Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
exo-harness-ai-pipeline
SkillsClaude Code AI Pipeline 2026 – PEV Framework Harness Plugin for Developers
git clone https://github.com/belialberu4-oss/exo-harness-ai-pipeline.git -
knowhere
Agents & frameworksKnowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
git clone https://github.com/Ontos-AI/knowhere.git -
awesome-harness-engineering
Agents & frameworksAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
git clone https://github.com/ai-boost/awesome-harness-engineering.git -
Chorus
Agents & frameworksThe Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
git clone https://github.com/Chorus-AIDLC/Chorus.git -
harness-mix
Agents & frameworksgit clone https://github.com/emo-xiaoyu/harness-mix.git -
AndroidHarness
Agents & frameworksAndroid Harness AI Coding Agent Native app for mobile, No Root No PC
git clone https://github.com/Sanuu7/AndroidHarness.git -
gepa
PromptsOptimize prompts, code, and more with AI-powered Reflective Optimization
git clone https://github.com/gepa-ai/gepa.git -
TORCH
SkillsKarpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian
git clone https://github.com/Encod3d-Sec/TORCH.git -
javis-os
MCP serversgit clone https://github.com/blogminhquy/javis-os.git -
marveen
Agents & frameworksAI csapatod, ami fut amíg te alszol.
git clone https://github.com/Szotasz/marveen.git -
zot
Agents & frameworksYet another coding agent harness, lightweight and written in go.
git clone https://github.com/patriceckhart/zot.git -
starnet
Agents & frameworksA living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
git clone https://github.com/androoAGI/starnet.git -
codex-claude-code-config
PromptsClaude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development
git clone https://github.com/AnastasiyaW/codex-claude-code-config.git -
san
Agents & frameworksOpen-source terminal agent runtime. Lean context, native speed, open all the way down — in a single Go binary.
git clone https://github.com/genai-io/san.git -
agnt
Tools & appsThe local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.
git clone https://github.com/agnt-gg/agnt.git -
claude-code-source-analysis
Agents & frameworksClaude Code 源码深度研究,包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。
git clone https://github.com/xiaonancs/claude-code-source-analysis.git -
grasp
Tools & appsGrasp helps you manage multiple projects and parallel coding agents in one visual workflow, so humans can understand faster and ship more.
git clone https://github.com/cocofhu/grasp.git -
zenith
MCP serversZenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
git clone https://github.com/Intelligent-Internet/zenith.git -
codex-source-analysis
Agents & frameworksOpenAI Codex 源码深度研究 (Rust + TS + Python):2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图
git clone https://github.com/xiaonancs/codex-source-analysis.git -
openharness
MCP serversThe ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
git clone https://github.com/autonomous-ai/openharness.git -
explicit-edit-benchmark
Datasets & benchmarksBenchmark coding agents and agent harnesses on 226 deterministic file-editing tasks with byte-exact verification and a public leaderboard.
git clone https://github.com/alexshpunt/explicit-edit-benchmark.git -
Empryo
Tools & appsAI coding harness for desktop, terminal and CI. Maps your repo, edits code by symbol through AST and LSP, then runs your checks. Any model or the plan you already pay for. Get it at https://empryo.com
git clone https://github.com/proxysoul/Empryo.git -
mu
Agents & frameworksmu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
git clone https://github.com/qybaihe/mu.git -
navin
SkillsOpen-source AI agents for coding, research and automation. Run locally with your models, persistent memory, multi-agent execution, skills, MCP and self-evolving.
git clone https://github.com/Navinspire-ia/navin.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.