Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
awaken
Agents & frameworksAI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
git clone https://github.com/awakenworks/awaken.git -
gargantua
MCP serversNative macOS system cleaner with YAML-driven safety rules, local AI explainability via MLX, and an MCP server for agent-controlled cleanup workflows.
git clone https://github.com/inceptyon-labs/gargantua.git -
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 -
agentglass
Agents & frameworks🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.
git clone https://github.com/SirAllap/agentglass.git -
AI skill that saves your Claude, ChatGPT or Gemini conversations as structured notes in your Obsidian vault: summary, decisions, action items, code, commits and Mermaid diagrams, filed by project. Works on desktop and mobile via local files, a linked computer, Make.com to OneDrive/Google Drive/Dropbox, or a Markdown download.
git clone https://github.com/Friendship7/save-conversation-to-obsidian.git -
api-skills
SkillsOne abstraction, 146 SaaS connectors. Agent skills for Apideck's Unified API — integrate Salesforce, QuickBooks, BambooHR, Jira, Shopify and 140+ more by changing one string.
git clone https://github.com/apideck-libraries/api-skills.git -
nemotron-3.5-120b-cq
Modelsimage text to text model by Cactus-Compute · mlx
Cactus-Compute/nemotron-3.5-120b-cq -
CoalTipple
SkillsSafe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated fable top rung. Not the cheapest router; the safest one inside Claude.
git clone https://github.com/TheColliery/CoalTipple.git -
reins
Agents & frameworksA lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.
git clone https://github.com/shamspias/reins.git -
dsh-video-storyboard
Agents & frameworksScene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.
git clone https://github.com/SAOS-3624/dsh-video-storyboard.git -
SpecForge
MCP serversSpecs your AI agent can't ignore. A deterministic compiler that turns your rules into checks: no AI inside, same input, same verdict. Rust · MCP-native · works with Claude Code, Cursor and any MCP agent.
git clone https://github.com/leaderiop/SpecForge.git -
UniFi Gateway
MCP serversSafe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.
ghcr.io/pete-builds/mcp-unifi:0.29.0 -
backlot
Agents & frameworksA local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, pagination, auth and per-document ACLs, over a corpus you supply.
git clone https://github.com/brekkylab/backlot.git -
agents-shipgate
MCP serversThe deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.
git clone https://github.com/ThreeMoonsLab/agents-shipgate.git -
lora-speedrun
Datasets & benchmarksSpeedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.
git clone https://github.com/Saivineeth147/lora-speedrun.git -
tokio-prompt-orchestrator
MCP serversLLM API proxy. Same prompt twice costs one call.
git clone https://github.com/Mattbusel/tokio-prompt-orchestrator.git -
stim
Agents & frameworksFast, isolated, local React Native and Expo environments for coding agents. Shared build caches, parallel worktrees, owned devices, and safe cleanup.
git clone https://github.com/appandflow/stim.git -
bug-hunter
Agents & frameworksAdversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
git clone https://github.com/codexstar69/bug-hunter.git -
skillstead
SkillsPractical, portable skills for agentic coding workflows — clearer diagrams, checked claims, safer GitHub releases, natural EN↔KO writing.
git clone https://github.com/kyungseo/skillstead.git -
collaborative-gym
Agents & frameworksFramework and toolkits for building and evaluating collaborative agents that can work together with humans.
git clone https://github.com/SALT-NLP/collaborative-gym.git -
token-optimizer-mcp
Tools & apps91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
hermes-agency-orchestrator
Agents & frameworksClaude Code Agent Workflows Guide 2026: Skills vs Teams vs Cost Analysis
git clone https://github.com/Sakshxm1/hermes-agency-orchestrator.git -
tweakcc-system-prompts
PromptsCustomized Claude Code system prompts for use with tweakcc — ~48k bytes smaller, 30% faster, same accuracy
git clone https://github.com/bl-ue/tweakcc-system-prompts.git -
chainloop
Agents & frameworksAgentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what your AI coding agents and CI/CD pipelines did, checked against policies as code, with the loop closed in CI/CD. AI sessions, SBOMs, VEX, SARIF and SLSA provenance, built on Sigstore and in-toto. Apache 2.0.
git clone https://github.com/chainloop-dev/chainloop.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.