Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
Awesome-Agent-Harnesses
Agents & frameworksCurated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.
git clone https://github.com/NeuraLiying/Awesome-Agent-Harnesses.git -
mate
Agents & frameworksProduction-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.
git clone https://github.com/antiv/mate.git -
Network-AI
Agents & frameworksTraffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks
git clone https://github.com/Jovancoding/Network-AI.git -
everruns
Agents & frameworksOpen source Rust framework and durable runtime for AI agents. MIT
git clone https://github.com/everruns/everruns.git -
CozyClay
Agents & frameworksOpen source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then take the same shots to an AI video model.
git clone https://github.com/HaD0Yun/CozyClay.git -
binny
Agents & frameworksBINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.
git clone https://github.com/openbin-ai/binny.git -
benchmarks
Agents & frameworksReproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.
git clone https://github.com/coval-ai/benchmarks.git -
QwenPaw-Data
Agents & frameworksAgentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)
git clone https://github.com/agentscope-ai/QwenPaw-Data.git -
Multi-Agent-Intelligent-Warehouse
Agents & frameworksAn open blueprint for intelligent warehouse operations, combining agentic AI, governed warehouse state, decision intelligence, and controlled execution. Agents analyze & propose actions, while deterministic policy, approval, validation, execution layers preserve safety, authority, & auditability.
git clone https://github.com/NVIDIA-AI-Blueprints/Multi-Agent-Intelligent-Warehouse.git -
chat-gun
Agents & frameworks🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools, Qwen/OpenAI-compatible LLM gateway. Ships an after-sales support agent: cited RAG with abstention, human-approved refunds, idempotent execution. OpenTelemetry + reproducible evals.
git clone https://github.com/HsienW/chat-gun.git -
caliper
Agents & frameworksRun your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, Hermes, Antigravity, and OpenCode.
git clone https://github.com/edonadei/caliper.git -
Spotter
Agents & frameworksOfficial codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
git clone https://github.com/zqc3117/Spotter.git -
SecGPT
Agents & frameworksAn Execution Isolation Architecture for LLM-Based Agentic Systems
git clone https://github.com/llm-platform-security/SecGPT.git -
xmatrix
Agents & frameworksGroup chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your own subscription and keeps the team's pages current.
git clone https://github.com/LambdaLabsHQ/xmatrix.git -
zhikuncode
Agents & frameworksCodex/Claude Code/Cursor的开源增强版,专注一句话实现复杂长程任务(教育、编程、办公、生活、娱乐、游戏)。部署在你自己的服务器上,团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口,Multi-Agent 协作,原生直连千问/DeepSeek 等国产大模型。技能/插件/跨会话记忆,8 层安全沙箱,数据不离开你的机器。Docker 一键部署,MIT 开源,零锁定。
git clone https://github.com/zhikunqingtao/zhikuncode.git -
Dais
Agents & frameworksYour Desktop AI Staffs.
git clone https://github.com/Dais-Project/Dais.git -
engraphis
Agents & frameworksLocal-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
git clone https://github.com/Coding-Dev-Tools/engraphis.git -
spark-agent
Agents & frameworksSparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across Agent sessions, route tasks to the right models, and extend the workspace with custom tools and apps. Reviewable, steerable, reversible runs on macOS, Windows and Linux.
git clone https://github.com/alexanderizh/spark-agent.git -
copilot-app-for-beginners
Agents & frameworksLearn how to get started using the GitHub Copilot app!
git clone https://github.com/github/copilot-app-for-beginners.git -
agent-plugins
Agents & frameworksBuild with Clay in your AI coding agent - skills, MCP tools, and the clay CLI for Claude Code, Codex, and Cursor. Search companies and people, run enrichment routines, and query tables from natural language.
git clone https://github.com/clay-run/agent-plugins.git -
awesome-jev-projects
Agents & frameworksAwesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync
git clone https://github.com/logicrw/awesome-jev-projects.git -
caura-long-run-fleet
Agents & frameworksLong-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.
git clone https://github.com/caura-ai/caura-long-run-fleet.git -
fullstack-langgraph-nextjs-agent
Agents & frameworksProduction-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.
git clone https://github.com/agentailor/fullstack-langgraph-nextjs-agent.git -
Meta_Kim
Agents & frameworksGoverned execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.
git clone https://github.com/KimYx0207/Meta_Kim.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.