InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

1,096 results with any of your words Clear search and filters
  1. Kojen

    MCP servers

    Train, evaluate, red-team and deploy AI agents: prompt tuning, LLM-judged evals, katas.

    Stale Official MCP Registry, ai.kojen Updated 9 days ago 1 note

  2. CleanCode AI

    MCP servers

    Automated codebase refactoring and type safety validator.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  3. CodeVulnerability

    MCP servers

    OWASP threat scanner auditing codebases for safety leaks.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  4. 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.

    Indexed GitHub, HsienW 141 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/HsienW/chat-gun.git
  5. Catch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-of-proof judge, framework-agnostic.

    Indexed GitHub, tonydzi 6 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/verbatim-citation-gate.git
  6. claude-skills

    Skills

    Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.

    Indexed GitHub, alonbaron 14 ★MITUpdated 2 days ago

    git clone https://github.com/alonbaron/claude-skills.git
  7. Orq.ai

    MCP servers

    Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.

    Stale Official MCP Registry, ai.orq Updated 3 months ago 1 note

  8. Speko AI

    MCP servers

    Manage Speko voice-AI agents, sessions, calls, phone numbers, knowledge bases, evals, and docs.

    Stale Official MCP Registry, ai.speko Updated 5 months ago 1 note

  9. rubrkit

    MCP servers

    MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

    Stale Official MCP Registry, com.rubrkit Updated 4 months ago 1 note

  10. changegamer

    MCP servers

    Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.

    Stale Official MCP Registry, io.github.beneb89 Updated 4 months ago 1 note

  11. sendblue-browser-mcp

    MCP servers

    Drive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.

    Stale Official MCP Registry, io.github.sendblue-api Updated 5 months ago 2 notes

    sendblue-browser-mcp@0.2.3
  12. Model Finder

    MCP servers

    Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing

    Stale Official MCP Registry, co.indigloo Updated 14 days ago 1 note

    model-finder-mcp@1.3.7
  13. vibescan

    MCP servers

    Free security scan for AI-written GitHub repos: leaked keys, .env, eval, SQLi, CORS.

    Stale Official MCP Registry, net.bigfloppy.vibescan Updated 19 days ago 1 note

  14. Sikaru Docs

    MCP servers

    Read-only search over the public Sikaru documentation: managed agents, inference, evals and traces.

    Stale Official MCP Registry, ai.sikaru Updated 13 days ago 1 note

  15. Grepped marketplace

    MCP servers

    Real company data for AI post-training, evals and RL environments, for qualified buyers.

    Stale Official MCP Registry, ai.grepped Updated 10 days ago 1 note

  16. hypokrates

    MCP servers

    Pharmacovigilance hypothesis generation from 15 public drug safety databases

    Stale Official MCP Registry, io.github.bruno-portfolio Updated 8 months ago 1 note

    hypokrates@0.7.1
  17. Scramble 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.

    Stale GitHub, novatechflow 7 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/novatechflow/ai-watermark-scrambler.git
  18. agent-leash

    Skills

    LEASH-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.

    Indexed GitHub, tonydzi 5 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/agent-leash.git
  19. evalgate

    MCP servers

    Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).

    Stale Official MCP Registry, io.github.ipezygj Updated 3 months ago 1 note

    eval-integrity@0.4.1
  20. evalpair

    MCP servers

    Run LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.

    Stale Official MCP Registry, io.github.Srikarmk Updated 12 days ago 2 notes

    evalpair@0.1.1
  21. skill-harness

    Skills

    How 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?”

    Stale GitHub, MrBinnacle 16 ★MITUpdated 15 days ago

    git clone https://github.com/MrBinnacle/skill-harness.git
  22. FireBuy

    MCP servers

    RFQ and quote comparison checklist for fire/public safety purchasing.

    Stale Official MCP Registry, com.checkmycontractorquote Updated 3 months ago 1 note

  23. Aegis Policy

    MCP servers

    Governance firewall and safety guardrails oracle for AI swarms.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  24. Tool-Guardian-Proxy

    MCP servers

    Safety execution proxy protecting clients during tool calls.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

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.