Havuz

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, G

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang

A native macOS terminal for agent-driven development, built on Ghostty.

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

Agent that actually understands social platforms. Fast. Precise. Deep.

The open-source trading harness for Claude Code / Codex agents.

Research-backed, eval-driven skills for AI agents

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, c

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict.

JobAppAgent: open-source AI job application agent (Agent Skill + CLI). Searches wide, matches one verified résumé, applies within your rules

Cover your Mac's screen with a hotkey while AI agents keep running, even with the lid closed. The covered screen glows when Claude Code, Cod

Build with Clay in your AI coding agent - skills, MCP tools, and the clay CLI for Claude Code, Codex, and Cursor. Search companies and peopl

jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones

A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client. Ghost th

An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine

Marketing skills for AI agents — paid ads, social media, SEO, competitor research, creative generation, email, analytics, and more. Powered

让 AI 像人一样说话、创作的规则集。Ruleset for making AI talk and write like a human.

Bring Codex inside ChatGPT for unlimited vibecoding — no Codex quota used!

A personal AI on machines you own — any agent, loops that run overnight, boards, memory, and git control. Client/server split, always-on, op

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

Pane tracker: all your AI plans in one Windows tray. Claude, Codex, Cursor, Copilot, Kimi, Grok and 15 more. Free, open source. The OpenUsag

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores l

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

Run Claude Code, Codex or any coding agent on any of your computers, and jobs across all of them at once. Free, MIT, no relay, no limits.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and

Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.

小liu破甲 - Codex CLI jailbreak prompt and one-click deploy tool. 基于CTF框架的Codex破甲提示词与一键部署工具

Approve Claude Code from your Mac's notch. A native SwiftUI menu-bar app that surfaces Claude Code permission prompts, questions, cost and c

Context meters, quota tracking, and provider rate limits for agents running in Herdr.

A shared, git-backed wiki your team's AI agents maintain but can't break — Claude Code, Codex, OpenCode and any MCP client.

An agent skill for prose that sounds clear, specific, and human.

Prism: sandboxed, themed, interactive visualizations in Obsidian notes

Image generation CLI that reuses your Codex (ChatGPT) login.

Local dashboard for Claude Code, Codex, OpenCode, OpenClaw and Qoder session history, token usage, cost tracking, tool calls and subagent re

Local static analysis and baseline-governed CI checks for coding-agent instructions: AGENTS.md, CLAUDE.md, Cursor, Copilot, and Gemini.

Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

Meet your crew. APX is an open-source Agent OS for running AI agents on your own machine — memory in plain files, agents that work together,

Styx is where everything converges: every repo you work in, the AI coding agents building in them, and every login they need to ship. Switch

Agent skills that turn docs/ into an LLM-maintained wiki and task tracker. Obsidian-friendly. Works with Claude Code, Codex and Copilot CLI.

Local dashboard for Claude Code and Codex CLI: which Claude Code session needs input, every tool call and Claude Code subagent live, cost an

A video harness work platform for Agents such as Claude or Codex: the agent writes the code that renders the film, checks its own frames, st

借脑：把团队里 AI 用得最好的那个人的 AI，借给每个人。Let coding agents on different machines start, continue and read each other's sessions (Claude Code ↔ Codex),

Anti-AI Slop UI/UX steering skills — filter, palette, and research tool for Kiro, Claude Code, Cursor, Windsurf, Copilot, and more. Build in

A state machine protocol for running controlled ML experiments with coding agents.

A harness that lets AI agents make server-client games of commercial quality on a prebuilt core

Personal Agent Skills and DeepSeek Harness (DSH) plugins: message edit, Skill Scout, prompt recall, autosuggest and enhance, plus a DSH plug

Self-hosted, MCP-native invoicing. Clients, invoices, estimates, time, expenses and Stripe payments, with a built-in MCP server so Claude Co

一款集成codex claudecode opencode workbuddy 等智能体的agent工具，可免除繁琐的配置，帮助小白更方便的使用gpt,claude,grok，国模等大模型，支持中转站对接

Local-first short-form video studio: MCP server, local API and a desktop board for editing videos by chat

itr-wala, Hindistan gelir vergisi beyannamesini hazırlamak için AI agent’lara belge okuma ve yönlendirme becerisi, Python tabanlı deterministik vergi hesaplama motoru sağlar.

Neden yükseliyor · README, bir Instagram reel’inin bir haftada 1,2 milyon görüntülenme aldığını ve deponun en yoğun haftasını yaşadığını belirtiyor; 63 günde 871 yıldız bu görünürlükle uyumlu olabilir. Ancak bu ilginin gerçek kullanıcıların beyannameyi başarıyla tamamladığını veya hesaplamaları bağımsız biçimde doğruladığını gösterdiği söylenemez. Son 28 günde 3 commit ve 1 farklı yazar olması da aktivite kanıtının sınırlı olduğunu gösteriyor.