InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. Fast Levenshtein distance and fuzzy similarity matcher autocorrecting hallucinated LLM tool calls

    Stale Official MCP Registry, io.github.alphaparkinc Updated 23 days ago 1 note

    https://github.com/Alpha-Park/genpark-levenshtein-fuzzy-tool-matcher-skill/releases/download/v1.0.1/genpark-levenshtein-fuzzy-tool-matcher-skill-v1.0.1.mcpb
  2. SKV Network

    MCP servers

    Memory + answer checks for AI agents: recall across chats, draft→check→seal, fewer hallucinations.

    Stale Official MCP Registry, network.skv Updated 16 days ago 1 note

  3. consensus-pipeline

    Agents & frameworks

    Multi-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线:多智能体部门长线任务解决框架,对抗AI幻觉,以学术研究为验证场景。

    Stale GitHub, fangqian616 120 ★MITUpdated 8 days ago

    git clone https://github.com/fangqian616/consensus-pipeline.git
  4. MetaGO Agent Harness

    MCP servers

    Decision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools.

    Stale Official MCP Registry, io.github.metago-ai Updated 50 days ago 1 note

    @metago-ai/mcp-server@1.3.3
  5. Assess UK lease tenant break clauses with grounded citations and a measured hallucination rate.

    Stale Official MCP Registry, io.github.Ankur-stockheads Updated 4 months ago 2 notes

    uk-break-clause-analyzer-mcp@0.1.1
  6. Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.

    Stale Official MCP Registry, io.github.KyTheKitty Updated 2 months ago 2 notes

    @verify-api/mcp@0.1.9
  7. Agent conversation state snapshotting and time-travel rollback engine pruning divergent hallucinatio

    Stale Official MCP Registry, io.github.alphaparkinc Updated 27 days ago 1 note

    https://github.com/Alpha-Park/genpark-agent-state-snapshot-time-travel-skill/releases/download/v1.0.1/genpark-agent-state-snapshot-time-travel-skill-v1.0.1.mcpb
  8. rails-ai-context

    MCP servers

    Rails MCP server: stop AI coding agents from guessing your app. A Ruby gem with 35 read-only tools that give Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI your real schema, models, routes, controllers and views. MCP or CLI, Gemfile or standalone, and it still answers when the app can't boot.

    Stale GitHub, crisnahine 171 ★MITUpdated 13 days ago

    git clone https://github.com/crisnahine/rails-ai-context.git
  9. civic-ai-tools

    MCP servers

    Open-source platform connecting AI assistants to government open data — MCP server, curated civic MCP directory, and anti-hallucination framework for all 559 Socrata portals

    Indexed GitHub, npstorey 48 ★MITUpdated 3 days ago

    git clone https://github.com/npstorey/civic-ai-tools.git
  10. Check npm packages for typosquats, hallucinated names, install scripts and risky new releases.

    Stale Official MCP Registry, io.github.tylerscomic-lab Updated 46 days ago 1 note

  11. Blocks typosquatted or hallucinated npm/PyPI packages before an AI agent installs them.

    Stale Official MCP Registry, io.github.julian-martin89 Updated 2 months ago 1 note

  12. Flags fake/mismatched token contract addresses and hallucinated supply figures before you trade.

    Stale Official MCP Registry, io.github.julian-martin89 Updated 39 days ago 1 note

  13. Helm MCP

    MCP servers

    Give your AI assistant access to real Helm chart data. No more hallucinated values.yaml files.

    Stale Official MCP Registry, io.github.Kubedoll-Heavy-Industries Updated 7 months ago 1 note

  14. Certified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.

    Stale Official MCP Registry, io.github.Calera-Labs Updated 21 days ago 1 note

  15. LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.

    Stale Official MCP Registry, io.github.JcJamet Updated 21 days ago 1 note

  16. claude-dd

    Skills

    Portable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.

    Stale GitHub, kopp0510 12 ★MITUpdated 17 days ago

    git clone https://github.com/kopp0510/claude-dd.git
  17. The centralized Headquarters for the Cognitive Lead AI multi-agent system. Features hallucination-resistant system prompts, MCP servers, and strict Agent Skills.

    Stale GitHub, mokhtarabadi 8 ★MITUpdated 19 days ago

    git clone https://github.com/mokhtarabadi/cognitive-lead-hq.git
  18. 🧠 Powerful, tested skills for Claude. Featuring CertMaster OS: turn PDFs, syllabi and lecture transcripts into Obsidian/Notion study notes with quizzes and anti-hallucination guardrails.

    Stale GitHub, HackBepa 16 ★MITUpdated 18 days ago

    git clone https://github.com/HackBepa/claude-skills-hub.git
  19. dual-brain

    Prompts

    A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.

    Stale GitHub, sleeplesshan 123 ★MITUpdated 10 days ago

    git clone https://github.com/sleeplesshan/dual-brain.git
  20. B2B GEO MCP: audit AI citations, flag SKU hallucinations, and ship >=9.5/10 JSON-LD & /agents.md.

    Stale Official MCP Registry, dev.verisource Updated 2 days ago 1 note

  21. Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

    Indexed OpenRouter model list, x-ai Updated 7 months ago

    x-ai/grok-4.20
  22. Enter a US stock ticker, get an analyst grade memo with DCF valuation, peer comparables, news sentiment, and earnings call tone analysis. Multi agent LLM pipeline (Claude + GPT-4o devil's advocate) with strict citation validation. FastAPI + Next.js + pgvector RAG. No hallucinated numbers

    Indexed GitHub, kbhujbal 51 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/kbhujbal/AlphaAnalyst-open-source-autonomous-equity-research-agent.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.