Havuz

CodeWiki is a knowledge platform that analyzes repositories into AST graphs, builds GraphRAG indexes, and generates source-grounded develope

原生 macOS 远程工作台：SSH · SFTP · 终端 · RDP · 端口转发 · 主机监控 | Native macOS remote workbench

The Git client that actually resolves conflicts: 8 deterministic patterns auto-resolve the ones that were never decisions, full trace on the

htop for your Claude Code sessions — real-time cost, cache efficiency, model comparison, and smart alerts

Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程

🔍 Reverse engineer any codebase into a build prompt — architecture breakdown, ASCII blueprint, and AI-ready reconstruction prompt

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

Build a Modern SaaS Landing Page 2026 | HTML & CSS Project

Lightweight Codex/Claude/Antigravity loop harness with strict evidence gates.

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

Project Management for the agent era

Claude Code AI Pipeline 2026 – PEV Framework Harness Plugin for Developers

Durable MCP control plane for long-running Codex Desktop tasks

Watch any GitHub user's commits stack up across their whole coding career as one rising chart — like star-history, but for commits. Compare

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Persistent memory for Claude Code — identity, context, and continuity across sessions

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), rever

Self-Hosted Mobile Device Streaming for QA Teams 2026

Best AI API Cost Tracker & Token Usage Monitor for Developers 2026

Best AI Coding Workflow Plugin Pipeline 2026

Parallel Flow Lab: Multi-Stage Dev Environments for Git Worktree Testing 2026

Ultimate React Native Workflow 2026 – One-Click Simulator & Metro Control

Git worktree manager for the terminal: CLI + TUI in Rust. Creates the worktree, runs your project setup, links the issue, and shows which AI

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re

Turn any CLI into a web GUI with one command

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce

macOS menu bar widget showing Claude Code & Codex usage limits as battery icons 🔋

One command to run the AI coding CLI you already pay for (Claude Code, Codex, Cursor, Gemini, Grok, aider) on a Tailscale-only Hetzner box —

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually ne

A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local agent management.

A native macOS GUI for Jujutsu (jj) — DAG graph, side-by-side diffs, interdiff, conflict resolution. Built with Rust + SwiftUI.

A native Rust CLI for orchestrating AI agents across projects, with persistent sessions, worktrees, and local-first control.

Local companion launcher and maintenance toolkit for the Codex desktop app.

Goal-based planning and proof gate for AI coding agents

Trusted localhost HTTPS — local CA, /etc/hosts, mDNS LAN sharing, reverse proxy. Maps https://name.local → localhost:port

Persistent memory for AI agents, for code, research and everyday life. Facts are typed, sourced, and retired when they change. Local SQLite,

An open-source build system that compiles your specs and architecture into working code.

A self-hosted LLM proxy and failover gateway supporting OpenAI & Gemini compatible endpoints. Routes requests dynamically across 12+ LLM pla

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

MCP server that orchestrates language servers into agent-native workflows. 65 tools, 30 CI-verified languages.

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

Open-source TypeScript framework for building operational software used by humans and AI agents.

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Give a service you are developing an HTTPS URL for webhooks, OAuth callbacks and previews, and join your own machines into a private, end-to

Open-source AI usage tracker — tokens, cost, and sessions across Claude Code, Codex, Hermes, Qoder, and more

Open-source universal AWS resource browser for MiniStack, Floci, LocalStack, Moto, and real AWS

A Claude Code skill that burns tokens on demand. Stress test, inflate metrics, or just set money on fire.

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio