Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
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 -
best-of-Agent-Harnesses
Agents & frameworks🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.
git clone https://github.com/RyanAlberts/best-of-Agent-Harnesses.git -
AlgoTune
Agents & frameworksAlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.
git clone https://github.com/oripress/AlgoTune.git -
daytona
Agents & frameworksDaytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
git clone https://github.com/daytonaio/daytona.git -
xLAM
Agents & frameworksxLAM: A Family of Large Action Models to Empower AI Agent Systems
git clone https://github.com/SalesforceAIResearch/xLAM.git -
metaharness
Agents & frameworks🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
git clone https://github.com/ruvnet/metaharness.git -
andee
Agents & frameworksAndee lives on your phone or Mac and uses any app like you do—no integrations, no root, any model; memory and passwords never leave your device | Andee 住进你的手机或 Mac,像你一样操作任何 App——无需集成、无需 Root、支持任意模型,记忆和密码绝不离开设备。
git clone https://github.com/kuafuai/andee.git -
brepjs
Agents & frameworksCAD in TypeScript with exact solids (B-Rep). AI agents can write parts with it and check them on OpenCascade.
git clone https://github.com/andymai/brepjs.git -
agent-starter-kit
Agents & frameworksThe scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .
git clone https://github.com/ntorga/agent-starter-kit.git -
assay
Agents & frameworksAn agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.
git clone https://github.com/awss1i/assay.git -
VoiceMem
Agents & frameworksInfrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
git clone https://github.com/xzf-thu/VoiceMem.git -
walrus-memory
Agents & frameworksA portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
git clone https://github.com/MystenLabs/walrus-memory.git -
CodeJury
Agents & frameworksTerminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.
git clone https://github.com/krishagarwal314/CodeJury.git -
C2C
Agents & frameworks[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
git clone https://github.com/thu-nics/C2C.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 -
Claude-of-Tanks
Agents & frameworksA World of Tanks-style armored combat simulator built directly with Three.js and Vite: 220 vehicles, 33 destructible battlefields, and 13 modes, with plate-level armor, ballistics, modules, spotting, and physics. Play in your browser on desktop or mobile. Built end-to-end by a multi-agent Claude/Codex pipeline.
git clone https://github.com/Kevin-Liu-01/Claude-of-Tanks.git -
centra-gideon-agent
Agents & frameworksThe companion AI agent that learns, adapts and gets the work done no matter the task
git clone https://github.com/Sidiora-Labs/centra-gideon-agent.git -
awesome-jev
Agents & frameworksLaunch what you built on Jev, TypeSafe AI's System One decision model: a weekly board where makers launch and people vote, over an index of public Jev examples by decision pattern, with source citations, dated link checks and call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema, platform matrix.
git clone https://github.com/kydlikebtc/awesome-jev.git -
trinity
Agents & frameworksSelf-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
git clone https://github.com/Abilityai/trinity.git -
cligate
Agents & frameworksPrivate AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tasks,model routing, accounts, keys, logs, dashboard.
git clone https://github.com/codeking-ai/cligate.git -
preference-lab
Agents & frameworksPolicy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.
git clone https://github.com/dengxianghua888-ops/preference-lab.git -
ante
Agents & frameworksGhost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.
git clone https://github.com/AntigmaLabs/ante.git -
Franklin
Agents & frameworksThe AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
git clone https://github.com/BlockRunAI/Franklin.git -
cross-review
Agents & frameworksCross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.
git clone https://github.com/lploc94/cross-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.