OwlMem command line: connect your AI apps to OwlMem in one command (npx -y owlmem install), an end-to-end encrypted vault for your AI agents, and a local MCP server.
Content-addressed identity, honest by construction — mint + mind, holographic merkle proofs, a reversible imprint codec, a reeducating harness, a measured billing model, pure-TypeScript ChaCha20-Poly1
venira-mcp — a standalone Model Context Protocol (MCP) server that gives coding agents (OpenCode, Claude Desktop, any MCP client) workspace-scoped tools in default/expert modes: file read/write/edit/d
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-c.
Fire Code: every codebase in one Windows window, each with its own Light Code agent working in parallel
Making Apple docs AI-readable
Claude Code style UI for pi: one-line tool groups, syntax-highlighted diffs, an activity spinner, and colors from your terminal theme
Devicons - Icon font, SVG sprite, and CLI for developer icons
Make your Agent Skills reactive. A permanent, secure webhook endpoint on your own machine that runs SKILL.md files with Claude Code or Codex the moment something happens, plus version-controlled sched
MCP Server for DOM element pointing - WebSocket bridge for element targeting
MCP server that gives AI agents correct Tailwind CSS palettes (50–950) from any color, for Tailwind v4, v3, v2 and v1
The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~26 ms local semantic search, ~2 KB pay
Web scraping, code review, content gen, sentiment. Zero Core Tools.
Context and token optimizer for LLM agents: see where Claude Code, Cursor, Codex and Gemini CLI tokens go, then cut them: an every-prompt hook, smarter compaction, an autopilot proxy that edits histor
Capture OAuth 2.0 authorization codes on a loopback redirect URI in Node.js, Deno and Bun, with a browser authorization provider for the MCP SDK
A team knowledge base for coding agents that keeps itself current: it learns from code review, developers and the code. Runs on your repos, CI and tokens; no service. For Claude Code, MCP, Cursor, Cop
MCP server for using Alchemy APIs
FrontMCP's skills catalog: SKILL.md instructions that teach coding agents to build, test and deploy FrontMCP servers
MCP tool adapter for Beignet agent capabilities
npm create @christianirack/brainllm <app>: a new BRAINLLM app (the Rust-powered full-stack web compiler for LLMs and AI agents) with its brain version pinned.
Personal AI assistant powered by Pi, Antigravity, Claude, Codex, Codex App, Cursor, Grok, Kiro, OpenCode, and Copilot — Web, Terminal, Slack, Telegram, and Discord interfaces with 33 skills active by
Azure DevOps MCP server: projects, repos, work items, pull requests, pipelines, and wikis.
Pre-classified capability registry for popular MCP servers (Slack, GitHub, Linear, Notion, Filesystem, Postgres, Email/SMTP/Gmail). Drop-in starter for @strixgov/tool-gateway.
Tool-agnostic AI development framework. Standardize projects across Claude Code, Cursor, Gemini, Codex, Windsurf, Copilot with automated templates, quality gates, persistent memory, and framework dete
MCP server for OpenAlex API - enabling literature review and research landscaping
CodexGuild MCP server (stdio) — boosts your coding agent: remote CodexGuild tools plus local stack detection from lockfiles, deprecated APIs found in your own code, and offline security audits of skil
Code review that happens while your agent writes: deterministic checks on the lines it changed, quiet unless it can prove a defect, and learning from your team's fixes and dismissals. Works with Claud
Model Context Protocol implementation for TypeScript - Client package
Coding-agent CLI with a code knowledge graph, memory and reviewable skills / CLI de agente de código com grafo de conhecimento, memória e skills revisáveis
MCP server for debuff: lets AI agents inspect, build, test and play a debuff game
AI agents runtime and meta-harness: routes each query to a cost-optimal model (LLM routing), evolves its own harness and orchestrates coding agents over MCP.
PostHog SDK for Model Context Protocol (MCP) servers — tracks tool usage, intent, and identity
Full-featured, lightweight MCP extension for the Pi coding agent: stdio, SSE & Streamable HTTP transports, OAuth 2.1 (PKCE + DCR), lazy/eager lifecycles — minimal dependencies, zero bloat.
Pre-launch security check for AI-built apps: leaked keys, open Supabase rules, unprotected routes, unsafe LLM code. Runs locally.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Turn Microsoft Fabric tables into an explainable graph and a GraphQL API.
Annuaire complet
IDE, git, linting et analyse de code. 8,812 serveurs, les plus utilisés en premier. Chacun ouvre la page de l'éditeur.