Vibe Coding DiscoverCategory
AI Agents
Autonomous and stateful agents for research, coding, and workflows.
| Project name | Stars | Category | Language | Tags | Summary | View Project |
|---|---|---|---|---|---|---|
| openclaw | ★ 390K | AI Agents | TypeScript | ai-assistant · multi-channel · self-hosted · local-first · plugins · skills · gateway · messaging-bots · privacy · sandboxing · cli · tui · nodejs · typescript · model-providers · personal-assistant | OpenClaw is a self-hosted, open-source AI assistant gateway that runs on your own devices and meets you in 20+ chat channels (Discord, Slack, WhatsApp, iMessage) plus native desktop and mobile apps. Models and agent harnesses are swappable plugins, with extensible tools, skills and a plugin SDK. | View Project → |
| hermes-agent | ★ 248K | AI Agents | Python | ai-agent · self-improving · tool-calling · agent-skills · memory · persistent-memory · multi-platform · messaging-gateway · subagents · cron-scheduler · agent-client-protocol · terminal-ui · self-hosted · model-agnostic · trajectory-generation · session-search | Hermes Agent is Nous Research's self-improving personal AI agent with tool calling, a built-in learning loop that writes and refines its own skills, persistent cross-session memory, and a messaging gateway for Telegram, Discord, Slack and more. Runs on CLI, VPS or serverless backends and is model-agnostic via Nous Port | View Project → |
| deepseek-harness | ★ 236K | AI Agents | TypeScript | agent-harness · plugin-architecture · cordis · deepseek · web-ui · desktop-app · typescript · nodejs · extensible · developer-preview · multi-platform · agent-lifecycle · api-gateway · persistence · monorepo · dsh-plugin | DeepSeek Harness (dsh) is DeepSeek AI's open-source agent harness built on an everything-is-a-plugin architecture via Cordis. It ships a local Web UI and desktop app, plus extensive docs on agent lifecycle, capability seams and plugin extension points. MIT, TypeScript, developer preview with breaking changes. | View Project → |
| n8n | ★ 206K | AI Agents | TypeScript | workflow-automation · no-code · low-code · ai-agents · mcp · mcp-client · mcp-server · self-hosted · integrations · visual-builder · human-in-the-loop · llm-orchestration · fair-code · templates · ipaas · typescript | n8n is a fair-code, self-hostable workflow automation platform with native AI: a visual canvas plus code for building multi-step AI agents, tool use, human approvals, and RAG, connected to 1500+ integrations and MCP servers/clients. | View Project → |
| AutoGPT | ★ 188K | AI Agents | Python | autonomous-agents · agent-platform · workflow-automation · visual-builder · agent-marketplace · no-code · multi-agent · scheduling · triggers · self-hosted · docker · integrations · llm · python · agent-runtime · low-code | AutoGPT is an open-source platform for building, deploying, and running AI agents that execute full workflows. It offers a visual builder, plain-English AutoPilot agent creation, a community marketplace, and 45+ integrations, with both hosted and self-hosted options. | View Project → |
| awesome-llm-apps | ★ 139K | AI Agents | Python | agents · multi-agent · rag · llm · python · agent-skills · templates · tutorials · streamlit · voice-agents · browser-automation · always-on-agents · open-source · example-apps | Curated monorepo of 100+ runnable AI agent, agent-skill, and RAG app templates in Python, each with code and step-by-step tutorials. Good starting point if you want working examples to clone, run, and adapt with Claude, Gemini, GPT, or open models. | View Project → |
| browser-use | ★ 116K | AI Agents | Python | browser-automation · ai-agents · computer-use · playwright · web-scraping · llm · python · browser-agent · task-automation · autonomous-agents · cli · mcp · structured-output · captcha-solving · multi-model · headless-browser | Browser Use is a Python library that lets LLM agents drive a real browser via Playwright to complete multi-step web tasks such as booking, form filling, and scraping. Supports OpenAI, Anthropic, Gemini, Groq, and local Ollama models, with custom tools, CLI/skill integration, and optional cloud browsers. | View Project → |
| TradingAgents | ★ 108K | AI Agents | Python | multi-agent · finance · trading · langgraph · llm · research · backtesting · risk-management · sentiment-analysis · technical-analysis · cli · docker · ollama · multi-provider | TradingAgents is a LangGraph-based multi-agent framework that simulates a trading firm: analyst, researcher, trader, risk and portfolio agents debate market data and emit trading decisions. Supports many LLM providers and local Ollama, with CLI, Docker and backtesting. | View Project → |
| paperclip | ★ 83K | AI Agents | TypeScript | multi-agent orchestration · agent management · agent workflows · task management · agent governance · human-in-the-loop · cost controls · scheduled agents · audit logs · multi-organization | An open-source control plane for coordinating AI agents as a team: assign goals and tasks, schedule runs, review work, manage permissions, and track budgets. Works with agents and runtimes including OpenClaw, Claude Code, Codex, and Cursor. | View Project → |
| deer-flow | ★ 83K | AI Agents | Python | multi-agent · superagent · deep-research · subagents · sandbox · long-term-memory · skills · langgraph · harness · workflow-orchestration · coding-agent · podcast-generation · report-generation · message-gateway · human-in-the-loop · self-hosted | ByteDance's DeerFlow 2.0 is a SuperAgent harness that orchestrates subagents, sandboxes, memory, skills and tools to run research, coding and content tasks lasting minutes to hours. Ships with a web UI, TUI, IM gateway, MCP server and LangGraph backend. | View Project → |
| lobehub | ★ 83K | AI Agents | TypeScript | multi-agent · agent-collaboration · agent-teams · agent-builder · mcp · skills · self-hosted · chat-ui · knowledge-base · scheduling · memory · workspace · plugins · llm-gateway · typescript · nextjs | LobeHub is a self-hostable multi-agent workspace that treats agents as the unit of work: it hires, schedules, and reports on an AI team. Includes an agent builder, 10k+ skills and MCP plugin library, shared pages/workspaces, and editable personal memory. | View Project → |
| learn-claude-code | ★ 77K | AI Agents | Python | agent-harness · tutorial · educational · claude-code · agent-loop · tool-use · subagents · context-compaction · permissions · hooks · memory · task-system · agent-teams · mcp · python · from-scratch | Educational Python tutorial that builds a nano Claude Code-like agent harness from zero, with 17 lessons covering agent loops, tool use, permissions, hooks, subagents, context compaction, memory, MCP plugins and agent teams. | View Project → |
| ai-agents-for-beginners | ★ 75K | AI Agents | Jupyter Notebook | ai-agents · education · course · microsoft-agent-framework · semantic-kernel · autogen · multi-agent · agentic-rag · mcp · a2a · agent-memory · context-engineering · browser-use · foundry-local · production-agents · jupyter-notebook | Microsoft's 18-lesson course for building AI agents, with Jupyter notebooks using Microsoft Agent Framework, Foundry, Semantic Kernel and AutoGen. Covers tool use, agentic RAG, multi-agent and planning patterns, memory, protocols (MCP/A2A), local agents and production deployment. | View Project → |
| MiroFish | ★ 74K | AI Agents | Python | multi-agent-simulation · swarm-intelligence · agent-memory · knowledge-graph · graphrag · prediction · social-simulation · digital-twin · llm · python · zep · public-opinion-analysis · financial-forecasting · persona-generation · simulation-engine · openai-compatible | MiroFish is a multi-agent simulation engine that turns seed material (news, policy drafts, financial signals) into a digital world of thousands of memory-equipped agents, then simulates futures and returns prediction reports. Built on OASIS/CAMEL with GraphRAG and Zep memory; supports OpenAI-compatible LLMs. | View Project → |
| ruflo | ★ 73K | AI Agents | TypeScript | multi-agent · swarm-intelligence · agent-orchestration · agent-harness · mcp-server · claude-code · codex · persistent-memory · self-learning · federation · rag · vector-memory · skills · plugins · autonomous-agents · typescript | Ruflo (formerly claude-flow) is an agent meta-harness for Claude Code and Codex: npx ruflo init adds 100+ specialized agents, coordinated swarms, self-learning vector memory, RAG, federation, MCP tools, plugins and hooks on top of your existing coding agent. | View Project → |
| claude-flow | ★ 73K | AI Agents | TypeScript | JavaScript · Claude · Swarm | Orchestration layer for swarming Claude-style agents across complex development work. | View Project → |
| career-ops | ★ 73K | AI Agents | JavaScript | job-search · ai-agent · resume · cv · cover-letter · ats · job-tracker · claude-code · local-first · cli · career · interview-prep · automation · ai-job-search · job-application · hiring | Open-source AI job search agent that runs locally in your AI coding CLI. Scans job portals, evaluates listings into an A-H report with a 1-5 score, tailors CVs and cover letters, and tracks applications. Local-first, human-in-the-loop. | View Project → |
| MetaGPT | ★ 71K | AI Agents | Python | multi-agent · llm · agent-framework · software-engineering · sop · natural-language-programming · agent-orchestration · code-generation · data-interpreter · role-based-agents · autonomous-agents · workflow-automation · python · openai | MetaGPT is a multi-agent framework that assigns roles like product manager, architect, and engineer to LLMs, turning a one-line requirement into a full software project through SOPs. It also ships a Data Interpreter agent for data analysis and code generation. | View Project → |
| MetaGPT | ★ 71K | AI Agents | Python | Python · MetaGPT · Software Agent | Software-company-in-a-box: multi-agent collaboration that writes software from a one-line brief. | View Project → |
| open-interpreter | ★ 68K | AI Agents | Rust | Python · Interpreter · Local Agent | Local-first agent that runs code on your machine to complete computer tasks. | View Project → |
| mem0 | ★ 66K | AI Agents | Python | agent-memory · long-term-memory · memory-layer · vector-store · embeddings · personalization · hybrid-search · temporal-reasoning · entity-linking · state-management · llm · python · typescript-sdk · semantic-search · cli · self-hosted | Mem0 is a drop-in memory layer for AI agents and LLM apps: it extracts, stores and retrieves user, session and agent memories on top of pluggable vector stores. Ships a Python/TS SDK, self-hosted server, CLI and agent skills, with hybrid semantic+keyword+entity retrieval. | View Project → |
| daily_stock_analysis | ★ 66K | AI Agents | Python | stock-analysis · AI-agent · quantitative-finance · LLM · multi-market · financial-news · trading-signals · decision-dashboard · automated-reports · market-data | A Python-based AI stock analysis system that combines multi-market price data, financial news, and LLMs to generate decision dashboards and reports. Includes a conversational stock-analysis agent, web interface, scheduled runs, and notifications. | View Project → |
| strix | ★ 65K | AI Agents | Python | pentesting · security · multi-agent · red-teaming · vulnerability-scanning · offensive-security · cli · docker · owasp-top-10 · bug-bounty · llm-security · autonomous-agents · ci-cd · sast · dast · exploit-validation | Strix is an open-source AI pentesting agent that autonomously runs your app, finds vulnerabilities, and validates them with working proofs-of-concept. Multi-agent orchestration covers recon, exploitation, and reporting through a developer-first CLI, Docker sandbox, and CI integration. | View Project → |
| OpenMontage | ★ 61K | AI Agents | Python | video production · AI agents · video generation · image generation · text-to-speech · video editing · production pipelines · agent skills · storyboarding · FFmpeg · Remotion | An agentic video production system that coordinates research, scripting, asset generation, editing, and rendering through AI coding assistants. Includes production pipelines, agent skills, a local live storyboard, and integrations with media-generation providers. | View Project → |
| autogen | ★ 61K | AI Agents | Python | multi-agent · agentic-ai · orchestration · llm-agent · mcp · code-execution · human-in-the-loop · event-driven · distributed-runtime · python · dotnet · no-code-gui · benchmarking · openai · autogen · maintenance-mode | Microsoft's multi-agent framework for agentic AI apps, with layered Core/AgentChat/Extensions APIs, MCP tool support, a no-code Studio GUI, and AutoGenBench evals. Now in maintenance mode; new projects are directed to Microsoft Agent Framework. | View Project → |
| crewAI | ★ 59K | AI Agents | Python | multi-agent · agent-orchestration · autonomous-agents · role-based-agents · crewai-crews · crewai-flows · llm · python · workflow-automation · event-driven · task-delegation · agent-collaboration · agent-memory · agent-tools · cli-scaffolding · observability | CrewAI is an open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven, controllable workflows (Flows). It ships a CLI for JSON/YAML project scaffolding, memory, tools, and optional enterprise control plane. | View Project → |
| OpenManus | ★ 58K | AI Agents | Python | ai-agents · multi-agent · computer-use · browser-automation · tool-use · mcp · llm-agents · agent-framework · python · playwright · web-scraping · data-analysis · sandbox · openai · ollama · task-automation | OpenManus is an open-source Python framework for general AI agents: tool use, Browser Use/BrowserGym browser automation, MCP servers, and multi-agent flows, with pluggable OpenAI, Anthropic, Azure, Google, or Ollama backends. Run one command to give an idea and let the agent execute it. | View Project → |
| Flowise | ★ 55K | AI Agents | TypeScript | low-code · no-code · visual-builder · drag-and-drop · agentic-workflow · multi-agent · chatbot · rag · langchain · workflow-automation · self-hosted · llm-orchestration · typescript · react · nodejs · docker | Flowise is a low-code/no-code visual builder for LLM apps: drag-and-drop nodes to compose AI agents, multi-agent workflows, chatbots and RAG pipelines on top of LangChain. Ships as a self-hostable Node/React monorepo with Docker and cloud options. Note: repo is archived. | View Project → |
| goose | ★ 55K | AI Agents | Rust | ai-agent · rust · desktop-app · cli · mcp · multi-provider · local-first · extensions · automation · acp · cross-platform · api · open-source · workflows · tool-use | goose is an extensible open-source AI agent from the Linux Foundation, shipping as a native desktop app, CLI, and API. It works with 15+ LLM providers and 70+ MCP extensions to install, execute, edit, and test code or handle research, writing, and automation tasks. | View Project → |
| multica | ★ 51K | AI Agents | Go | ai-agents · agent-orchestration · multi-agent · coding-agents · issue-tracking · self-hosted · kanban-board · agent-cli · workflow-automation · daemon · autopilots · execution-logs · team-collaboration · claude-code · codex · skills | Multica is a self-hostable workspace where you assign issues to AI coding agents as teammates: agents pick up work on your own runtime daemon, comment progress, and hand back a diff for review. It drives 26 agent CLIs (Claude Code, Codex, Cursor, Kimi...) with execution logs, token cost tracking, squads, and autopilots | View Project → |
| ai-agent-book | ★ 51K | AI Agents | Python | ai-agent · book · tutorial · multi-agent · context-engineering · agent-memory · rag · mcp · coding-agent · reinforcement-learning · agent-evaluation · computer-use · fine-tuning · multimodal · llm · python | Open-source book on AI agent design principles and engineering practice: full text in 15 languages, PDF/EPUB downloads, and 109 runnable companion experiments spanning context engineering, memory/RAG, MCP tools, coding agents, evaluation, post-training, and multi-agent collaboration. | View Project → |
| airi | ★ 50K | AI Agents | TypeScript | ai-companion · vtuber · live2d · vrm · voice-chat · tts · stt · self-hosted · digital-human · game-agent · minecraft · factorio · neuro-sama · desktop-app · memory · avatar | AIRI is an open-source, self-hosted AI companion and virtual character (waifu/VTuber) built on LLMs, with realtime voice chat, Live2D/VRM avatars, and agents that can play Minecraft and Factorio. Ships as web, macOS, Windows and mobile apps. | View Project → |
| nanobot | ★ 48K | AI Agents | Python | personal-ai-assistant · self-hosted · multi-agent · mcp · agent-memory · webui · chatops · telegram-bot · discord-bot · workflow-automation · openai-compatible · local-llm · cron-scheduling · python-sdk · tool-use · subagents | nanobot is a lightweight, self-hosted Python personal AI agent runtime. It runs in a WebUI, terminal, or chat apps (Telegram, Discord, Slack, WeChat, Email) with built-in tools, long-term memory, MCP support, multi-agent delegation, cron automations, and an OpenAI-compatible API. | View Project → |
| CowAgent | ★ 47K | AI Agents | Python | multi-agent · agent-harness · multi-model · memory · knowledge-base · skills · mcp · chatbot · wechat · telegram · self-evolution · tool-use · browser-automation · multimodal · task-planning · one-line-install | CowAgent (formerly chatgpt-on-wechat) is a Python agent harness: it plans tasks, runs tools, installs skills, and keeps long-term memory plus a personal knowledge base. Multi-agent, multi-model, and multi-channel, deployable via one-line install or Docker. | View Project → |
| AstrBot | ★ 41K | AI Agents | Python | chatbot · multi-platform · im-integration · mcp · plugins · knowledge-base · persona · agent-sandbox · multimodal · tts · stt · docker · webui · self-hosted · llm-gateway · i18n | AstrBot is a self-hosted Python agent chatbot platform that plugs LLMs, MCP tools, plugins, personas and a knowledge base into 15+ IM apps (QQ, Telegram, Discord, Slack, WeCom, Feishu, DingTalk). Ships Docker/CLI install, WebUI and a plugin marketplace. | View Project → |
| openhuman | ★ 40K | AI Agents | Rust | agent-harness · agent-orchestration · local-first · memory · mcp · rust · tauri · desktop · privacy · workflows · sub-agents · personal-ai · second-brain · obsidian · skills · multi-agent | OpenHuman is a Rust/Tauri desktop agent harness that builds a local-first memory tree from your accounts, then orchestrates fleets of sub-agents and durable workflows with MCP, skills and messaging channels. | View Project → |
| agents | ★ 40K | AI Agents | Python | AI agents · coding agents · agent skills · multi-agent · agent plugins · agent marketplace · orchestration · cross-harness · Claude Code · Codex · Cursor · OpenCode · GitHub Copilot · Pi | A marketplace of coding-agent plugins, with 202 agents, 183 skills, 105 commands, and multi-agent workflows. It generates harness-native artifacts for Claude Code, Codex, Cursor, OpenCode, Antigravity, Copilot, and Pi from shared sources. | View Project → |
| oh-my-claudecode | ★ 39K | AI Agents | TypeScript | claude-code · multi-agent · orchestration · agent-teams · workflow-automation · cli · claude-code-plugin · parallel-execution · vibe-coding · autopilot · mcp · code-review · qa-testing · subagents · typescript | A Claude Code plugin and CLI that adds teams-first multi-agent orchestration: /team and /autopilot spawn staged agent pipelines (plan, PRD, exec, verify, fix) plus MCP and tmux-backed CLI workers for parallel coding tasks. | View Project → |
| OpenMAIC | ★ 39K | AI Agents | TypeScript | multi-agent · education · course-generation · interactive-classroom · slides · quiz-generation · whiteboard · text-to-speech · pptx-export · agent-skills · durable-sessions · document-parsing · self-hosted · openclaw · pbl · i18n | OpenMAIC is a self-hostable multi-agent platform that turns any topic or document into an interactive classroom: agent-generated slides, quizzes, simulations and PBL activities with AI teachers, whiteboard drawing, TTS and .pptx export. Ships a SKILL.md agent skill for OpenClaw, Codex and other workbenches, plus a chat | View Project → |
| UI-TARS-desktop | ★ 39K | AI Agents | TypeScript | multimodal-agent · gui-agent · computer-use · browser-automation · vision-language-model · mcp · agent-stack · electron · cli · web-ui · desktop-automation · gui-operator · agent-tars · ui-tars · event-stream · sdk | ByteDance's TARS stack ships Agent TARS (multimodal agent CLI/Web UI with GUI, vision and MCP tool use) plus UI-TARS Desktop, a native desktop app driving computer and browser operators from the UI-TARS vision-language model. | View Project → |
| 500-AI-Agents-Projects | ★ 38K | AI Agents | Python | ai-agents · multi-agent · awesome-list · curated-collection · use-cases · examples · tutorials · crewai · langgraph · autogen · agno · llamaindex · mcp · industry-applications · learning-resources · python | Curated catalog of 500+ AI agent projects and use cases, with links to open-source implementations and self-contained runnable examples across CrewAI, LangGraph, AutoGen, Agno and LlamaIndex. Best for developers surveying agent frameworks and industry use cases rather than a usable library. | View Project → |
| ai-engineering-hub | ★ 38K | AI Agents | Jupyter Notebook | tutorials · llm · rag · agents · mcp · multi-agent · fine-tuning · multimodal · vector-database · evaluation · voice-agents · learning-resource · deepseek · ocr · jupyter-notebooks · production-examples | A large collection of hands-on Jupyter-notebook tutorials and runnable demos covering LLM apps, RAG pipelines, AI agents, MCP servers, fine-tuning and model evaluation. Best used as a learning/reference library of practical examples rather than a single installable product. | View Project → |
| financial-services | ★ 38K | AI Agents | Python | claude · agents · skills · plugins · financial-services · mcp · managed-agents · investment-banking · equity-research · private-equity · wealth-management · excel-modeling · fund-admin · kyc · claude-code · slash-commands | Anthropic's reference Claude agents, skills, and MCP data connectors for financial-services workflows: banking, research, PE, fund admin, and wealth management. Ships as Cowork/Claude Code plugins or deployable Managed Agent cookbooks, all file-based markdown and JSON. | View Project → |
| khoj | ★ 38K | AI Agents | Python | ai-assistant · second-brain · self-hosted · rag · semantic-search · personal-agents · automations · deep-research · document-qa · chat · local-llm · obsidian · emacs · whatsapp · image-generation · speech-to-text | Khoj is a self-hostable personal AI app that answers questions from your docs and the web via semantic search and RAG, lets you build custom agents and scheduled automations, and works with local or online LLMs across web, Obsidian, Emacs, desktop and WhatsApp clients. | View Project → |
| QwenPaw | ★ 35K | AI Agents | TypeScript | personal-ai-assistant · self-hosted · multi-agent · agent-harness · skills · mcp · multi-channel · memory · sandbox · chatbot · automation · scheduling · browser-use · computer-use · plugins · tui | QwenPaw is a self-hosted personal AI assistant built on AgentScope. It runs local or in the cloud, connects to chat channels (DingTalk, Lark, Discord, Telegram, iMessage), and extends via Skills, Plugins, MCP and a three-layer memory. | View Project → |
| ChatDev | ★ 34K | AI Agents | Python | multi-agent · orchestration · llm · zero-code · low-code · workflow · agent-collaboration · yaml-config · web-console · mcp · deep-research · python | ChatDev 2.0 (DevAll) is a zero-code multi-agent orchestration platform: define agents, workflows and tasks in YAML, then run them via a FastAPI backend and Vue web console. Ships MCP support, memory, and Docker deployment for scenarios like research, data viz and content automation. | View Project → |
| buzz | ★ 34K | AI Agents | Rust | nostr · multi-agent · agent-collaboration · self-hosted · relay · workspace · cli · workflows · acp · mcp · audit-log · git-events · chat · search · rust | Buzz is a self-hostable Nostr relay workspace where humans and AI agents share the same rooms, channels, git events and workflows. Agents act as first-class members with their own keys, audit trail, JSON-only buzz-cli, and an ACP/MCP harness for Goose, Codex and Claude Code. | View Project → |
| Vibe-Trading | ★ 34K | AI Agents | Python | ai-agent · trading · algorithmic-trading · backtesting · multi-agent · quantitative-finance · fintech · mcp · llm · langgraph · paper-trading · broker-integration · natural-language · shadow-account · market-data | Python AI trading agent (LangGraph + LangChain) that turns natural-language requests into market research, backtests, and paper trades. Ships an MCP server, FastAPI backend, React UI, 18 broker/data connectors, and multi-agent swarm plus shadow-account trading. | View Project → |
| xiaozhi-esp32 | ★ 30K | AI Agents | C++ | voice assistant · ESP32 · MCP · chatbot · IoT · voice interaction · device control · wake word · audio streaming · multimodal | C++ firmware for ESP32-based voice chatbots with streaming audio, wake-word detection, optional camera input, and MCP-based device control. Supports multiple ESP32 boards and WebSocket or MQTT+UDP connections to AI services. | View Project → |
| composio | ★ 30K | AI Agents | TypeScript | agents · tool-calling · function-calling · mcp · integrations · authentication · toolkits · llmops · developer-tools · cli · sessions · oauth · triggers · sandbox · typescript · python | Composio is a TypeScript/Python SDK and CLI that equips AI agents with 1000+ pre-authenticated app toolkits, per-user sessions, auth, triggers and tool search, plus provider adapters and hosted MCP endpoints for popular agent frameworks. | View Project → |
| FastGPT | ★ 30K | AI Agents | TypeScript | AI agents · RAG · visual workflows · knowledge base · MCP · hybrid search · reranking · self-hosted | FastGPT is a self-hostable platform for building LLM agents and question-answering apps. It combines document ingestion, RAG retrieval, visual workflow orchestration, MCP integration, and application monitoring. | View Project → |
| deepagents | ★ 30K | AI Agents | Python | agent-harness · multi-agent · sub-agents · context-management · filesystem · persistent-memory · human-in-the-loop · skills · mcp · tool-calling · sandbox · langgraph · coding-agent · streaming · checkpointing | Deep Agents is LangChain's batteries-included agent harness built on LangGraph: planning, sub-agents, filesystem, context management, memory and skills out of the box. Model-agnostic and extensible, it also ships a prebuilt terminal coding agent (dcode). | View Project → |
| openai-agents-python | ★ 30K | AI Agents | Python | multi-agent · agents · orchestration · handoffs · guardrails · tracing · tools · mcp · voice-agents · realtime · sandbox · human-in-the-loop · sessions · streaming · python · openai | OpenAI's lightweight Python SDK for building multi-agent workflows: agents with tools, guardrails, handoffs, sessions and tracing. Provider-agnostic across OpenAI APIs and 100+ LLMs, with sandbox, realtime and voice agent support. | View Project → |
| gpt-researcher | ★ 30K | AI Agents | Python | deep-research · autonomous-agent · multi-agent · web-scraping · report-generation · citations · rag · mcp · llm-providers · planner-executor · local-documents · python · research-automation · image-generation | GPT Researcher is an autonomous deep-research agent that plans sub-questions, scrapes and aggregates 20+ web or local sources, and writes cited reports. Works with any LLM provider, supports MCP data sources, local docs, PDF/Word export, and a FastAPI + Next.js UI. | View Project → |
| smolagents | ★ 29K | AI Agents | Python | agents · code-agents · multi-agent · tool-calling · react-loop · sandboxed-execution · mcp · llm-agnostic · vision · web-browsing · hub-integration · minimal-abstractions · python · agent-framework | smolagents is Hugging Face's minimal Python library for building LLM agents that write their actions as executable Python code. It supports CodeAgent and ToolCallingAgent, multi-agent hierarchies, MCP/LangChain tools, sandboxed execution, and any model provider via LiteLLM. | View Project → |
| cua | ★ 27K | AI Agents | HTML | computer-use · desktop-automation · gui-agents · mcp · virtualization · sandbox · vm · benchmarks · evals · trajectory-data · macos · windows · linux · browser-use · containerization · cross-platform | Cua is an open-source computer-use agent stack: a cross-OS driver to control native apps, isolated cloud desktop fleets, local macOS/Linux VMs via Lume, CUA-S1 decision models, and Cua Bench for evaluating agents and exporting trajectories. | View Project → |
| hindsight | ★ 27K | AI Agents | Python | agent memory · long-term memory · memory learning · recall · reflection · personalization · MCP · coding agents | Hindsight is a self-hostable memory system for AI agents, with APIs and SDKs to retain, recall, and reflect on information over time. It integrates with agent frameworks and coding assistants and supports a range of hosted and local LLM providers. | View Project → |
| Open-AutoGLM | ★ 26K | AI Agents | Python | phone agent · computer use · mobile automation · multimodal · UI automation · Android · iOS · HarmonyOS · ADB · HDC · natural language tasks | An open-source phone-use agent that interprets screen content with AutoGLM vision-language models, plans actions, and controls Android, iOS, or HarmonyOS devices. Includes a Python API and CLI, with ADB, HDC, and WebDriverAgent-based device control. | View Project → |
| awesome-claude-code-subagents | ★ 25K | AI Agents | Shell | Claude Code · subagents · coding agents · agent collection · developer assistants · specialized agents · plugin marketplace | A collection of 161+ specialized subagent definitions for Claude Code, organized into categories such as core development, language specialists, and infrastructure. Install agents as plugins or copy them into Claude Code's agent directories. | View Project → |
| stagehand | ★ 25K | AI Agents | TypeScript | browser-agent · browser-automation · web-scraping · data-extraction · self-healing · playwright · cdp · headless-chrome · cloud-browser · mcp · session-persistence · webmcp · shadow-dom · iframes · opentelemetry · typescript | Stagehand is Browserbase's SDK for browser agents: act(), observe(), and extract() wrap Playwright-style primitives with LLM reasoning, self-healing selectors, and schema-validated extraction. Ships TypeScript, Python, and Go SDKs plus a hosted MCP server for giving coding agents browser control. | View Project → |
| letta | ★ 25K | AI Agents | — | stateful agents · memory · llm · self-improving · memgpt · agent framework · long-term memory · ai agents · letta · agent sdk · persistent memory · agent runtime | Letta (formerly MemGPT) is a platform for building stateful AI agents with advanced memory that learn and self-improve over time. It includes an agent runtime, SDK, and integrations for channels like Slack and Telegram. | View Project → |
| activepieces | ★ 25K | AI Agents | TypeScript | AI agents · MCP · workflow automation · no-code · integrations · self-hosted · human-in-the-loop · TypeScript | Activepieces is a self-hostable workflow automation platform with AI agent capabilities. Its integration pieces can be exposed as MCP tools for clients such as Claude Desktop, Cursor, and Windsurf. | View Project → |
| skyvern | ★ 23K | AI Agents | Python | browser automation · computer use · web agent · workflow automation · RPA · computer vision · Playwright · natural language | Skyvern is a browser automation agent and Playwright-compatible SDK that uses LLMs and computer vision to carry out natural-language tasks across websites. It includes a workflow builder, API, and Python and TypeScript clients. | View Project → |
| go-micro | ★ 23K | AI Agents | Go | go · golang · ai-agents · agent-harness · multi-agent · mcp · a2a · microservices · service-discovery · distributed-systems · tool-calling · durable-workflows · memory · guardrails · llm · rpc | Go Micro is a Go agent harness and service framework where agents are services: endpoints become LLM tools, with memory, planning, delegation, guardrails, MCP/A2A interop, and durable flows in one runtime. | View Project → |
| MaxKB | ★ 23K | AI Agents | Python | agent-platform · rag · agentic-workflow · knowledge-base · mcp · chatbot · no-code · multi-modal · enterprise · workflow-engine · llm · self-hosted · ollama · pgvector · customer-service · django | MaxKB is a self-hosted enterprise agent platform combining RAG pipelines, a visual agentic workflow engine, and MCP tool use. It connects private or public LLMs, ingests documents into pgvector, and delivers zero-code chat agents for customer service and internal knowledge bases. | View Project → |
| screenpipe | ★ 22K | AI Agents | Rust | AI memory · agent context · screen capture · local-first · MCP · multimodal · speech-to-text · OCR · computer history · privacy | Screenpipe records screen and audio activity locally, transcribes speech, and makes computer history searchable for people and AI agents. It exposes history through an MCP server and supports agent workflows and automations. | View Project → |
| adk-python | ★ 22K | AI Agents | Python | ai-agents · multi-agent · agent-framework · python · agent-orchestration · workflow-engine · tool-calling · human-in-the-loop · agent-evaluation · mcp · a2a · model-agnostic · deployment · code-first · gemini · llm | Google's code-first Python framework for building, orchestrating, evaluating and deploying AI agents. Offers graph workflow runtime, multi-agent task delegation, MCP/OpenAPI tools, HITL confirmation, a dev web UI and Cloud Run / Vertex AI deployment. Model-agnostic but optimized for Gemini. | View Project → |
| jev-ultrafast | ★ 21K | AI Agents | Python | browser-agent · computer-use · web-automation · dom-snapshot · action-space · agent-loop · speculative-decoding · structured-state · element-indexing · chrome · fast-inference · no-screenshots · llm-agent · typesafe · browser-harness · form-filling | Python browser agent with a dynamic indexed action space: TypeSafe Jev picks an operation and element per observed DOM table, and a small LLM writes text only for TYPE_TEXT. Runs a Google Flights search in ~7s with one request per decision cycle. | View Project → |
| suna | ★ 20K | AI Agents | TypeScript | AI agents · multi-agent · cloud computer · self-hosted · agent skills · company memory · MCP · connectors · sandbox · human approval · automation · CLI | Kortix is a self-hostable AI agent platform for managing agents, skills, company memory, and connectors as versioned files. Agents work in isolated cloud computers and submit changes for human review; it includes web, CLI, desktop, and mobile apps. | View Project → |
| eliza | ★ 19K | AI Agents | TypeScript | multi-agent · agent-runtime · typescript · plugins · local-inference · chatbot · discord · telegram · slack · rag · memory · browser-automation · wallet · on-device · cli · voice | elizaOS is an open-source TypeScript framework and runtime for building autonomous, plugin-extensible AI agents across web, desktop, and mobile. It includes an agent app, CLI, local on-device inference, RAG memory, and messaging/wallet integrations. | View Project → |
| agent-zero | ★ 19K | AI Agents | Python | agent-framework · autonomous-agents · computer-use · docker · linux-desktop · browser-automation · multi-agent · subagents · plugins · skills · memory · mcp · a2a · web-ui · self-hosted · python | Agent Zero is a Dockerized agent framework that gives an LLM a full Linux XFCE desktop, a DOM-annotatable browser, live document cowork, projects, memory, plugins, skills, and MCP/A2A connectors. It supports multi-agent delegation and a host bridge for working in your real local repos. | View Project → |
| agent-zero | ★ 19K | AI Agents | Python | Python · Agent Zero · Personal Agent | Personal, general-purpose agent that learns your computer and grows its own tools. | View Project → |
| openworker | ★ 18K | AI Agents | Python | ai-coworker · desktop-agent · local-first · human-in-the-loop · approval-gating · audit-trail · mcp-client · connectors · automations · security-review · multi-provider · ollama · tauri · cli · agent-governance · unattended-runs | OpenWorker is an open-source, local-first AI coworker desktop agent (Python backend + Tauri/React UI) that completes real deliverables across files, terminal, and 25+ connectors. Governance is built in: approval gates, hard human-only floors, reviewer-model auto-approve, and per-tool audit provenance. Runs on your own | View Project → |
| paseo | ★ 18K | AI Agents | TypeScript | agent-orchestration · coding-agents · multi-agent · claude-code · codex · copilot · opencode · mobile · desktop · voice-control · self-hosted · cli · typescript-sdk · mcp-server · plugins · agent-skills | Paseo is a self-hosted orchestration layer that runs Claude Code, Codex, Copilot, OpenCode and Pi coding agents in parallel on your machines, with iOS/Android/desktop/web/CLI clients, voice control, an MCP server, plugins, and a TypeScript SDK. | View Project → |
| camel | ★ 18K | AI Agents | Python | multi-agent · agents · agent-society · LLM · synthetic-data · role-playing · workforce · memory · toolkits · benchmarks · RAG · python · MCP · data-generation · simulation · scaling-laws | CAMEL is a Python framework for building and studying multi-agent systems at scale, with agents, societies, toolkits, memories, and data generation. It supports role-playing, workforce orchestration, RAG, benchmarks, and MCP tool integration for agent research and automation. | View Project → |
| SuperAGI | ★ 18K | AI Agents | Python | autonomous-agents · agent-framework · multi-agent · llmops · toolkits · agent-memory · workflows · vector-db · concurrent-agents · telemetry · gui · docker · nextjs · python · marketplace · production-agents | SuperAGI is a dev-first open-source framework for building, managing and running autonomous AI agents with toolkits, memory, workflows, vector DBs and telemetry. Python/FastAPI backend plus Next.js GUI, deployable via Docker Compose. | View Project → |
| trigger.dev | ★ 16K | AI Agents | TypeScript | durable-workflows · ai-agents · background-jobs · task-orchestration · queues · retries · cron-schedules · observability · tracing · human-in-the-loop · llm-streaming · realtime · typescript-sdk · self-hosting · mcp-server · serverless | Open-source TypeScript platform for building and deploying durable AI agents and workflows: long-running tasks with no timeouts, retries, queues, cron schedules, human-in-the-loop waits, realtime LLM streaming, and full tracing. Self-hostable via Docker or Kubernetes. | View Project → |
| botpress | ★ 15K | AI Agents | TypeScript | chatbots · agents · LLM · conversational-AI · SDK · CLI · integrations · low-code · deployment · TypeScript · OpenAI · GPT-4 · chatbot-platform · hub | Botpress is an open-source platform and TypeScript SDK/CLI for building, deploying, and managing GPT/LLM chatbots and agents. It ships integrations, a CLI, and example bots-as-code for the Botpress Cloud runtime. | View Project → |
| E2B | ★ 14K | AI Agents | Python | sandbox · code-execution · ai-agents · code-interpreter · computer-use · secure-execution · sdk · python · typescript · llm · cloud-infrastructure · firecracker · self-hosting · agent-tools | E2B is open-source infrastructure plus JS/Python SDKs for running AI-generated code in secure isolated sandboxes. It provides code interpreter and desktop/computer-use APIs so agents can execute code and control real tools safely. | View Project → |
| ViMax | ★ 12K | AI Agents | Python | agentic video generation · multi-agent · video generation · storyboarding · scriptwriting · novel adaptation · image generation · AI filmmaking · character consistency · Web UI · TUI | An agentic video-creation system that coordinates story planning, scriptwriting, storyboarding, image and video generation, and final assembly. Supports idea-, screenplay-, and novel-to-video workflows, with interactive TUI and Web UI controls. | View Project → |
| OpenCreator | ★ 12K | AI Agents | TypeScript | ai-agents · codex · agent-workspace · skills · mcp · video-translation · dubbing · tts · subtitles · image-generation · video-generation · multimodal · local-first · desktop-app · creator-tools · localization | OpenCreator is a local-first AI workspace and agent app built on Codex CLI, combining reusable Skills, MCP and a runtime with visual creator tools for video translation, dubbing, subtitles, TTS, image/video generation and writing. | View Project → |
| UI-TARS | ★ 12K | AI Agents | Python | gui-agent · computer-use · vision-language-model · multimodal · ui-automation · grounding · reinforcement-learning · desktop-automation · mobile-automation · browser-automation · screen-understanding · action-parsing · bytedance · research | ByteDance's UI-TARS is an open-source native GUI agent built on a vision-language model that perceives screenshots and emits mouse/keyboard actions for desktop, mobile, and browser automation. The repo ships deployment guides, prompt templates, and action-parsing utilities (pip install ui-tars). | View Project → |
| MemOS | ★ 12K | AI Agents | TypeScript | long-term-memory · agent-memory · memory-os · hybrid-retrieval · rag · mcp · self-evolving · skill-evolution · vector-database · knowledge-base · multi-agent · token-savings · context-management · local-first · sqlite · neo4j | Memory OS for LLMs and AI agents: unified add/retrieve/edit/delete of long-term and multi-modal memory as an inspectable graph, with hybrid retrieval (vector + FTS5), async ingestion, skill evolution, and plugins for OpenClaw, Hermes and DeepSeek Harness. | View Project → |
| voltagent | ★ 11K | AI Agents | TypeScript | typescript · ai-agents · multi-agent · llm · mcp · rag · workflow-engine · memory · guardrails · evals · observability · voice · openai · nodejs · agent-framework · tools | VoltAgent is an open-source TypeScript framework for building AI agents with memory, tools, MCP, RAG, workflows, voice and guardrails, plus multi-agent supervisor routing. It pairs with the VoltOps console for observability, evals and deployment. | View Project → |
| astrid | ★ 10K | AI Agents | Rust | agent-runtime · wasm · sandbox · capability-security · mcp · rust · microkernel · wasmtime · ipc · llm · audit-log · ed25519 · content-addressed-storage · cli · multi-agent · os | Astrid is a Rust user-space runtime (heading toward an OS) that runs LLM agents and tools as sandboxed WASM capsules with cryptographic, per-principal capability grants. The kernel is a dumb event router with no LLM or tool state; use it to compose secure agent systems, MCP tools, and services. | View Project → |
| omnigent | ★ 10K | AI Agents | Python | multi-agent · agent-orchestration · agent-framework · meta-harness · claude-code · codex · cursor · agent-governance · policies · sandboxing · session-sharing · coding-agents · mcp · yaml · self-hosted · python | Omnigent is an open-source meta-harness and Python framework that orchestrates Claude Code, Codex, Cursor, and custom YAML agents under one session, with policy enforcement, sandboxing, and real-time multi-device collaboration. | View Project → |
| inkos | ★ 10K | AI Agents | TypeScript | ai-agent · creative-writing · novel-generation · ai-writing · interactive-fiction · storyboard · translation · multi-agent · cli · tui · studio-ui · skills · memory · llm-routing · openclaw · typescript | InkOS is a TypeScript story-creation AI agent system for novels, shorts, scripts, storyboards, interactive open worlds and translation. It ships a shared pi-agent harness, 15 built-in SKILL.md skills, SQLite FTS5 story memory, review/revision pipelines, and Studio/TUI/CLI surfaces with multi-provider model routing. | View Project → |
| OpenShell | ★ 9.8K | AI Agents | Rust | agent runtime · sandbox · security · isolation · access policies · credential protection · network controls · kernel enforcement · policy verification · gateway | A runtime for running autonomous AI agents in isolated sandboxes. It enforces filesystem, system-call, and network policies, protects credentials, and supports reviewing policy changes before they take effect. | View Project → |
| AutoAgent | ★ 9.8K | AI Agents | Python | multi-agent · zero-code · natural-language · agent-builder · deep-research · self-improving · workflow-orchestration · tool-generation · llm · cli · docker · agent-framework · research-assistant · code-generation · python | AutoAgent is a zero-code framework that builds and orchestrates LLM agents, tools, and workflows from natural language alone. Includes a Deep Research-style multi-agent mode, agent editor, workflow editor, and CLI, with model-agnostic provider support via LiteLLM. | View Project → |
| computer | ★ 9.3K | AI Agents | TypeScript | computer-use · agent-workspace · virtual-filesystem · sandbox · code-execution · durable-storage · Cloudflare Workers · FUSE | A TypeScript toolkit for giving agents a durable workspace and execution environment on Cloudflare. It combines a SQLite-backed virtual filesystem with container, shell, and JavaScript runtimes. | View Project → |
| XianyuAutoAgent | ★ 9.3K | AI Agents | Python | customer-service · multi-agent · chatbot · llm · prompt-engineering · e-commerce · xianyu · context-memory · negotiation · intent-routing · python · websockets · openai-compatible · automation · expert-routing | Python LLM agent that runs a 24/7 automated Xianyu (Idle Fish) customer-service bot: it classifies buyer intent, routes to price/tech/default expert prompts, keeps conversation context, and negotiates prices with tiered discounts via an OpenAI-compatible API (default Qwen). | View Project → |
| artemis | ★ 9.2K | AI Agents | Python | ai-agents · android · mobile-automation · test-automation · computer-use · mcp · ui-automation · multimodal · androidworld · adb · logcat · cli · python-sdk · web-console · benchmark | Google's ARTEMIS is an AI agent that executes natural-language instructions on real Android devices, driving apps end-to-end and capturing logs and screenshots. It ships an MCP server for IDE assistants, a CLI, Python SDK, and 99%+ AndroidWorld success. | View Project → |
| agentic-inbox | ★ 8K | AI Agents | TypeScript | email · cloudflare-workers · ai-agent · mcp · durable-objects · self-hosted · workers-ai · email-routing · auto-draft · r2 · sqlite · hono · react-router · streaming · tool-calling · typescript | Self-hosted email client running on Cloudflare Workers with an embedded AI email agent (Cloudflare Agents SDK + Workers AI) that reads, searches and drafts replies, plus an MCP endpoint so external AI tools can act on mailboxes. | View Project → |
| osaurus | ★ 8K | AI Agents | Swift | macos · swift · apple-silicon · local-llm · offline · multi-agent · mcp-server · persistent-memory · sandbox · computer-use · browser-automation · privacy · image-generation · orchestrator · subagents · cryptographic-identity | Osaurus is a native Swift/SwiftUI macOS harness for AI agents: local or cloud models, persistent memory, sandboxed code execution, browser and computer use, image generation, MCP support, and cryptographic agent identity. Fully offline-capable and MIT licensed. | View Project → |
| munder-difflin | ★ 8K | AI Agents | TypeScript | multi-agent · agent-orchestration · local-first · claude-code · codex · gemini-cli · opencode · electron · desktop-app · agent-memory · hive-mind · autonomous-agents · mailbox-routing · terminal-agents · human-in-the-loop · typescript | Munder Difflin is a local-first Electron desktop harness that wraps terminal coding CLIs (Claude Code, Codex, Gemini CLI, Qwen, OpenCode, and more) into a coordinated office of agents with shared markdown memory, mailboxes, and a supervisor agent that routes work and escalates approvals. | View Project → |
| harness-sdk | ★ 7.4K | AI Agents | Python | agents · agent-framework · multi-agent · mcp · sdk · llm · python · typescript · streaming · structured-output · guardrails · observability · evals · memory · model-agnostic · tools | Strands Agents is an Apache-2.0 SDK for building and running AI agents in Python and TypeScript. It provides an in-process agent loop with tools, MCP, multi-agent patterns, memory, streaming, guardrails, tracing and evals, and is model-agnostic across Bedrock, Anthropic, OpenAI and Gemini. | View Project → |
| Yuxi | ★ 7.2K | AI Agents | Python | multi-agent · agentic-rag · knowledge-graph · multi-tenant · self-hosted · mcp · agent-skills · sandbox · knowledge-base · langgraph · document-parsing · rag-evaluation · subagents · rbac · kbqa · docker | Yuxi is a self-hosted, multi-tenant knowledge agent platform that combines Agentic RAG, Neo4j knowledge graphs, LangGraph multi-agent orchestration, MCP/Skills, sandboxed file tools and RBAC in one Docker-deployed workspace. Aimed at teams that need to own their data, models and permissions. | View Project → |
| swarms | ★ 7.2K | AI Agents | Python | multi-agent · agent-orchestration · swarms · mcp · workflows · sequential-workflow · concurrent-workflow · graph-workflow · group-chat · mixture-of-agents · agent-memory · tool-calling · prompt-engineering · production-agents · autonomous-agents · python | Python framework for orchestrating multi-agent systems: prebuilt sequential, concurrent, graph, and mixture-of-agents architectures, plus MCP client/server support so agents can call external tools or be exposed as MCP tools. Apache-2.0, pip-installable, runs on any LiteLLM-supported model. | View Project → |
| awesome-agentic-ai-zh | ★ 7.1K | AI Agents | Python | agentic-ai · learning-roadmap · awesome-list · multi-agent-systems · mcp · rag · prompt-engineering · claude-code · agent-skills · cli-agents · education · tutorial · trilingual · chinese · llm · python | Trilingual (繁中/EN/简中) learning roadmap for agentic AI: 9 stages from LLM basics to multi-agent production, with 240+ curated resources, runnable Python starter examples and role-based tracks (developer, researcher, teacher, knowledge worker). | View Project → |
| OpenAlice | ★ 7.1K | AI Agents | TypeScript | trading · finance · multi-agent · agent-orchestration · market-data · broker-integration · ibkr · quantitative-research · prediction-markets · scheduled-tasks · local-first · electron · cli · desktop-app · workspaces · paper-trading | OpenAlice is a local AI trading agent orchestrator that connects agents like Claude Code and Codex to market data, research workspaces, scheduled tasks, and broker accounts. It covers research, thesis tracking, paper trading, and approved order execution across equities, crypto, forex, and macro. | View Project → |