Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
playwright_mcp
Agents & frameworksinvisible playwright mcp: Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.
git clone https://github.com/oss-invisible/playwright_mcp.git -
Awesome-Agent-Harness
Agents & frameworksThe first survey dedicated to LLM agent harnesses — 168 references, 34 evidence-coded systems, and 30 evaluation entries.
git clone https://github.com/Gloriaameng/Awesome-Agent-Harness.git -
Lynn
Agents & frameworks开源桌面 AI Agent 与 CLI:长期记忆、多 Agent、实时语音;Qwen3.8-27B Coder390 EfficientThink 本地 GGUF(llama.cpp Q2/Q3,内置 Q4 MTP)· Open-source desktop AI agent & CLI with Coder390 local models
git clone https://github.com/MerkyorLynn/Lynn.git -
PumpGrok
Agents & frameworks1-Click Grok Bot 8 Man Crypto Trading Desk as seen on X
git clone https://github.com/swcstudiospace/PumpGrok.git -
agency-orchestrator
Agents & frameworks🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。
git clone https://github.com/jnMetaCode/agency-orchestrator.git -
verl-agent
Agents & frameworksverl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
git clone https://github.com/langfengQ/verl-agent.git -
Aegis
Agents & frameworksRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes.
git clone https://github.com/Justin0504/Aegis.git -
ntm
Agents & frameworksNamed Tmux Manager: a Go control plane to spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Antigravity, omp, Grok) across tmux panes - graph-aware work triage, safety policy and approvals, Agent Mail coordination, checkpoints/timelines, and robot JSON + REST/SSE/WebSocket/OpenAPI surfaces.
git clone https://github.com/Dicklesworthstone/ntm.git -
EhrAgent
Agents & frameworks[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records
git clone https://github.com/wshi83/EhrAgent.git -
OpenFlow
Agents & frameworksOpenFlow — a visual builder for multi-agent AI workflows, built on the opencode engine
git clone https://github.com/SeeRay11/OpenFlow.git -
guaca
Agents & frameworksA quiet group of AI agents on your own machine. Works out of sight, tells you only what matters. AGPL, self-hosted.
git clone https://github.com/madebywelch/guaca.git -
ai-factory
Agents & frameworksYou want to build with AI, but setting up the right context, prompts, and workflows takes time. AI Factory handles all of that so you can focus on what matters — shipping quality code.
git clone https://github.com/lee-to/ai-factory.git -
dsh-im
Agents & frameworks通过扫码或机器人凭据把IM机器人接入DeepSeek Harness(支持飞书、微信、钉钉、企业微信、QQ、Slack、Telegram、Discord和WhatsApp)。 Connect IM bots to DeepSeek Harness via QR code or credentials (9 channels).
git clone https://github.com/xmanrui/dsh-im.git -
adk-js
Agents & frameworksAn open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
git clone https://github.com/google/adk-js.git -
meta_skill
Agents & frameworksLocal-first skill management platform for AI coding agents: dual SQLite+Git persistence, semantic search, bandit-optimized suggestions, and MCP integration
git clone https://github.com/Dicklesworthstone/meta_skill.git -
opencode-team
Agents & frameworksAI agent team that takes an idea from research to launch, built on opencode. No framework, no extra dependencies.
git clone https://github.com/sametcelikbicak/opencode-team.git -
generative-ai
Agents & frameworksComprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.
git clone https://github.com/genieincodebottle/generative-ai.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 -
Proxima
Agents & frameworksMulti-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API
git clone https://github.com/Zen4-bit/Proxima.git -
harness-score
Agents & frameworksYour AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.
git clone https://github.com/paladini/harness-score.git -
kensaku
Agents & frameworksSearch inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
git clone https://github.com/yjid/kensaku.git -
agentcall
Agents & frameworksAgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)
git clone https://github.com/pattern-ai-labs/agentcall.git -
adk-java
Agents & frameworksAn open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
git clone https://github.com/google/adk-java.git -
dsh-auto-review
Agents & frameworksSecond-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
git clone https://github.com/PerryLink/dsh-auto-review.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.