Havuz

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

Give Claude Code or Antigravity an intern: drive Gemini (Antigravity), Codex, Copilot, Cursor and opencode as sub-agents, plus experimental

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

Sub2API 0.2.7 OpenAI OAuth 插件：Excel2API BPS 隧道、Codex CLI 工具目录、请求时区与并行降智检测。

Use GPT-6-Astra from local Codex for free - no paid plan, no API key, just a signed-in prism.openai.com session

Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.

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

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledg

Service status monitoring

Local-first AI image creation workbench | 本地优先的 AI 图片创作工作台

Observra is an open-source observability and telemetry framework designed for AI and agentic systems, providing deep visibility into agent b

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

Use OpenAI Codex models in GitHub Copilot Chat with ChatGPT OAuth

A self-hostable LLM router / gateway: OpenAI- and Anthropic-compatible, explicit-first routing with fallbacks, spend limits, and metadata-on

Skill RSI is a recursive self-improvement loop for Agent Skills, grounded in evals. Standalone or Codex plugin.

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

Self-improving agent harness for ChatGPT and Codex on Mac. #1 on AssistantBench. On-disk memory, privacy zones, verified completion.

The agent loop for Python. Your harness, any model.

Preserved-layout English-Chinese PDF translation for Zotero using Codex or OpenAI-compatible APIs

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

Chromium (Chrome/Edge) DevTools panel for debugging SSE / EventSource / NDJSON streaming responses. Inspect, filter, search, and export stre

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model provide

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Self-hosted alphaxiv-style paper-reading app (FastAPI CORS proxy + Vite/React/TS SPA)

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compre

基于 Sub2API 的非官方可扩展衍生版。

A native desktop coding agent built with Rust and GPUI.

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

Community troubleshooting knowledge layer for OpenAI Codex

Codex integration plugin for DeepSeek Harness, providing native Codex conversations powered by the Codex App Server, with workspace, termina

Open-source Kanban where every column is an AI agent

AI-powered meeting recorder on XIAO ESP32-S3 — live transcription, summaries, and AI chat

sigma is a Go package for provider-neutral AI model calls.

网页版登录态 → OpenAI 兼容本地反代：DeepSeek / Qwen / Doubao 免费额度驱动 ZCode。Web login → OpenAI-compatible local API.

macOS menu bar app that tracks usage limits and switches accounts across Claude Code, Claude Desktop, and OpenAI Codex — one click to flip w

Adversarial multi-model consensus protocol for Hermes Agent. Independent solve. Adversarial critique. Formal scoring. Verified synthesis.

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

AI生图提示词模板库，按角色与模板分类整理，包含写实cos、漫展场景、镜头、灯光、材质和负面词模板

Multi-platform automated operation and publishing (Xiaohongshu / Douyin / TikTok / X / YouTube / WeChat Official Accounts) for Muse, Dots, a

🔍 Detect API model dilution and fingerprint which LLM is actually running behind any OpenAI-compatible or Anthropic endpoint

专为sub2api打造的iframe嵌入式AI图片生成工具，纯前端实现，无依赖开箱即用。支持文生图、图生图、多种分辨率、批量生成和历史记录功能。

VerumTrade -- An open-source multi-agent AI trading framework, with visible reasoning and decision traces from evidence to final trade propo

Voice-based AI interview coach — feed it any job description in your language, practice in a fully controlled session, and get instant Engli

Mine reusable skills from your coding agents' transcripts (Claude Code, Codex CLI, or any agent) with outcome-weighted scoring and a local r

OpenChatGPTSkin is an open-source theme system for Codex Desktop. It does more than replace the home-page background: one color, background,

AI-powered log diagnostics engine that analyzes server logs, stack traces, and infrastructure failures to identify root causes and recommend

轻量的 AI Agent 核心：给它模型地址和工具（文件目录或内存对象），自动循环「问模型 → 执行工具 → 再问模型」；支持 4 种协议、上下文压缩保留、提示词缓存，纯对话模型也能用工具。

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

API Scraper — Hunt down leaked API keys in GitHub commits, validate them against live endpoints, and check remaining balances. Multi-service