InnerVault

Library

85,762 resources from 11 public sources. 53 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

  1. dsh-auto-memory

    Agents & frameworks

    Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

    Indexed GitHub, AskTheWay 132 ★MITUpdated 2 days ago

    git clone https://github.com/AskTheWay/dsh-auto-memory.git
  2. localharness

    Agents & frameworks

    An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).

    Stale GitHub, ahwurm 59 ★MITUpdated 12 days ago

    git clone https://github.com/ahwurm/localharness.git
  3. Agent-App

    Skills

    Agent App is application that AI agent can build, evolve, and operate. A collaboration space for both humans and agents.

    Stale GitHub, CraftOS-dev 8 ★MITUpdated 8 days ago

    git clone https://github.com/CraftOS-dev/Agent-App.git
  4. ruflo

    MCP servers

    🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

    Indexed GitHub, ruvnet 81.8k ★MITUpdated today

    git clone https://github.com/ruvnet/ruflo.git
  5. open-astravia

    Skills

    开源 · 本地优先的 AI 智能体:编程与实干兼备。 自带模型密钥,内置 MCP、技能、插件、工作流、知识库以及数据库。

    Indexed GitHub, maomaochong-ai 53 ★Apache-2.0Updated yesterday

    git clone https://github.com/maomaochong-ai/open-astravia.git
  6. Orkas

    Agents & frameworks

    Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.

    Indexed GitHub, Orkas-AI 9,388 ★MITUpdated yesterday

    git clone https://github.com/Orkas-AI/Orkas.git
  7. BossConsole

    MCP servers

    Open-source, multi-platform harness for AI agents - a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 200+ MCP tools. Built for enterprises, science & research.

    Stale GitHub, risa-labs-inc 816 ★Apache-2.0Updated 20 days ago

    git clone https://github.com/risa-labs-inc/BossConsole.git
  8. alloy

    Agents & frameworks

    Model-agnostic agent harness for Elixir

    Stale GitHub, alloy-ex 91 ★MITUpdated 34 days ago

    git clone https://github.com/alloy-ex/alloy.git
  9. speq-skill

    Skills

    A light-weight and straightforward workflow for spec-driven development with Claude Code and Codex. Written in Rust 🦀

    Stale GitHub, marconae 55 ★MITUpdated 30 days ago

    git clone https://github.com/marconae/speq-skill.git
  10. harness-sdk

    Agents & frameworks

    Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

    Indexed GitHub, strands-agents 9,221 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/strands-agents/harness-sdk.git
  11. garcon

    Agents & frameworks

    Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.

    Indexed GitHub, cfal 104 ★Custom licence (see repository)Updated today

    git clone https://github.com/cfal/garcon.git
  12. OpenAdapt

    Tools & apps

    For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt turns it into a local program that repeats the steps with no model calls, checks each save, and stops when something doesn't match.

    Indexed GitHub, OpenAdaptAI 1,884 ★MITUpdated 2 days ago

    git clone https://github.com/OpenAdaptAI/OpenAdapt.git
  13. waku-agent

    Agents & frameworks

    Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

    Indexed GitHub, ShenSeanChen 2,177 ★MITUpdated yesterday

    git clone https://github.com/ShenSeanChen/waku-agent.git
  14. mi

    Tools & apps

    self-extending sandboxed agentic harness. a loop, two tools and an llm

    Indexed GitHub, av 106 ★Updated 5 days ago

    git clone https://github.com/av/mi.git
  15. Agentic PR reviews for the IBM Carbon Design System, run by IBM Bob or Claude from a codified review prompt and grounded by Carbon MCP. Built on a reusable agent harness for IBM Cloud Code Engine: scheduled, parallel runs, a per-run spend cap, a web console, Elasticsearch telemetry and a Slack digest. A skill adapts it to your repo, job or agent.

    Indexed GitHub, carbon-design-system 34 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/carbon-design-system/Carbon-Monitor.git
  16. clawboo

    Agents & frameworks

    An open-source studio for teams of AI agents, from marketing squads to dev teams to research crews. Deploy a team, then watch them delegate and collaborate live. Self-hosted, one command.

    Indexed GitHub, clawboo 171 ★MITUpdated today

    git clone https://github.com/clawboo/clawboo.git
  17. Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in computer control.

    Stale GitHub, Kyne0328 26 ★Apache-2.0Updated 14 days ago

    git clone https://github.com/Kyne0328/rel-ai-chatgpt-web-harness.git
  18. pioneer

    Skills

    Multiplayer harness where humans and AI agents work together and build on shared context.

    Stale GitHub, pioneerdotai 21 ★MITUpdated 4 days ago

    git clone https://github.com/pioneerdotai/pioneer.git
  19. SharpClawCode

    Tools & apps

    C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins

    Stale GitHub, clawdotnet 110 ★MITUpdated 10 days ago

    git clone https://github.com/clawdotnet/SharpClawCode.git
  20. Improve Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.

    Stale GitHub, rwang23 5 ★MITUpdated 16 days ago

    git clone https://github.com/rwang23/skill-evolution.git
  21. forge

    Skills

    Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.

    Stale GitHub, brightstack 12 ★MITUpdated 18 days ago

    git clone https://github.com/brightstack/forge.git
  22. learn-agent-the-hard-way

    Docs & tutorials

    笨办法学 Agent · 亲手打造一个 harness——不用框架,32 个练习亲手写出一个 agent harness 的每一层。系列第一本,全书已完结,三本各自独立不分先后。

    Stale GitHub, Leihb 61 ★Custom licence (see repository)Updated 57 days ago

    git clone https://github.com/Leihb/learn-agent-the-hard-way.git
  23. pi

    Agents & frameworks

    A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop, and pi-coding-agent, native in Go with no Node.js runtime. Anthropic/OpenAI/Google, 999-model catalog.

    Indexed GitHub, sky-valley 89 ★MITUpdated yesterday

    git clone https://github.com/sky-valley/pi.git
  24. openbench

    Datasets & benchmarks

    Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost

    Stale GitHub, minghinmatthewlam 137 ★MITUpdated 2 months ago

    git clone https://github.com/minghinmatthewlam/openbench.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.