InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

2,041 results Clear search and filters

Looks like a goal we have a starting path for: I want to build an AI agent

  1. kiso

    Agents & frameworks

    The durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line TypeScript kernel, and kiso-code, the coding agent built on it.

    Indexed GitHub, vincemakes 96 ★MITUpdated today

    git clone https://github.com/vincemakes/kiso.git
  2. cuga-agent

    Agents & frameworks

    CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

    Indexed GitHub, cuga-project 1,186 ★Apache-2.0Updated yesterday

    git clone https://github.com/cuga-project/cuga-agent.git
  3. wmux

    MCP servers

    The ADE for AI agents. Automate everything else. Do your true work.

    Indexed GitHub, openwong2kim 455 ★MITUpdated today

    git clone https://github.com/openwong2kim/wmux.git
  4. Arcgentic

    MCP servers

    Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

    Stale GitHub, Arch1eSUN 285 ★MITUpdated 45 days ago

    git clone https://github.com/Arch1eSUN/Arcgentic.git
  5. awesome-jev

    Skills

    Jev demos, projects, SDKs and skills, with source links and a curated X gallery.

    Indexed GitHub, Amal-David 247 ★CC0-1.0Updated 3 days ago

    git clone https://github.com/Amal-David/awesome-jev.git
  6. heym

    MCP servers

    Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

    Indexed GitHub, heymrun 1,684 ★Custom licence (see repository)Updated today

    git clone https://github.com/heymrun/heym.git
  7. Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP needed.

    Stale GitHub, szymdzum 177 ★MITUpdated 28 days ago

    git clone https://github.com/szymdzum/browser-debugger-cli.git
  8. awesome-multi-agent-orchestrators

    Agents & frameworks

    Awesome-style curated list and directory for multi-agent orchestration.

    Indexed GitHub, Agent-Analytics 189 ★Updated today

    git clone https://github.com/Agent-Analytics/awesome-multi-agent-orchestrators.git
  9. pydantic-deepagents

    Agents & frameworks

    Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

    Stale GitHub, vstorm-co 1,111 ★MITUpdated 17 days ago

    git clone https://github.com/vstorm-co/pydantic-deepagents.git
  10. UltraData-SFT-Agent-2609

    Datasets & benchmarks

    Hugging Face dataset by openbmb

    Indexed Hugging Face Hub, openbmb 322 ♥apache-2.0Updated 2 months ago

    openbmb/UltraData-SFT-Agent-2609
  11. Martin Loop

    MCP servers

    One system around coding agents to run, verify, recover, and hand off software work.

    Stale Official MCP Registry, io.github.Keesan12 394 ★Updated 13 days ago 1 note

    @martinloop/mcp@0.9.0
  12. hippo-memory

    MCP servers

    Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). Local-first. Measured: about half the repeat mistakes of built-in memory alone, at the same cost.

    Indexed GitHub, kitfunso 792 ★MITUpdated 4 days ago

    git clone https://github.com/kitfunso/hippo-memory.git
  13. kanzo

    MCP servers

    Self-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.

    Stale GitHub, emanuele-em 1,149 ★AGPL-3.0Updated 5 days ago

    git clone https://github.com/emanuele-em/kanzo.git
  14. self-bench

    Datasets & benchmarks

    Benchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.

    Indexed GitHub, mupt-ai 34 ★MITUpdated today

    git clone https://github.com/mupt-ai/self-bench.git
  15. 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
  16. paneflow

    MCP servers

    Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI.

    Indexed GitHub, arthjean 96 ★GPL-3.0Updated yesterday

    git clone https://github.com/arthjean/paneflow.git
  17. lazyskills

    Tools & apps

    mission control for agent skills

    Stale GitHub, alvinunreal 291 ★MITUpdated 51 days ago

    git clone https://github.com/alvinunreal/lazyskills.git
  18. Hill-Climb

    Skills

    Make your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.

    Indexed GitHub, Bil0000 111 ★MITUpdated 4 days ago

    git clone https://github.com/Bil0000/Hill-Climb.git
  19. paperthin

    Skills

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    Indexed GitHub, LilMGenius 1,445 ★MITUpdated yesterday

    git clone https://github.com/LilMGenius/paperthin.git
  20. troupe

    Agents & frameworks

    Run a team of coding agents you can actually watch: one approved plan, each role in its own tmux window and git worktree, on Claude Code or Codex.

    Indexed GitHub, hitianqi 54 ★MITUpdated 3 days ago

    git clone https://github.com/hitianqi/troupe.git
  21. agy-staff

    Agents & frameworks

    Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.

    Indexed GitHub, keli-wen 860 ★MITUpdated 4 days ago

    git clone https://github.com/keli-wen/agy-staff.git
  22. skills

    Skills

    Agent skills and MCP servers that teach coding agents to write, run, and repair Momentic tests.

    Indexed GitHub, momentic-ai 17 ★Custom licence (see repository)Updated today

    git clone https://github.com/momentic-ai/skills.git
  23. Linghun

    Tools & apps

    AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

    Indexed GitHub, linghungegeg 475 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/linghungegeg/Linghun.git
  24. friday

    Agents & frameworks

    A local-first desktop alternative to Grok Bot, OpenBot, T3 Code, Herdr and Orca. Run Claude Code, Codex, Cursor and 13 more coding agents as one team on your own computer: a shared board, agents that check each other’s work, and no account. Free. macOS, Windows, Linux.

    Indexed GitHub, splashxmoon 67 ★MITUpdated yesterday

    git clone https://github.com/splashxmoon/friday.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.