Library
86,689 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
pic-standard
MCP serversOpen standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
git clone https://github.com/pic-standard/pic-standard.git -
OpenAgentCore
Agents & frameworksThe OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.
git clone https://github.com/MiniMax-AI/OpenAgentCore.git -
margince
MCP serversA CRM your AI agents can actually work in. Source-available: it's yours, you get the source.
git clone https://github.com/margince/margince.git -
wilmai
MCP serversWilma, Finland's school system, with AI: an MCP server, CLI and agent skills for Claude, ChatGPT, Codex, OpenClaw, Grok Bot and Meta Muse, and WilmAI Home, a desktop app for students and parents (Mac, Windows). Runs on your computer.
git clone https://github.com/aikarjal/wilmai.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Squad Leader.
git clone https://github.com/alphaparkinc/openclaw-genpark-squad-leader.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Receipt Ledger.
git clone https://github.com/alphaparkinc/openclaw-genpark-receipt-ledger.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Market Sniper.
git clone https://github.com/alphaparkinc/openclaw-genpark-market-sniper.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Legal Shield.
git clone https://github.com/alphaparkinc/openclaw-genpark-legal-shield.git -
openclaw-genpark-lead-nexus
SkillsDeterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Lead Nexus.
git clone https://github.com/alphaparkinc/openclaw-genpark-lead-nexus.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Lead Harvester.
git clone https://github.com/alphaparkinc/openclaw-genpark-lead-harvester.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Inbox Liquidator.
git clone https://github.com/alphaparkinc/openclaw-genpark-inbox-liquidator.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Compute Broker.
git clone https://github.com/alphaparkinc/openclaw-genpark-compute-broker.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Compliance Shield.
git clone https://github.com/alphaparkinc/openclaw-genpark-compliance-shield.git -
dsh-mcp-manager
MCP serversMCP server manager plugin for DeepSeek Harness: Settings → MCP page, OAuth (PKCE + dynamic client registration) or static-token auth, tools registered as mcp__<name>__*
git clone https://github.com/hyqhyq3/dsh-mcp-manager.git -
Terminal-RSI-27B
Modelstext generation model by Teriminal-RSI · transformers
Teriminal-RSI/Terminal-RSI-27B -
mache
MCP serversIDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
git clone https://github.com/agentic-research/mache.git -
task-orchestrator
MCP serversServer-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
git clone https://github.com/jpicklyk/task-orchestrator.git -
text generation model by nota-ai · mlx
nota-ai/Nemotron-3.5-Lightning-30B-A3B-Nota-Ternary-MLX-1014 -
derive
MCP serversReview and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.
git clone https://github.com/derive-to/derive.git -
authkestra
MCP serversThe Compile-Time Safe Identity & AI Agent Authorization Engine for Rust
git clone https://github.com/Authkestra/authkestra.git -
dcc-mcp-zbrush
SkillsPre-alpha ZBrush MCP adapter for AI agents to inspect high-poly meshes and subtools, manage brushes, and export OBJ assets through the DCC-MCP gateway using the official Python SDK.
git clone https://github.com/dcc-mcp/dcc-mcp-zbrush.git -
tintins-chess-analysis
MCP serversStockfish + LLM chess coach: an MCP server and web board that explain your mistakes in plain English
git clone https://github.com/Chess-analysis-mcp/tintins-chess-analysis.git -
Synabun
Tools & appsOpen-source persistent memory MCP server and self-hosted AI workspace for Claude Code, Codex and OpenCode. SynaBun Assistant coordinates their agents.
git clone https://github.com/danilokhury/Synabun.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.