InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

357 results with any of your words Clear search and filters
  1. harness-score

    Agents & frameworks

    Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

    Indexed GitHub, paladini 621 ★MITUpdated 3 days ago

    git clone https://github.com/paladini/harness-score.git
  2. best-of-Agent-Harnesses

    Agents & frameworks

    🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly.

    Indexed GitHub, RyanAlberts 1,526 ★CC-BY-SA-4.0Updated 2 days ago

    git clone https://github.com/RyanAlberts/best-of-Agent-Harnesses.git
  3. AlgoTune

    Agents & frameworks

    AlgoTune 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.

    Stale GitHub, oripress 118 ★MITUpdated 4 months ago

    git clone https://github.com/oripress/AlgoTune.git
  4. daytona

    Agents & frameworks

    Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

    Stale Archived GitHub, daytonaio 71.5k ★Updated 3 months ago 1 note

    git clone https://github.com/daytonaio/daytona.git
  5. xLAM

    Agents & frameworks

    xLAM: A Family of Large Action Models to Empower AI Agent Systems

    Stale GitHub, SalesforceAIResearch 638 ★Apache-2.0Updated 5 months ago

    git clone https://github.com/SalesforceAIResearch/xLAM.git
  6. 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).

    Indexed GitHub, ruvnet 747 ★MITUpdated 3 days ago

    git clone https://github.com/ruvnet/metaharness.git
  7. andee

    Agents & frameworks

    Andee 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。

    Indexed GitHub, kuafuai 6,022 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/kuafuai/andee.git
  8. brepjs

    Agents & frameworks

    CAD in TypeScript with exact solids (B-Rep). AI agents can write parts with it and check them on OpenCascade.

    Indexed GitHub, andymai 142 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/andymai/brepjs.git
  9. agent-starter-kit

    Agents & frameworks

    The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .

    Stale GitHub, ntorga 147 ★MITUpdated 2 months ago

    git clone https://github.com/ntorga/agent-starter-kit.git
  10. assay

    Agents & frameworks

    An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

    Stale GitHub, awss1i 107 ★MITUpdated 29 days ago

    git clone https://github.com/awss1i/assay.git
  11. VoiceMem

    Agents & frameworks

    Infrastructure 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.

    Stale GitHub, xzf-thu 2,510 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/xzf-thu/VoiceMem.git
  12. walrus-memory

    Agents & frameworks

    A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

    Stale GitHub, MystenLabs 132 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/MystenLabs/walrus-memory.git
  13. CodeJury

    Agents & frameworks

    Terminal-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.

    Stale GitHub, krishagarwal314 148 ★MITUpdated 3 months ago

    git clone https://github.com/krishagarwal314/CodeJury.git
  14. C2C

    Agents & frameworks

    [ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

    Stale GitHub, thu-nics 757 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/thu-nics/C2C.git
  15. agentcall

    Agents & frameworks

    AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)

    Indexed GitHub, pattern-ai-labs 201 ★MITUpdated 2 days ago

    git clone https://github.com/pattern-ai-labs/agentcall.git
  16. Claude-of-Tanks

    Agents & frameworks

    A 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.

    Indexed GitHub, Kevin-Liu-01 539 ★MITUpdated 3 days ago

    git clone https://github.com/Kevin-Liu-01/Claude-of-Tanks.git
  17. centra-gideon-agent

    Agents & frameworks

    The companion AI agent that learns, adapts and gets the work done no matter the task

    Stale GitHub, Sidiora-Labs 212 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/Sidiora-Labs/centra-gideon-agent.git
  18. awesome-jev

    Agents & frameworks

    Launch 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.

    Indexed GitHub, kydlikebtc 602 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/kydlikebtc/awesome-jev.git
  19. trinity

    Agents & frameworks

    Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

    Indexed GitHub, Abilityai 777 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/Abilityai/trinity.git
  20. cligate

    Agents & frameworks

    Private 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.

    Stale GitHub, codeking-ai 131 ★AGPL-3.0Updated 33 days ago

    git clone https://github.com/codeking-ai/cligate.git
  21. preference-lab

    Agents & frameworks

    Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.

    Stale GitHub, dengxianghua888-ops 50 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/dengxianghua888-ops/preference-lab.git
  22. ante

    Agents & frameworks

    Ghost 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.

    Stale GitHub, AntigmaLabs 2,014 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/AntigmaLabs/ante.git
  23. Franklin

    Agents & frameworks

    The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.

    Indexed GitHub, BlockRunAI 565 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/BlockRunAI/Franklin.git
  24. cross-review

    Agents & frameworks

    Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.

    Stale GitHub, lploc94 167 ★MITUpdated 6 days ago

    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.