Every repo we’ve run
722 so far. Search by name, what it does, or keyword.
jo-inc/camofox-browser
Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.
- browser
kaelorlabs/smitline
Make phone calls and join Zoom, Microsoft Teams and Google Meet meetings from any AI agent. Self-hosted MCP server, open source.
- MCP
- ai-agents
- google-meet
- meeting-bot
- microsoft-teams
- phone-calls
- self-hosted
- signalwire
- telephony
- twilio
- local-first
lalabase/lalabase
Self-hosted project management for devs and their clients: tickets, time tracking, docs and meetings, with an AI assistant that cites its sources. AGPL-3.0.
- MCP
- docs
- local-first
langchain-ai/social-media-agent
📲 An agent for sourcing, curating, and scheduling social media posts with human-in-the-loop.
leepokai/jev-guard
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
- skills
localthink-org/gbrain-localthink
Backup your AI agent's knowledge and conversations to your own git repo — GBrain export + agent session logs converted to LocalThink Format (LTF) markdown. No SaaS, no vendor lock.
- git
lucasrosati/claude-code-memory-setup
Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.
- memory
- Obsidian
mixelpixx/KiCAD-MCP-Server
KiCAD MCP is a Model Context Protocol (MCP) implementation that enables Large Language Models (LLMs) like Claude to directly interact with KiCAD for printed circuit board design.
- MCP
- design
mongodb-js/mongodb-mcp-server
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
- MCP
- mongodb
- mongodb-atlas
- mongodb-database
- database
moritzkremb/jev-voice-browser
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
- browser
nailulgh/antigravity-obsidian-memory
Shared Long-Term Memory & Synchronization Plugin for AI Agents using Obsidian as a persistent, token-efficient cognitive brain (Mem0 & CoALA Architecture).
- memory
- Obsidian
oscarlora/ad-production-kit
Everything you need to make Meta ads with Claude, Codex or any AI agent: skills and tools to go from idea to ready-to-launch ad. Built on what I learned making ads for ecommerce brands: 7+ years, 2,000 ads and $20M+ in ad spend.
- skills
rorkai/App-Store-Connect-CLI
Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more
- CLI
shannhk/llm-wikid
Karpathy-style LLM knowledge base for Obsidian. Clone, run Claude Code, start building your second brain.
- MCP
- Obsidian
- notes
solisolsoli/context-layer
Give your AI agents the context in your notes. Local Markdown and Obsidian retrieval, source-linked memory, MCP, and optional GitHub sources.
- MCP
- ai-agents
- claude-code
- markdown
- obsidian
- python
- retrieval
- second-brain
- codex
- github-context
- local-first
- obsidian-plugin
- memory
- GitHub
- notes
swastiksingh-dev/Aura-Components-MCP
Free MCP server for the Aura (aura.build) public catalogue: 2,495 components, 192 skills, 30,688 assets, 725 design systems. 35 tools, zero dependencies, no login.
- MCP
- design
- skills
talirezun/the-curator
Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you own — readable in Obsidian, synced through your own private GitHub repo. Share it with a cohort. Coding agents resume from it across sessions, models and machines.
- MCP
- agent-memory
- ai-agents
- claude
- gemini
- knowledge-graph
- knowledge-management
- llm
- local-first
- markdown
- nodejs
- Obsidian
- GitHub
tamaratran/fast-jev-compaction
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.