Havuz

Open coding agent that matches the best at lower cost: any model, sandboxed, scriptable, embeddable. Engine of Murage.

Any agent as native Claude Code teammates. Codex, Gemini, Kimi today. GLM, DeepSeek next.

Repo-native project memory for AI-assisted development: workorders, playbooks, examples, checks, handoff rules, and release-readiness discip

Safety net for AI-assisted coding. Records a working baseline, detects regressions after AI edits, and preserves your uncommitted work.

Local Codex control with bounded runs, crash recovery, and auditable results. Optional ChatGPT bridge.

Starter kit for agentic WordPress development. CLAUDE.md/AGENTS.md templates, the wordpress-development skill, curated MCP servers, sub-agen

Claude Code skills to help you think like a Senior Engineer.

AI-native methodology for Go backend microservices: rebuild the whole codebase from docs/ + .claude/skills, driven by a 12-lens high-perform

Self-hosted mission control for real Claude Code and Codex sessions — persistent terminals, automations, and browser/mobile control.

Redpen makes coding agents prove they are actually done.

Start with a concept, not a stack. A harness-agnostic protocol that scaffolds greenfield projects from a rigorous concept instead of a chain

macOS workbench for running many Claude Code sessions side by side: session cards, fork DAG, kanban, tiered notifications, Git worktrees, Cl

🧠 Native macOS menu-bar dashboard for AI coding: Claude / Codex / Gemini / Grok / Kimi quotas and official Coding Plan usage (Volcengine, Al

Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.

Agentic terminal forked from the holy Alacritty.

Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillat

One workflow methodology across 10 AI coding tools (Cursor, Claude Code, Opencode, Aider, Windsurf, Cline, ...) in a single ~1,350 token spe

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, re

Open-source AI orchestration service. One API, multiple AI providers.

Terminal-first workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status per project, code viewer + Git, sy

A live, graph-verified map of your codebase for AI coding agents — real call graphs, compiler-verified edges, and hard safety gates on the w

backlog: Your AI agent forgets between sessions. Backlog remembers.

Claude Code skill: turn your last AI coding session into a credibility-checked, quiz-placed reading path

Save your tokens!

Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max wit

Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.

World's first compiler and execution platform for AI systems — turn prompts, skills, and multi-step agent workflows into versioned, packagea

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

Local-first dashboard for tracking Codex, Claude Code, and GitHub Copilot token usage/spend by repo, session, model, and tool.

Code from your phone — self-hosted mobile web UI for terminal coding agents (OpenCode chat + real terminal)

Codex-style /goal loops for Cursor Agent chat with local .goal state — no Agent SDK.

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI

An agents skill for auditing Ruby on Rails applications, identifying security issues, code quality problems, and common misconfigurations.

Drop this CLAUDE.md into your project. Watch Claude Code mass level up. One file. Zero config.

Distribute and safely manage a cross-host personal harness and durable work state.

Pre-launch security checklist for AI-generated apps (Lovable, v0, Bolt, Cursor). 69 checks covering Supabase RLS, exposed keys, and prompt i

Load-bearing comments only. Stops Claude Code narrating your code back to you in comments.

Your AI coding recovery score, from the terminal. Parses Claude Code JSONL sessions → cost, tokens, DRS estimate, per-project breakdown. Zer

Six steps to make a new Phoenix app work well with AI coding agents: pin the toolchain, turn mix precommit into a real gate, split the gener

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat

Disciplined software development — build real, well-architected software with an AI coding agent. From idea to blueprint to built.

Agent skills for pragmatic programmers.

Bridges Superpowers + OpenSpec workflows into OpenCode with enforced worktree isolation.

A local verification receipt for AI coding agents

Local Figma handoff packages for developers and AI coding agents.

Browse, search, and resume your local AI coding CLI sessions — Claude Code, Codex, Grok, opencode, Cursor, Gemini, Copilot, Goose, Droid — i

一个能让 Codex 连续开发 60 小时的 Skill：Claude 先规划，Codex 按垂直切片持续实现，Trellis 记录进度，Long-Run Execution 支持恢复。

Agent Skill + Playwright/axe-core verification loop that teaches AI coding agents to build accessible frontends on the first pass. Companion

Codebuddy IDE CN（国内版）的非官方 Linux 自动化打包与安装构建脚本工具