Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
AWT (AI Watch Tester)
MCP serversAI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.
aat-devqa@1.8.0 -
Aval
MCP serversYour agent asks you before it acts. You answer with one tap on your phone. Human-in-the-loop.
-
AgentGuard by Audiscape
MCP serversStops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.
-
SCRIPTMASTERLABS — SML ticker-research
MCP serversOne cheap, loopable answer per call for a US ticker: market regime, trend + strength, key levels, ne
-
git-qa
MCP serversOpen-source human-in-the-loop QA runner: an AI agent works the test sheet, a person signs off.
-
OpenClaw GenPark Deep Auditor - Multi-hop agent trajectory auditor with cyclic loop detection, diversity scoring, and execution drift prevention.
git clone https://github.com/alphaparkinc/openclaw-genpark-deep-auditor.git -
vibecode-pro-max-kit
PromptsYour 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
git clone https://github.com/withkynam/vibecode-pro-max-kit.git -
bft-progress-council-mcp
MCP serversBFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is
bft-progress-council-mcp@1.1.9 -
Code Guardian
MCP serversSafe to run? Will it work? Complete? An A-F grade for any repo, plus a verify loop. Never runs it.
code-guardian-mcp@0.7.1 -
Agent Trace Check
MCP serversRead a tool-call log from an AI agent run and see which calls failed, looped or were slow.
-
fullstack-langgraph-nextjs-agent
Agents & frameworksProduction-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.
git clone https://github.com/agentailor/fullstack-langgraph-nextjs-agent.git -
ai-engineer-notebooks
PromptsHands-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.
git clone https://github.com/calmrocks/ai-engineer-notebooks.git -
LinkedIn MCP Server (Salesbot)
MCP serversHuman-in-the-loop LinkedIn outreach and a built-in sales CRM for AI agents. Safety-gated, anti-spam.
-
pi
Agents & frameworksA 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.
git clone https://github.com/sky-valley/pi.git -
flutter-flame-harness
Agents & frameworksIdea-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.
git clone https://github.com/tjdrhs90/flutter-flame-harness.git -
Groundtruth — Ask Real Humans
MCP serversHuman-in-the-loop user research: ask real people what the web can't answer, get verbatim replies
-
OnPage.dev
MCP serversFree SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key.
-
67 tools: agent blockpages, onboarding, messaging + hire loop on Hedera. Server never holds keys.
-
diagnosing-bugs
SkillsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
-
chainloop
Agents & frameworksAgentic 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.
git clone https://github.com/chainloop-dev/chainloop.git -
vibe-check
PromptsBy 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.
git clone https://github.com/TexasBedouin/vibe-check.git -
WongStack
SkillsRepo-native workflow for AI coding agents: your team's process, plans, and decisions live in the repo, so Claude Code and Codex run the same explore → plan → apply → ship loop.
git clone https://github.com/matthewwong525/WongStack.git -
Ghost in the Droid
MCP serversGive any AI agent a real Android phone or iPhone. 66 MCP tools, 117 hub skills, human in the loop.
ghost-in-the-droid@1.6.0 -
awesome-ai-agent-tools
PromptsAI agent tools for coding assistants: skills, MCP servers, agent loops, subagents, hooks, plugins, and CLI tools. Machine-readable catalogs. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ agents.
git clone https://github.com/michielhdoteth/awesome-ai-agent-tools.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.