InnerVault

Library

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

Results

422 results with any of your words Clear search and filters
  1. A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

    Indexed GitHub, Sanexxxx777 16 ★MITUpdated yesterday

    git clone https://github.com/Sanexxxx777/curated-claude-code.git
  2. planwright

    Skills

    Autopilot for spec-driven development on Claude Code: sign off a spec and a guardrailed agent fleet builds, reviews, and delivers draft PRs. Scales from one feature to an agentic software factory. You keep sign-off and merge.

    Stale GitHub, inkatze 5 ★MITUpdated 12 days ago

    git clone https://github.com/inkatze/planwright.git
  3. aihappey-chat

    Skills

    Browser-native multi-provider AI client with chat, Agents, MCP, Skills, Plugins, Decisions, BYOK/OAuth and human-in-the-loop workflows.

    Stale GitHub, achappey 6 ★Updated 15 days ago

    git clone https://github.com/achappey/aihappey-chat.git
  4. AWT (AI Watch Tester)

    MCP servers

    AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.

    Stale Official MCP Registry, io.github.ksgisang Updated 33 days ago 2 notes

    aat-devqa@1.8.0
  5. Aval

    MCP servers

    Your agent asks you before it acts. You answer with one tap on your phone. Human-in-the-loop.

    Stale Official MCP Registry, io.github.taraxe Updated 29 days ago 1 note

  6. Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.

    Stale Official MCP Registry, com.audiscape.agentguard Updated 16 days ago 1 note

  7. One cheap, loopable answer per call for a US ticker: market regime, trend + strength, key levels, ne

    Stale Official MCP Registry, com.scriptmasterlabs Updated 14 days ago 1 note

  8. git-qa

    MCP servers

    Open-source human-in-the-loop QA runner: an AI agent works the test sheet, a person signs off.

    Stale Official MCP Registry, io.github.meta-taro Updated 6 days ago

  9. OpenClaw GenPark Deep Auditor - Multi-hop agent trajectory auditor with cyclic loop detection, diversity scoring, and execution drift prevention.

    Stale GitHub, alphaparkinc 7 ★MITUpdated 17 days ago

    git clone https://github.com/alphaparkinc/openclaw-genpark-deep-auditor.git
  10. Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

    Stale GitHub, withkynam 1,151 ★MITUpdated 4 months ago

    git clone https://github.com/withkynam/vibecode-pro-max-kit.git
  11. BFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 49 days ago 3 notes

    bft-progress-council-mcp@1.1.9
  12. Code Guardian

    MCP servers

    Safe to run? Will it work? Complete? An A-F grade for any repo, plus a verify loop. Never runs it.

    Stale Official MCP Registry, io.github.LuminariSoftwares Updated 5 days ago 1 note

    code-guardian-mcp@0.7.1
  13. Agent Trace Check

    MCP servers

    Read a tool-call log from an AI agent run and see which calls failed, looped or were slow.

    Stale Official MCP Registry, app.openkrill Updated 32 days ago 1 note

  14. fullstack-langgraph-nextjs-agent

    Agents & frameworks

    Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.

    Stale GitHub, agentailor 134 ★MITUpdated 2 months ago

    git clone https://github.com/agentailor/fullstack-langgraph-nextjs-agent.git
  15. Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.

    Stale GitHub, calmrocks 743 ★MITUpdated 10 days ago

    git clone https://github.com/calmrocks/ai-engineer-notebooks.git
  16. Human-in-the-loop LinkedIn outreach and a built-in sales CRM for AI agents. Safety-gated, anti-spam.

    Stale Official MCP Registry, cz.salesbot Updated 5 months ago 1 note

  17. 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 2 days ago

    git clone https://github.com/sky-valley/pi.git
  18. flutter-flame-harness

    Agents & frameworks

    Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, generator-evaluator loops, AdMob, and store submission.

    Indexed GitHub, tjdrhs90 61 ★MITUpdated yesterday

    git clone https://github.com/tjdrhs90/flutter-flame-harness.git
  19. Human-in-the-loop user research: ask real people what the web can't answer, get verbatim replies

    Stale Official MCP Registry, app.vercel.groundtruth-ruby Updated 2 months ago 1 note

  20. OnPage.dev

    MCP servers

    Free SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key.

    Stale Official MCP Registry, dev.onpage Updated 34 days ago 1 note

  21. 67 tools: agent blockpages, onboarding, messaging + hire loop on Hedera. Server never holds keys.

    Stale Official MCP Registry, io.github.VoiceScapee Updated 28 days ago 1 note

  22. Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  23. 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 25 days ago

    git clone https://github.com/chainloop-dev/chainloop.git
  24. vibe-check

    Prompts

    By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics, clean-code habits, a verify-and-iterate loop, a checkup for the mess). For Claude Code, Codex, and Antigravity. grill-me is for engineers, vibe-check is for everyone else.

    Indexed GitHub, TexasBedouin 640 ★MITUpdated 4 days ago

    git clone https://github.com/TexasBedouin/vibe-check.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.