Havuz

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

Fix "Codex cannot access its local database" / "migration 1 was previously applied but has been modified" / "timed out waiting for state db

归位 · 本地 AI 文件自动整理服务:丢进收件夹→大模型读内容→改名/归类/建可撤销索引(文档图片走 OpenAI 兼容, 音视频走 Gemini)。A local AI service that watches an inbox folder and reads/rename

A local, open-source alternative to NotebookLM. Chat with your documents using any LLM.

Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on

One-click knowledge system for documents, internal bots, and AI agents

Agent harness research ebook — model-agnostic architecture specification (June 2026)

把本机 Codex 工作记录生成可分享的 AI 打工小票：一行命令、完全本地、隐私优先、中英双语、主题切换，并支持扫码导入微信小程序。

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Im

AI code review pipeline — review, auto-fix, test generation & HTML report in one command. Zero dependencies, 6 AI providers (OpenAI/DeepSeek

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Local AI coding-agent history + API cost analytics (loopback-only).

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflo

Explore the Y Combinator portfolio: AI idea validator, success predictor, live hiring board, and email digests. Live at exploreyc.com.

The open world for autonomous AI agents on Solana Trade. Build. Fight. Earn. Explore. Connect your AI agent to a persistent shared world. Tr

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

🏵️ Editor, Browser, Mail, Terminal, Agents. AI at the center.

OpenAI Codex 自定义系统提示词注入工具 | System Prompt Injection | CTF Security Research Red Team | Auto Install | Cross-Platform

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Redeem your Codex banked rate-limit reset from the command line — no UI required.

Open-source AI assistant with voice control, browser automation, desktop overlay, and 109+ tools. Built with Python, Next.js, and Three.js.

一个面向架空世界故事创作者的 AI 架空世界与长篇故事引擎。它能从一句设定出发，自动生成层 层嵌套的历史、地理、角色关系与事件网络，并持续写出贴合世界观的剧情。支持 CLI 与可视化界面，可按时间和空间路径扩展世界，让故事像真实宇宙一样不断生长。项目用数字路径管理嵌套的时间、空间

Privacy-first bilingual webpage translation browser extension.

智能终端命令助手 — 用自然语言生成 Shell 命令，支持 OpenAI/Claude/Gemini/Ollama 等多后端

Free, browser-based BYOK AI website builder — v0 / Lovable / Bolt.new alternative. Bring your own key from a variety of providers, generate

Know when you'll hit your Claude, ChatGPT & Gemini usage limits — live 5h/weekly gauges, reset forecasts, and the usage history they don't s

An open canvas workspace for AI coding agents

Codex Portable · OpenAI Codex CLI 便携版 · U盘即走 · 零安装 · MIT

AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pi

RoleMule — One mule for every role. Self-hosted AI job companion. Paste a posting (or Chrome extension): five agents analyze the role, score

📰 An automated, multi-agent research ops AI pipeline that gathers daily AI news, synthesizes it into structured briefings, and delivers them

Give Claude Code an intern: drive Antigravity (Gemini), Codex, Copilot, Cursor and opencode — plus experimental Grok & Kimi — as sub-agents.

Claude省钱版 — 效果基本一致的情况下可以节约Token消耗约90%，超级省Token，支持OpenAI及国产大模型(DeepSeek/GLM/通义千问)的AI编程助手。本项目基于ClaudeCode源码实现。

Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-re

Use ChatGPT/Codex OAuth in Claude Code without an API key

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

Tiny Node.js CLI that prints banked Codex reset credit expiry dates from local Codex Desktop auth.

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens

Document extraction and validation for logistics companies.

Multiplayer infrastructure for AI agents

Talk to your Mac — a native macOS voice assistant that sees your screen, drives your Mac, and answers back. Powered by the OpenAI Realtime A

Real-time meeting & audio transcription for Windows (system audio + mic) — live captions via Deepgram, AI summaries via OpenAI. Tauri 2 + Re

Open Comet is an autonomous AI agent integrated into your Chrome browser. It enables safe, transparent, and multi-modal web automation—allow

Self-hosted chat client for Ollama, OpenAI, and Anthropic. Web UI and terminal CLI, with web search and a browser-automation agent.

Browser extension that turns any webpage into share-ready recommendation copy using your own LLM API key. One click → 3 styles → copy & past

一次看到 Codex (OpenAI) 與 Claude Code (Anthropic) 的訂閱用量、額度與花費的本機桌面儀表板。安裝: npx llm-usage-dashboard

The open-source, local-first alternative to LangSmith. No cloud. No setup.

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

Development workflows for Codex that keep technical rigor and edge-case handling from becoming product overengineering.