Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ntm
Agents & frameworksNamed Tmux Manager: a Go control plane to spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Antigravity, omp, Grok) across tmux panes - graph-aware work triage, safety policy and approvals, Agent Mail coordination, checkpoints/timelines, and robot JSON + REST/SSE/WebSocket/OpenAPI surfaces.
git clone https://github.com/Dicklesworthstone/ntm.git -
be-ambitious-harness
SkillsMake AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and an independent verifier that never sees the worker's reasoning. Plain markdown, EN + RU.
git clone https://github.com/alexpiar/be-ambitious-harness.git -
forgejudge
MCP serversOpen eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
forgejudge@0.1.0 -
retriEVAL
MCP serversLLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
ghcr.io/hcarrillo001/retrieval-mcp:1.0.0 -
ai-maxxing-skills
SkillsSkills Claude Code pour créer ton SaaS personnel (Cloudflare, Convex, Lumail, Stripe) : grill-me, audit-safety et plus. Ressource : codelynx.dev/fx
git clone https://github.com/Melvynx/ai-maxxing-skills.git -
Lycheetah-Framework
SkillsPublic method documents. How the work is thought and governed. Self-taught, in Dunedin. Not a commercial offer.
git clone https://github.com/Lycheetah/Lycheetah-Framework.git -
server
MCP serversObservability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor
@argosvix/mcp-server@1.1.2 -
PuzzleTide
MCP serversWord search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.
puzzletide-mcp@0.2.1 -
AgenticX
Agents & frameworksAgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
git clone https://github.com/DemonDamon/AgenticX.git -
ai-reliability-copilot
PromptsTurn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
git clone https://github.com/YanpengQi7/ai-reliability-copilot.git -
digline
MCP serversRead, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
digline-mcp@0.10.0 -
Lore Context
MCP serversGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
@lore-context/server@0.6.0-alpha.1 -
numguard
MCP serversVerify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
numguard@0.1.1 -
PublicSafetyBid
MCP serversScore public safety bids and vendor fit.
-
testlink-mcp
MCP serversAI-friendly, safety-first TestLink MCP server
testlink-mcp@1.0.8 -
HostDeFi
Public APIsFree A+–F token-safety grades across Solana and EVM chains
-
patton-protocol
SkillsAgent Skills package for bounded coding-agent missions, and a Claude Code hook that asks before existing files change. Pre-registered study: the hook cut cleanup harm from 0.196 to 0 over 224 runs; the skill text alone did not.
git clone https://github.com/vladimirrott/patton-protocol.git -
roblox-best-practices-skill
SkillsRoblox/Luau coding standard packaged as an Agent Skill for AI coding assistants. A 12-rule card routing to 43 references: code review, platform limits, data safety, monetization, launch policy, and Studio MCP and Open Cloud safety. Framework-agnostic, text-only, and installs to 60+ agents including Claude Code, Cursor, Codex, and Windsurf.
git clone https://github.com/andrian-syh/roblox-best-practices-skill.git -
email-marketing-bible
SkillsEmail marketing skill for AI agents, by George Hartley (founded SmartrMail). Plans, writes, audits and sends email with hard send-safety gates. Works in Claude, ChatGPT, Codex and Cursor. Free, MIT, vendor-neutral.
git clone https://github.com/CosmoBlk/email-marketing-bible.git -
ZeroWidth Caliper
MCP serversBuild datasets and rubrics, then run evals that score your AI in Caliper.
-
元铸工坊 SOSOFAST (yuanzhu)
MCP serversGoverned AI workflow assets: staged writes, evals-gated template forging, ontology via MCP.
yuanzhu@0.2.2 -
QueryPilot
MCP serversSafe SQL gateway for AI agents: SELECT-only validation, access policies, masking, audit trail, evals
querypilot@0.1.1 -
MoltJobs
MCP serversBrowse MoltJobs jobs, manage owned AI agents, review evals, and place authorized USDC bids.
-
Openlayer
MCP serversInspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals.
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.