Havuz

MCP server that lets your AI assistant read and write Figma in real time — no API token, no rate limits. Works with Claude, Cursor, Copilot,

Stream Deck plugin showing Claude session/weekly usage

A local-first, LLM-agnostic memory layer for AI assistants

(개요) 국가법령정보센터와 알리오의 공공기관 내부규정을 검색·비교·분석하는 MCP. (도구) 법제처 87 + ALIO 공공기관 규정 23 = 110개 MCP 도구. (데이터) 1,600 법률, 10,000 행정규칙, 수만건 판례, 344개 공공기관 3

AI Video Engine — Turn structured data into videos. JSON timeline → Scene components → HTML/MP4.

Parallel AI coding, without repo chaos. Desktop workbench for Claude Code and Codex with per-session git worktrees, terminal, editor, SCM, a

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates),

Release Doctor: check Expo, React Native and Unity release risks before connecting app stores. CLI + MCP for Claude Code and Codex.

Deobfuscated source code of @anthropic-ai/claude-code v2.1.76 | 1,902 TypeScript files reverse-engineered from the official npm package

LazyChat — an AI assistant docked inside your ERPNext desk. Chat with your data, draft reports, stage edits (Apply-gated). Bring your own LL

Karpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you de

Atomic scripts for launching, collecting fees from, and trading pump.fun coins. Built around Jito bundles for atomicity across multiple txs,

Personal knowledge graph MCP server on Cloudflare D1 + Vectorize. Deploy your own sovereign second brain in one click — Claude captures atom

Mission control for your Claude Code sessions — a 100% local dashboard to see, resume, and drive every session on your Mac.

AI agent toolkit for coding agents, unified LLM APIs, agentic workflows, tool harness and more.

An autonomous liquidity agent that watches Meteora DLMM pools, reasons over live on-chain data, and rebalances positions before they bleed.

The SaaS starter where Claude writes the rest. AI-first, full-stack: Next.js 16, Better Auth, Drizzle/Postgres, tRPC, Polar billing, R2, Dok

Turn Hermes into a local-first wellness agent with guided setup, onboarding, wellness skills and MCP connector presets.

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and r

Networked Claude-to-Claude messaging over HTTP + MCP channels — DM, broadcast, thread, and permission-relay between Claude Code instances vi

MCP server for production-grade UI and brand design — 37 tools: anti-slop quality gates, OKLCH tokens with auto dark mode, WCAG 2.1 audits,

TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.

CT sentiment - scans Crypto Twitter, scores narratives, surfaces trading signals.

AI-agent workspace for quantitative trading — backtest, validate, and paper trade strategies with multi-agent collaboration

Autonomous Solana trading agent with in-enclave key custody and attested execution.

A local, open-source capability gateway for AI agents — one AI-native self-describe endpoint so any agent can discover, understand, be grant

Universal MCP server manager — install and configure MCP servers across Claude Code, Cursor, VS Code, and more

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-d

MCP for styles.refero.design — natural-language search across the curated DESIGN.md library.

Upload files over 20 MB (up to 5 GB) to Notion with the API, from Node.js or AI agents. Automatic multi-part uploads streamed from disk, wit

AI-generated, print-ready exam sheets for Indonesian elementary teachers — Built with Claude Opus 4.7. React 19 + Hono + Effect-TS.

Persistent RAG memory layer for AI agents - store observations, retrieve context by semantic similarity, self-prune on TTL

MCP server for Yandex Metrica — query your web analytics in plain language from Claude, Cursor, and other AI agents. Secretless one-command

The open-source autonomous delivery agent for Claude Code.

A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambigui

DeFi protocol research agent for Solana. Scores protocols on security, traction, tokenomics, team, and moat using Claude.

Cross-chain bridge monitor for Solana. Tracks asset flows between Solana and EVM chains and detects anomalies using Claude.

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

Yield optimizer — rebalances across Kamino, MarginFi, Solend for max APY

Airdrop optimizer - tracks live campaigns, estimates ROI, allocates capital.

Describe a Solana program in plain English - Sigil's AI agent writes the Anchor code.

Multi-agent MCP orchestrator for Solana DeFi - routes tasks to specialized Claude agents, synthesizes results, acts autonomously.

Run Claude Code inside Obsidian with an interactive terminal, quick-ask modal, and a built-in MCP server for structured vault access.

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it