Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
inspeximus@3.27.0 -
OpenLeads
MCP serversFind leads with honest email evidence, then work them: CRM, sequences, tasks, deals. No API keys.
openleads@5.5.0 -
SkillForge
SkillsA skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.
git clone https://github.com/tripleyak/SkillForge.git -
{ "role": "Calm, careful parking ticket appeal assistant who helps drivers understand a parking ticket or penalty notice, check it for errors, collect and organize evidence, decide whether to pay or challenge it, and…
-
code-review-gate-skill
SkillsAuditable code review skill for Claude Code and Codex: four independent probes, evidence-backed findings, and a JSON-derived merge gate.
git clone https://github.com/kyy-logs/code-review-gate-skill.git -
Prysai-LLM-Playbook
PromptsAn evidence-led, eight-locale LLM playbook: a transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.
git clone https://github.com/Prysai/Prysai-LLM-Playbook.git -
Aletheore
MCP serversOpen source (AGPL-3.0) evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs.
git clone https://github.com/Aletheore/Aletheore.git -
ProofFetch — Cited Web Evidence
MCP serversWeb pages your agent can quote: 1,000 full fetches a month free, no card, then $0.01 a page.
-
frame-trace-mcp
MCP serversBest AI QA Evidence Recorder MCP Server for Automated Testing 2026
git clone https://github.com/yashsindya2014-hash/frame-trace-mcp.git -
English school edtech contract renewals and buyer briefs; DfE AI-safety toolkit. USDC on Base.
-
GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish.
-
ContribAI
Tools & appsMaintainer-governed agent for evidence-backed open-source contribution proposals
git clone https://github.com/tang-vu/ContribAI.git -
wirken
MCP serversThe enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
git clone https://github.com/gebruder/wirken.git -
thinking-framework-skills
SkillsEvidence-graded, agent-executable thinking-method skills - 63 frameworks reduced to their working mechanism, honestly graded, and producing a concrete artifact. 63 frameworks + 4 tools + 9 recipes for Claude Code, Codex, and other AI agents. Advanced (Gold) tier.
git clone https://github.com/product-on-purpose/thinking-framework-skills.git -
lean-ctx
Tools & appsLeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: CLI, MCP, hooks and supported proxy paths.
git clone https://github.com/yvgude/lean-ctx.git -
电商视觉文案设计SOP Skill - 让电商设计小白也能一键做出5年资深设计经验的商品图片.兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent. AI-powered e-commerce visual strategy skill for main images, PDP/A+, copywriting, localization, evidence-aware compliance and image prompts.
git clone https://github.com/feichanggege/ecommerce-visual-copywriting-skill.git -
LastSearch
MCP serversEvidence-backed web research for AI agents with citations and confidence scores.
lastsearch@1.4.3 -
PandaWard
MCP serversLocal, evidence-based application security assessment with an evidence ledger and retests.
https://github.com/ratomirjovanovic/pandaward/releases/download/v0.2.15/pandaward-mcp.mcpb@0.2.15 -
Agentic-SEO-Skill
SkillsAn LLM-first SEO analysis skill for Antigravity, Codex, Claude with 16 specialized sub-skills, 10 specialist agents, and 88 optional utility scripts used as evidence collectors.
git clone https://github.com/Bhanunamikaze/Agentic-SEO-Skill.git -
spec-harness
Agents & frameworks面向 AI 编程智能体的任务包工作流工具,用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)
git clone https://github.com/MicTx/spec-harness.git -
osint-forge-skills
Skills⚒️ Open-source OSINT and digital forensics skills for AI assistants. Investigate sources, challenge hypotheses, analyze artifacts, and produce evidence-referenced reports with portable case files and offline Python tools. Designed for Claude Code, Codex, OpenCode, and Gemini CLI.
git clone https://github.com/OSINT-Forge-Community/osint-forge-skills.git -
BambooAI
Agents & frameworksAI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.
git clone https://github.com/pgalko/BambooAI.git -
LoopGrid MCP
MCP serversMCP bridge for tamper-evident evidence around consequential AI and agent decisions.
loopgrid-mcp@0.1.0 -
NiFiMCP
MCP serversEvidence-backed, read-only Apache NiFi investigation: cited evidence and reviewable flow drafts
nifimcp-server@0.1.0rc1
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.