial machine learning for large language models.
• fr0gger/Awesome-GPT-Agents ⭐ 6522 - A curated community-driven repository compiling diverse GPT agents specialized in offensive and defensive cybersecurity tasks, providing AI-powered tools for malware analysis, threat intelligence, vulnerability assessment, and more.
• guardrails-ai/guardrails ⭐ 6949 Python - Guardrails is a Python framework that enhances AI application reliability by providing input/output guards to detect and mitigate risks and generate structured data from large language models.
• Ne0nd0g/merlin ⭐ 5543 Go - Merlin is a cross-platform post-exploitation Command & Control server and agent supporting multiple protocols and advanced encryption for secure and flexible red teaming operations.
• PromtEngineer/localGPT ⭐ 22029 Python - LocalGPT enables secure, private conversations with your documents on your local device using various open-source GPT models and embeddings without any data leaving your computer.

↑ Back to TOC

Red-Teaming Platforms

• beclab/Olares ⭐ 4004 Shell - Olares is an open-source sovereign cloud operating system that enables users to run local AI models, manage personal data, and self-host various applications securely and privately on their own hardware.

↑ Back to TOC

RAG and Business Analytics

• Canner/WrenAI ⭐ 15390 TypeScript - Wren AI is an open-source Generative Business Intelligence AI agent that enables data-driven teams to interact with their data using natural language to generate SQL queries, visualizations, and reports for smarter business insights.
• chroma-core/chroma ⭐ 28162 Rust - Chroma is an open-source search and retrieval database specifically designed for AI applications, supporting efficient management and querying of embeddings for tasks like document retrieval.
• vanna-ai/vanna ⭐ 23542 Python - Vanna is an open-source Python framework that uses Retrieval-Augmented Generation and large language models to convert natural language questions into accurate SQL queries for various databases, simplifying data access and querying.

↑ Back to TOC

Data Integration and Specialized Solutions

• airweave-ai/airweave ⭐ 6377 Python - Airweave is a platform that turns any app, database, URL, or API into a semantically searchable server for AI agents, enabling easy retrieval of structured and unstructured data through REST and MCP endpoints.
• cocoindex-io/cocoindex ⭐ 10132 Rust - CoCoIndex is an ultra-performant data transformation framework for AI, specializing in incremental processing and real-time data indexing for AI agents and knowledge graphs.
• cube-js/cube ⭐ 20076 Rust - Cube Core is an open-source semantic layer that enables AI, business intelligence, and embedded analytics by providing a flexible, API-driven platform supporting multiple SQL data sources and real-time analytics.
• dolthub/dolt ⭐ 22945 Go - Dolt is a SQL database with Git-like capabilities for data versioning, allowing users to branch, merge, diff, and clone data.
• electric-sql/electric ⭐ 10218 TypeScript - Electric is a real-time sync engine that replicates data from PostgreSQL to various clients, addressing challenges like partial replication and data distribution for modern application development.
• getzep/graphiti ⭐ 22433 Python - Graphiti is a framework for building and querying real-time, temporally-aware knowledge graphs designed to support AI agents in dynamic environments with efficient incremental updates and hybrid retrieval methods.
• llmware-ai/llmware ⭐ 14850 Python - llmware is a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines using small, specialized language models integrated with secure knowledge sources for efficient AI applications.
• mindsdb/mindsdb ⭐ 39230 Python - MindsDB is an AI-powered query engine platform that connects, unifies, and enables conversational querying over large-scale federated data sources including databases, data warehouses, and SaaS applications.
• pingcap/tidb ⭐ 40123 Go - TiDB is an open-source, cloud-native, distributed SQL database offering high availability, horizontal scalability, strong consistency, and MySQL compatibility, designed for various workloads includ...
• ruc-datalab/DeepAnalyze ⭐ 4182 Python - DeepAnalyze is the first agentic large language model designed for autonomous data science, automating the entire data science pipeline from data preparation to report generation across diverse data types.
• run-llama/llama_index ⭐ 49813 Python - LlamaIndex is a leading data framework that enables building LLM-powered applications by providing tools for data ingestion, structuring, and advanced querying to augment large language models with private and external data.
• vectordotdev/vector ⭐ 21956 Rust - Vector is a high-performance observability data pipeline for collecting, transforming, and routing logs, metrics, and traces across various vendors.
• zilliztech/deep-searcher ⭐ 7848 Python - DeepSearcher is an open-source platform that combines large language models and vector databases to enable secure and intelligent search, reasoning, and reporting on private enterprise data.

↑ Back to TOC

Code Automation and Testing

• alibaba/arthas ⭐ 37107 Java - Arthas is an open-source Java diagnostic tool by Alibaba that enables real-time production troubleshooting and performance monitoring without code changes or JVM restarts.
• BuilderIO/micro-agent ⭐ 4272 TypeScript - BuilderIO/micro-agent is an AI-powered tool that writes and iteratively refines code by generating tests and ensuring all test cases pass, focusing on reliable test-driven development.
• judge0/judge0 ⭐ 4196 HTML - Judge0 is a robust, scalable, and open-source online code execution system that supports over 60 programming languages and is designed for easy integration into various applications.
• qodo-ai/qodo-cover ⭐ 5294 Python - Qodo-Cover is an AI-powered tool that automates the generation of unit tests to enhance code coverage, supporting integration with GitHub CI workflows and local CLI usage.
• SWE-agent/SWE-agent ⭐ 19379 Python - SWE-agent is an autonomous software engineering tool that uses large language models to automatically fix GitHub issues, perform web tasks, and solve cybersecurity challenges, achieving state-of-the-art results in automated software repair and offensive cybersecurity.

↑ Back to TOC

Integration and Extensions

• ComposioHQ/composio ⭐ 26468 Python - Composio is a production-ready toolset that equips AI agents and LLMs with over 250 high-quality integrations across software, OS operations, and search capabilities, featuring managed authentication and a pluggable architecture for custom extensions.

↑ Back to TOC

Courses and Tutorials

• alirezadir/Machine-Learning-Interviews ⭐ 8343 Jupyter Notebook - A comprehensive guide to prepare for machine learning and AI technical interviews at major tech companies, covering coding, ML fundamentals, system design, and behavioral aspects.
• dair-ai/Prompt-Engineering-Guide ⭐ 69768 MDX - A comprehensive guide and resource hub for prompt engineering, context engineering, retrieval-augmented generation, and AI agents, offering tutorials, papers, tools, and courses to optimize the use of large language models.
• daveebbelaar/ai-cookbook ⭐ 4149 Python - The AI Cookbook by Dave Ebbelaar offers practical examples and tutorials with copy/paste code snippets to help developers build real-world AI systems efficiently.
• huggingface/agents-course ⭐ 25066 Jupyter Notebook - The Hugging Face Agents Course is a comprehensive educational resource that teaches the fundamentals and advanced concepts of AI agents and large language models through structured units, practical frameworks, and community collaboration.
• NirDiamant/GenAI_Agents ⭐ 20192 Jupyter Notebook - GenAI_Agents is a comprehensive repository offering tutorials, implementations, and community resources for building and advancing generative AI agents from basic to advanced levels.
• patchy631/ai-engineering-hub ⭐ 27587 Jupyter Notebook - AI Engineering Hub is a comprehensive repository offering in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for learners and practitioners.
• rohitg00/ai-engineering-from-scratch ⭐ 26047 Python - AI Engineering from Scratch is a comprehensive curriculum that teaches artificial intelligence from the ground up, starting with math and progressing to complex AI agents, with practical, hands-on ...
• shareAI-lab/learn-claude-code ⭐ 63918 Python - Learn Claude Code is an educational project that teaches how to build modern AI coding agents like Claude Code through a progressive tutorial covering core concepts, planning, subagents, and skills mechanisms.
• The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge ⭐ 12106 Python - An AI-powered tool that analyzes GitHub repositories and generates beginner-friendly tutorials with visualizations to simplify understanding complex codebases.

↑ Back to TOC

Research Lists and Survey Projects