Havuz

The open-source autonomous delivery agent for Claude Code.

👻 Ghostfox — the browser that can SEE: Gecko-native agent browser. 71 MCP tools, unhookable a11y/compositor vision, captcha solvers, page_do

Snap a line before your agents build.

Scores 10,100+ open-source AI repos on Impact / Velocity / Health - refreshed 6x daily.

Infinite scroll terminal multiplexer and agent orchestrator for macOS

Hermes plugin: one /crew message becomes verified work on the kanban board. A coordinator owns every card until its proof passes.

Claude Code hook that blocks unquoted rm -rf $VAR and repo-root deletes, even in bypassPermissions mode

One voice agent to control all your Claude Code sessions — drive them hands-free from your browser or phone.

A code-only world engine for AI agents: build whole towns and landscapes in three.js as code (pre-alpha)

Local, provider-agnostic agentic hub: an orchestrator and a squad of little monsters on your machine

MCP-сервер для КОМПАС-3D v24: ИИ-агент строит детали и сборки, а сервер проверяет каждый шаг измерением модели.

Stack traces that tell the tale — a Logback appender that turns Java errors into AI-ready reports

TinyFish MCP server — web search, page fetching & extraction, browser automation and page monitoring for Claude, Cursor, VS Code and any MCP

The guidelines for building UI components with a perfect user experience, developer experience and agentic experience.

One prompt → a swarm of 150+ specialist Cursor agents that plan, build, test & harden your whole project in parallel, sharing an Obsidian br

Error gates for AI coding agents: detects recurring tool-call failures and promotes them into enforced gates - remind first, hard-block on s

A local workspace for Prime Agent with persistent sessions, subagents, MCP tools and file previews. Control it from your phone via Tailscale

Your team's coding agents warn each other before they edit the same file. Claude Code, Codex, Cursor and 17 more.

Codex plugin for orchestrating local coding-agent CLIs with task contracts, questions, observability, and review gates

TypeScript SDK for durable agents, workflows, and custom execution kinds. Built by Swirls.

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Local-first work memory for Claude Code, Codex and Copilot. Plain Markdown files hold your projects, people, decisions and meetings, with a

Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, A

Orchestrate coding agents on Linux, macOS and Windows. Parallel worktrees; hand work between agents without re-explaining.

Approve your AI coding agents' permission prompts from the menu bar or a Dynamic Island under the notch, and see what each one is doing righ

The open-source Claude skill for UI/UX design. 84 UI styles, 192 color palettes, 74 font pairings, 99 UX guidelines & 161 industry rules acr

Real-time alert bot for Robinhood Chain - Telegram, Discord, and X (Twitter). Tracks new launches, graduations, whale trades, Stock Token pr

Self-hosted, cross-platform control plane for persistent AI employees with local channels, replaceable Worker Hosts, human approval, memory,

The most comprehensive agent skills for writing real, idiomatic Rust and porting code from other languages.

A second brain for Claude Code and Codex that keeps receipts, following Karpathy's LLM Wiki pattern: the agent keeps your markdown vault. Sk

Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes, a search layer for a Karpathy-styl

给 AI Agent 的前端设计管线：先写 DESIGN.md 与 MOTION.md，经 job 分发、OpenSpec 与证据门禁再写代码。

A two-floor 3D virtual office in the browser: playable CEO, AI agent team, Telegram chat, CAD/Blender/ICT drawings from one dataset. Docs in

Roblox/Luau coding standard packaged as an Agent Skill for AI coding assistants. A 12-rule card routing to 43 references: code review, platf

Evidence-bounded skill for drafting, rewriting, humanizing, and auditing IEEE/ACM engineering manuscripts.

Manage your Herdr agents by voice — hands-free, from anywhere. A voice-first agent harness for Claude Code, Codex and other coding agents, w

Personal Solana memecoin intelligence dashboard: an open-source, self-hosted whale tracker and copy-trading deck you run by talking to your

Machine-enforced frontend UI/UX skill pack for AI agents. Registry + lazy loading: a 2,154-token router loads one skill per request out of 4

Pony is the hands, you pick the brain. Let Claude, Grok, Gemini or any MCP agent use your Android phone.

Keep the agent honest: a plain-English linter for Markdown prose and code comments.

npm-compatible registry that crowdfunds supply chain security: donors pay auditors and maintainers in USDC on Algorand via x402

An open research workbench for idea discovery, autonomous mathematics, and evidence-grounded rebuttals.

A Claude Code skill that shows you where your folder structure sends an agent before you trust it with the task.

The multi-agent coding terminal. Run Claude Code, Codex and other agents in parallel on Linux and macOS. They send each other tasks and repo

Build your own personal assistant that never forgets. Self-hosted, open source, harness-agnostic.

Describe a team of AI agents and they work on your repo around the clock. BYOK desktop app for macOS, Windows and Linux.

Playwright, but built for AI agents: the browser API models already know, token-efficient a11y snapshots, and scroll-driven collection over

Open-source, Local-first AI (SI) Second Brain.

Hermes, on the fly. A light, everyday mobile app (PWA) for your Hermes Agent bots.

Dreamwork MCP server: job search, tailored application materials, and application tracking for AI assistants.