InnerVault

Library

85,340 resources from 11 public sources. 54 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. compozy

    Agents & frameworks

    An operating system for AI agents. The autonomous control plane for your agents: see and steer every Claude Code, Codex, and Cursor session. Always-on agents check in on their own, and you step in only when one needs you.

    Indexed GitHub, compozy 2,873 ★MITUpdated yesterday

    git clone https://github.com/compozy/compozy.git
  2. awesome-ai-anatomy

    Agents & frameworks

    Source code teardowns of 15 AI coding agents. What is actually inside Claude Code, Dify, OpenHands, Cline, MemPalace, oh-my-codex, Goose, Codex CLI, and 7 more. Architecture diagrams, design patterns. Every claim fact-checked.

    Stale GitHub, NeuZhou 253 ★MITUpdated 7 months ago

    git clone https://github.com/NeuZhou/awesome-ai-anatomy.git
  3. the-pair

    Agents & frameworks

    Open-source AI pair programming desktop app: a read-only Mentor and an Executor agent cross-check each other's code to catch AI mistakes before they land. Bring any model — Claude, GPT, Gemini, Kimi, GLM, Qwen or local Ollama. No agent CLI needed. macOS / Windows / Linux.

    Indexed GitHub, timwuhaotian 390 ★Apache-2.0Updated yesterday

    git clone https://github.com/timwuhaotian/the-pair.git
  4. willdeep-cli

    Agents & frameworks

    自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.

    Indexed GitHub, niuwoai 201 ★Custom licence (see repository)Updated today

    git clone https://github.com/niuwoai/willdeep-cli.git
  5. SWE-AF

    Agents & frameworks

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

    Indexed GitHub, Agent-Field 1,129 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/Agent-Field/SWE-AF.git
  6. SztuCode

    Agents & frameworks

    An experimental playground for open-source, all-in-one office AI for universities: code, docs, spreadsheets, slides, browser – all are the AI's workspace. Local-first, event-driven, auditable, with both TypeScript and Python implementations.

    Stale GitHub, rojim666 110 ★MITUpdated 5 days ago

    git clone https://github.com/rojim666/SztuCode.git
  7. open-dynamic-workflows

    Agents & frameworks

    Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

    Stale GitHub, xz1220 111 ★MITUpdated 28 days ago

    git clone https://github.com/xz1220/open-dynamic-workflows.git
  8. joxo

    Agents & frameworks

    Team workspace for AI coding agents: your Claude Code, Codex, Cursor, Gemini CLI and OpenCode agents share one project, task board and handoffs. Desktop, iPhone and MCP server.

    Stale GitHub, JoxoAI 57 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/JoxoAI/joxo.git
  9. wicked-studio

    Agents & frameworks

    The ADE (agentic development environment) for running a team of coding agents: start a job with a chat, answer what needs you with the evidence, and build apps and dashboards over your data in a chat.

    Stale GitHub, mikeparcewski 173 ★MITUpdated 6 days ago

    git clone https://github.com/mikeparcewski/wicked-studio.git
  10. clisbot

    Agents & frameworks

    Agentic Coding CLI & chat bot

    Stale GitHub, longbkit 131 ★Custom licence (see repository)Updated 15 days ago

    git clone https://github.com/longbkit/clisbot.git
  11. coral

    Agents & frameworks

    Agentic IDE for Claude Code, Codex CLI, Antigravity CLI, and Pi.dev

    Indexed GitHub, subgentic 129 ★Apache-2.0Updated today

    git clone https://github.com/subgentic/coral.git
  12. tty7

    Agents & frameworks

    The terminal that outlives its window. Shells survive quitting the app, agents can drive other agents, and remote machines work the same way. Pure Rust, GPU-rendered.

    Stale GitHub, l0ng-ai 1,315 ★Apache-2.0Updated 24 days ago

    git clone https://github.com/l0ng-ai/tty7.git
  13. ovis

    Agents & frameworks

    Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote PCs over SSH, web push alerts

    Indexed GitHub, devswha 2,076 ★MITUpdated today

    git clone https://github.com/devswha/ovis.git
  14. swarm-orchestrator

    Agents & frameworks

    A local coding agent: give it a task, it makes the change, checks each requirement with swarm-verify, and returns the patch with signed evidence of what is done.

    Stale GitHub, moonrunnerkc 113 ★ISCUpdated 12 days ago

    git clone https://github.com/moonrunnerkc/swarm-orchestrator.git
  15. agent-flow

    Agents & frameworks

    Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

    Stale GitHub, patoles 1,702 ★Apache-2.0Updated 37 days ago

    git clone https://github.com/patoles/agent-flow.git
  16. 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 yesterday

    git clone https://github.com/RyanAlberts/best-of-Agent-Harnesses.git
  17. nodecode

    Agents & frameworks

    A living agent organism in Lisp.

    Indexed GitHub, nodecode-ai 273 ★MITUpdated today

    git clone https://github.com/nodecode-ai/nodecode.git
  18. opencastle

    Agents & frameworks

    Multi agens orchestration setup for Github Copilot, Cursor, Claude Code, OpenCode, Windsurf, Codex and Antigravity.

    Stale GitHub, monkilabs 80 ★MITUpdated 11 days ago

    git clone https://github.com/monkilabs/opencastle.git
  19. chainloop

    Agents & frameworks

    Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs, VEX, SARIF and SLSA provenance, built on Sigstore and in-toto. Apache 2.0.

    Stale GitHub, chainloop-dev 604 ★Apache-2.0Updated 24 days ago

    git clone https://github.com/chainloop-dev/chainloop.git
  20. claude-command-center

    Agents & frameworks

    CCC puts coding agents on call for your product. Bugs from customers and monitoring go to agents that fix them. Real decisions reach you by message. Preview.

    Indexed GitHub, amirfish1 219 ★Custom licence (see repository)Updated today

    git clone https://github.com/amirfish1/claude-command-center.git
  21. minimal

    Agents & frameworks

    Run your agent in a Minimal box. Ship and run software with isolation on your own computer.

    Indexed GitHub, gominimal 240 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/gominimal/minimal.git
  22. Mikka

    Agents & frameworks

    Move your coding agents off your laptop. Mikka runs each task on its own isolated cloud machine, connects it with the agents on your computers, and sets everything up from one sentence to the Coordinator.

    Indexed GitHub, alexj11324 87 ★AGPL-3.0Updated today

    git clone https://github.com/alexj11324/Mikka.git
  23. tokscale

    Agents & frameworks

    🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.

    Stale GitHub, junhoyeo 5,720 ★MITUpdated 25 days ago

    git clone https://github.com/junhoyeo/tokscale.git
  24. mobius

    Agents & frameworks

    möbius is a small, frontend-neutral Rust framework for coding agents.

    Indexed GitHub, citizenhicks 566 ★Apache-2.0Updated yesterday

    git clone https://github.com/citizenhicks/mobius.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.