Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Kojen
MCP serversTrain, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.
-
CleanCode AI
MCP serversAutomated codebase refactoring and type safety validator.
-
CodeVulnerability
MCP serversOWASP threat scanner auditing codebases for safety leaks.
-
chat-gun
Agents & frameworks🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools, Qwen/OpenAI-compatible LLM gateway. Ships an after-sales support agent: cited RAG with abstention, human-approved refunds, idempotent execution. OpenTelemetry + reproducible evals.
git clone https://github.com/HsienW/chat-gun.git -
verbatim-citation-gate
SkillsCatch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-of-proof judge, framework-agnostic.
git clone https://github.com/tonydzi/verbatim-citation-gate.git -
claude-skills
SkillsSix Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.
git clone https://github.com/alonbaron/claude-skills.git -
Orq.ai
MCP serversBuild and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
-
Speko AI
MCP serversManage Speko voice-AI agents, sessions, calls, phone numbers, knowledge bases, evals, and docs.
-
rubrkit
MCP serversMCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
-
changegamer
MCP serversAgent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
-
sendblue-browser-mcp
MCP serversDrive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.
sendblue-browser-mcp@0.2.3 -
Model Finder
MCP serversFind the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing
model-finder-mcp@1.3.7 -
vibescan
MCP serversFree security scan for AI-written GitHub repos: leaked keys, .env, eval, SQLi, CORS.
-
Sikaru Docs
MCP serversRead-only search over the public Sikaru documentation: managed agents, inference, evals and traces.
-
Grepped marketplace
MCP serversReal company data for AI post-training, evals and RL environments, for qualified buyers.
-
hypokrates
MCP serversPharmacovigilance hypothesis generation from 15 public drug safety databases
hypokrates@0.7.1 -
ai-watermark-scrambler
SkillsScramble statistical AI text watermarks by rewriting with a local model (vLLM, Ollama), and strip C2PA, EXIF, XMP and invisible Unicode. Agent skill plus Python CLI.
git clone https://github.com/novatechflow/ai-watermark-scrambler.git -
agent-leash
SkillsLEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.
git clone https://github.com/tonydzi/agent-leash.git -
evalgate
MCP serversStatistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
eval-integrity@0.4.1 -
evalpair
MCP serversRun LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.
evalpair@0.1.1 -
skill-harness
SkillsHow do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”
git clone https://github.com/MrBinnacle/skill-harness.git -
FireBuy
MCP serversRFQ and quote comparison checklist for fire/public safety purchasing.
-
Aegis Policy
MCP serversGovernance firewall and safety guardrails oracle for AI swarms.
-
Tool-Guardian-Proxy
MCP serversSafety execution proxy protecting clients during tool calls.
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.