Havuz

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover,

Screenshot clipboard paste fix for Claude Code, Codex & Cursor — works on macOS, SSH remote, WSL2. Tiny background daemon (9 MB RAM, 0% CPU)

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Drive the OpenAI Codex Micro macro pad from Claude Code. Six Agent Keys show which of your projects needs you, and pressing one jumps to its

A compact heads-up display for your coding agent. Instruments while it works, the answer when it stops. Claude Code, Codex, OpenCode.

Keep growing TypeScript codebases maintainable. Trellis measures complexity, duplication, and import cycles, pinpoints structural debt, and

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of read

Retired. Excalibur (xcb) routed coding tasks across Codex and Claude Code subscriptions. Source and releases are preserved for reference.

Self-hosted remote terminal for iPhone, iPad & browser — attach tmux and run Claude Code, Codex, or any CLI agent from anywhere. Free for on

Terminal-native frontend for DeepSeek Harness with real scrollback; a direct, in-process consumer of Harness capabilities.

Unofficial CLI for automating Apple Feedback Assistant workflows: prepare, submit, attach, and verify

Compare OpenAPI specs and find potential affected JS, TS, and Python callers. Offline, zero runtime dependencies, with a one-command demo.

Drop-in replacement for git worktree add that shares disk blocks instead of copying your tree. On the Linux kernel, 1816 MB becomes 36 MB.

Community troubleshooting knowledge layer for OpenAI Codex

get -- get anything from your computer

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

A k9s-inspired CLI and TUI for managing Claude Code sessions — browse, search, inspect, and clean up your AI coding sessions

Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.

Minimalist & smart Go-based TUI assistant for plant care. Tracks watering schedules locally with SQLite, syncs with Open-Meteo API, and supp

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

Use Claude Code's UI with OpenAI GPT-5.6 (Sol/Terra/Luna) as the engine — powered by your ChatGPT Plus/Pro subscription via a local Codex pr

👁️ The visual layer for CLI coding agents. Pipe JSON → interactive native UI → modified JSON back. Like fzf, but for visual decisions.

AI coding runtime hygiene for Codex, Claude Code, Cursor, Windsurf, MCP servers, and safe workspace caches. Try: npx z-clean audit

A terminal file explorer with full Git and GitHub integration, AI chat, and reactive panels that stay in sync as you navigate.

Open-source BYOK AI coding agent with a desktop app, scriptable CLI, and built-in multi-agent orchestration. Written in Go.

Find what's using a port, who started it (Claude Code, Cursor, Docker…), whether your network can reach it, and stop it safely. An lsof alte

Advanced AI platform

⚡ Instant, zero-config local Wi-Fi file sharing from terminal to phone via terminal QR code and sleek web UI.

Local-first AI coding personality profiler, usage dashboard, and evidence-grounded roast.

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain

Local-first workspace token calculator and model recommender for coding agents, with repo maps, VS Code, CLI, and MCP.

What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.

TUI for managing .env files

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qw

The networked cross-session for coding agents — @mention another team's AI so yours and theirs integrate directly across sessions, machines,

A modular all-in-one CLI package manager for searching, installing, updating, and upgrading apps and developer tools across multiple package

把实现计划派发给另一个 AI 执行，你只负责审——纯 CLI 的协调者/executor 两角色协作工具（opencode / Claude Code / grok / codex，支持远程开发机）

Agent Knowledge Manager (akm). A CLI tool to manage AI agent knowledge, memories, skills, and more.

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

A tiny, declarative, agent-friendly library for your Git repositories.

GitDeclutter — safely analyze and clean stale local Git branches. Classifies branches as SAFE, REVIEW, KEEP or PROTECTED.

Local two-agent collaboration for Claude Code, Codex, and Grok Build. Keep your native sessions and tools; relay, review, and audit in a sha

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

Free subdomains under makes.fyi / agentdomains.co, claimed from the CLI. A/AAAA/CNAME/TXT/NS records, auto-HTTPS proxy and forwarding for th

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Open-source design-system drift scanner — audit tokens, components, a11y & docs; score adoption; hand fixes to your coding agent. Local-firs

Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key)

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6%