InnerVault

Library

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

Results

  1. FlyEnv

    MCP servers

    Native local development environment for Windows, macOS & Linux. A modern alternative to XAMPP, MAMP, Laragon and Laravel Herd, with runtimes, databases, web servers, local sites, HTTPS, AI coding tools and MCP.

    Indexed GitHub, xpf0000 3,366 ★BSD-3-ClauseUpdated today

    git clone https://github.com/xpf0000/FlyEnv.git
  2. Grok-UI

    Agents & frameworks

    Local-first live command center for Grok Build — runtime, ACP control, session history, and Git changes.

    Stale GitHub, joeynyc 141 ★MITUpdated 18 days ago

    git clone https://github.com/joeynyc/Grok-UI.git
  3. hybridclaw

    AI repositories

    Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory

    Indexed GitHub, HybridAIOne 161 ★MITUpdated 3 days ago

    git clone https://github.com/HybridAIOne/hybridclaw.git
  4. lobu

    MCP servers

    Open-source control plane and runtime for organisational agents: shared company context & brain

    Indexed GitHub, lobu-ai 235 ★Apache-2.0Updated today

    git clone https://github.com/lobu-ai/lobu.git
  5. awsl

    Agents & frameworks

    Codex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees

    Indexed GitHub, XhinLiang 96 ★Apache-2.0Updated yesterday

    git clone https://github.com/XhinLiang/awsl.git
  6. cli-jaw

    Agents & frameworks

    🦈 2-line install personal AI assistant. 11 AI runtime surfaces (Claude, Codex, Cursor, Gemini, Grok, Antigravity, OpenCode, Copilot), 200+ skills, zero ban risk.

    Stale GitHub, lidge-ai 213 ★MITUpdated 8 days ago

    git clone https://github.com/lidge-ai/cli-jaw.git
  7. atmosphere

    AI repositories

    Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

    Indexed GitHub, Atmosphere 3,834 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/Atmosphere/atmosphere.git
  8. awaken

    Agents & frameworks

    AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.

    Indexed GitHub, awakenworks 101 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/awakenworks/awaken.git
  9. mobileClaw

    Agents & frameworks

    Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

    Stale GitHub, eggbrid2 379 ★Custom licence (see repository)Updated 4 months ago

    git clone https://github.com/eggbrid2/mobileClaw.git
  10. AgentLoom

    Agents & frameworks

    Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

    Indexed GitHub, linora-u 169 ★Updated 3 days ago

    git clone https://github.com/linora-u/AgentLoom.git
  11. Reference architecture and working case study for Codex × Antigravity agent-runtime collaboration.

    Stale GitHub, a275618631 11 ★MITUpdated 14 days ago

    git clone https://github.com/a275618631/codex-antigravity-collaboration.git
  12. agentao

    MCP servers

    Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

    Indexed GitHub, jin-bo 312 ★MITUpdated today

    git clone https://github.com/jin-bo/agentao.git
  13. plip-oss

    MCP servers

    Open-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.

    Stale GitHub, hussainn7 39 ★MITUpdated 9 days ago

    git clone https://github.com/hussainn7/plip-oss.git
  14. Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning application. When an AI application can't evaluate data with a high degree of confidence, human reviewers can take over. This human review is called a human review workflow. To create and start a human review workflow, you need three resources: a worker task template , a flow definition , and a human loop…

    Indexed APIs.guru OpenAPI Directory, Mike Ralphson Updated 6 years ago

  15. 🧠 Curated collection of 2700+ best agent skills — AI, coding, marketing, design, finance and more. Harness-agnostic: works with Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, Hermes and any Agent Skills runtime. Refreshed daily by MyClaw.ai — Powered by MyClaw.ai

    Indexed GitHub, LeoYeAI 2,187 ★MITUpdated 3 days ago

    git clone https://github.com/LeoYeAI/agent-master-skills.git
  16. oh-my-diff

    Skills

    Oh My Diff: A Moddable Codex Runtime

    Indexed GitHub, dzkchen 19 ★MITUpdated 2 days ago

    git clone https://github.com/dzkchen/oh-my-diff.git
  17. mnemon

    Agents & frameworks

    LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

    Stale GitHub, mnemon-dev 716 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/mnemon-dev/mnemon.git
  18. mcpsentry

    MCP servers

    Security scanner and runtime proxy for MCP servers.

    Stale Official MCP Registry, io.github.Roshan6335 Updated 2 months ago 1 note

    @roshan6335/mcpsentry@0.1.2
  19. EVMole

    MCP servers

    Local structured analysis of deployed EVM runtime bytecode

    Stale Official MCP Registry, io.github.cdump Updated 34 days ago 1 note

    evmole-mcp@0.9.4
  20. HARTOS

    Agents & frameworks

    An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

    Indexed GitHub, hertz-ai 52 ★Apache-2.0Updated today

    git clone https://github.com/hertz-ai/HARTOS.git
  21. octomind

    Tools & apps

    Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.

    Indexed GitHub, Muvon 663 ★Apache-2.0Updated today

    git clone https://github.com/Muvon/octomind.git
  22. SkillHone

    Skills

    Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

    Stale GitHub, Tencent 172 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/Tencent/SkillHone.git
  23. Writ

    Agents & frameworks

    Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

    Stale GitHub, infinri 217 ★MITUpdated 28 days ago

    git clone https://github.com/infinri/Writ.git
  24. dsh-skill

    Skills

    Official plugin & skill development kit for DeepSeek Harness (DSH). Grounded in core runtime contracts for Claude Code, Codex, Antigravity, and DSH.

    Stale GitHub, realchendahuang 25 ★MITUpdated 23 days ago

    git clone https://github.com/realchendahuang/dsh-skill.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.