Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to connect AI to my tools
-
xgrep
MCP serversUltra-fast indexed code search engine — faster than ripgrep on repeated searches, lighter than zoekt. Built-in MCP server for AI agents. Also does fast file finding (fd/find alternative).
git clone https://github.com/momokun7/xgrep.git -
pinboard
SkillsKeep coding-agent work coherent across tasks, interruptions, and review.
git clone https://github.com/valsteen/pinboard.git -
CONCISE
SkillsCONCISE - Cuts prose filler
git clone https://github.com/0xyph3r/CONCISE.git -
skills-tracker
SkillsReal-time tracking of every new GitHub 'skills' repo to capture the AI agent skill ecosystem trend
git clone https://github.com/linny006/skills-tracker.git -
nestjs-skills
SkillsSeven Agent Skills for NestJS implementation, architecture, OOP, code and feature audits, runtime performance, and safe Git publication.
git clone https://github.com/amirtaherkhani/nestjs-skills.git -
codex-long-jobs
SkillsBackground jobs for OpenAI Codex CLI and VS Code: run long tasks without model polling and wake the original session on completion.
git clone https://github.com/zycdev/codex-long-jobs.git -
lazyagents
SkillsThe lazygit for AI coding agents: skills, sessions, usage, providers and hooks for Claude Code, Codex, Gemini CLI, OpenCode, Pi, Crush and Hermes Agent.
git clone https://github.com/rogeriojunior31/lazyagents.git -
session-story
SkillsGenerate a self-contained HTML "session story" that links each prompt in a vibe coding session to the file edits it caused, with a review timeline, a GitHub-style diff view, and a plain-language narrative.
git clone https://github.com/nalaj/session-story.git -
stacklit
MCP serversStop making your AI re-read your codebase. Stacklit maps your repo once and keeps the map fresh. In a 450-session test, agents ran 82% fewer grep and glob searches. Free, MIT, one Go binary. Sets up Claude Code, Cursor, Codex and 22 more.
git clone https://github.com/glincker/stacklit.git -
typst-dev-container
SkillsTypst + Pandoc dev container: reproducible PDF document builds in Docker, VS Code Dev Containers, and GitHub Codespaces.
git clone https://github.com/1solomonwakhungu/typst-dev-container.git -
sage
AI repositoriesChat with any codebase in under two minutes | Fully local or via third-party APIs
git clone https://github.com/Storia-AI/sage.git -
.claude
PromptsThe Ultimate Claude Code Toolkit: 183 skills, 10 agents, 29 commands, 7 hooks, and 86 marketplace repos (11,300+ community skills). Drop-in ~/.claude config with a generated index and router that loads the right resources on demand, or install just the skills as a plugin.
git clone https://github.com/travisjneuman/.claude.git -
coding.sh
MCP serversOpen-source, local-first observability and evals for AI agents: see what Claude Code, Codex, Cursor and others did and what it cost.
git clone https://github.com/jackulau/coding.sh.git -
toh-framework
Tools & appsType one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is verified done. Works in Claude Code, Cursor, Antigravity, Codex and ZCode.
git clone https://github.com/wasintoh/toh-framework.git -
flisk
MCP serversThe local runtime your AI coding agent can start, check and fix. One command runs your multi-service app from a Compose file or plain commands, and an MCP server gives Claude Code, Cursor and Codex its health, logs and controls. MIT, no account.
git clone https://github.com/flisk-sh/flisk.git -
nautilus
SkillsRepository-based product discovery for Cursor, Codex, and OpenCode. Turn product questions into testable hypotheses, prototypes, and evidence-backed PRDs.
git clone https://github.com/shinpr/nautilus.git -
brix
SkillsPick a stack and copy one command. Brix installs the skills. Add your own prompt, and your agent uses those skills to build the repo.
git clone https://github.com/robosushie/brix.git -
joxo
Agents & frameworksTeam workspace for AI coding agents: your Claude Code, Codex, Cursor, Gemini CLI and OpenCode agents share one project, task board and handoffs. Desktop, iPhone and MCP server.
git clone https://github.com/JoxoAI/joxo.git -
dsh-mcp-panel
MCP serversMCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settings MCP tab with server CRUD (approval-gated writes, automatic backups) and a tool trial console over the official tool pipeline (Apache-2.0, dsh-plugin).
git clone https://github.com/PerryLink/dsh-mcp-panel.git -
Benzi
Tools & appsBenzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it. Every language runs its own tree-sitter grammar into the same query map.
git clone https://github.com/oooscoos/Benzi.git -
pi-skill-shiori
SkillsPi extension that reduces Agent Skill catalog tokens with policy-based skill retrieval and on-demand skill loading.
git clone https://github.com/eiei114/pi-skill-shiori.git -
OPM
SkillsClaude Code plugin: brainstorm → plan → TDD with subagents → verified done. Fewer tokens, no fake 'tests pass'.
git clone https://github.com/harshadmadaye/OPM.git -
kanso
SkillsSix Claude Code skills that keep AI-generated code tight. Audit, refactor, commit, PR, curate context.
git clone https://github.com/blakecyze/kanso.git -
ai-primitives-hub
PromptsVS Code extension and CLI for managing, sharing, and installing AI primitives (Agents, Skills, Prompts, Instructions, MCP) collections for GitHub Copilot and other AI assistants
git clone https://github.com/AmadeusITGroup/ai-primitives-hub.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.