Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
GenPark Levenshtein Fuzzy Tool Matcher
MCP serversFast Levenshtein distance and fuzzy similarity matcher autocorrecting hallucinated LLM tool calls
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 -
SKV Network
MCP serversMemory + answer checks for AI agents: recall across chats, draft→check→seal, fewer hallucinations.
-
consensus-pipeline
Agents & frameworksMulti-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。
git clone https://github.com/fangqian616/consensus-pipeline.git -
MetaGO Agent Harness
MCP serversDecision lock, anti-hallucination, meta-evolution and provenance for any MCP agent. 55 tools.
@metago-ai/mcp-server@1.3.3 -
UK Break Clause Analyzer
MCP serversAssess UK lease tenant break clauses with grounded citations and a measured hallucination rate.
uk-break-clause-analyzer-mcp@0.1.1 -
VerifyAPI — fact-check with signed receipts
MCP serversFact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.
@verify-api/mcp@0.1.9 -
GenPark Agent State Snapshot & Time-Travel Skill
MCP serversAgent conversation state snapshotting and time-travel rollback engine pruning divergent hallucinatio
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 -
rails-ai-context
MCP serversRails 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.
git clone https://github.com/crisnahine/rails-ai-context.git -
civic-ai-tools
MCP serversOpen-source platform connecting AI assistants to government open data — MCP server, curated civic MCP directory, and anti-hallucination framework for all 559 Socrata portals
git clone https://github.com/npstorey/civic-ai-tools.git -
npm Supply Chain Audit
MCP serversCheck npm packages for typosquats, hallucinated names, install scripts and risky new releases.
-
pkg-oracle — Dependency Trust Oracle
MCP serversBlocks typosquatted or hallucinated npm/PyPI packages before an AI agent installs them.
-
token-oracle — Token Trust Oracle
MCP serversFlags fake/mismatched token contract addresses and hallucinated supply figures before you trade.
-
Helm MCP
MCP serversGive your AI assistant access to real Helm chart data. No more hallucinated values.yaml files.
-
Calera FINSEC — Certified SEC Memory
MCP serversCertified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.
-
IA-QA Eval & RAG — 38 tools
MCP serversLLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.
-
claude-dd
SkillsPortable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.
git clone https://github.com/kopp0510/claude-dd.git -
cognitive-lead-hq
SkillsThe centralized Headquarters for the Cognitive Lead AI multi-agent system. Features hallucination-resistant system prompts, MCP servers, and strict Agent Skills.
git clone https://github.com/mokhtarabadi/cognitive-lead-hq.git -
claude-skills-hub
Skills🧠 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.
git clone https://github.com/HackBepa/claude-skills-hub.git -
dual-brain
PromptsA 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.
git clone https://github.com/sleeplesshan/dual-brain.git -
Verisource — B2B GEO & AI Citation Intelligence
MCP serversB2B GEO MCP: audit AI citations, flag SKU hallucinations, and ship >=9.5/10 JSON-LD & /agents.md.
-
SpaceXAI: Grok 4.20
ModelsGrok 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...
x-ai/grok-4.20 -
AlphaAnalyst-open-source-autonomous-equity-research-agent
Agents & frameworksEnter 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
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.