Havuz

Adaptive inference scheduling for AI agents — per-round model, effort and provider routing for coding harnesses: a Command Code mod or a loc

The ops layer for running Claude Code and Codex all day on a Mac: subscription-first routing with overflow to GLM/OpenRouter/Bedrock, pausel

An assistant for Windows that works inside 118 desktop programs and services through code instead of screenshots. It writes each program's o

OpenAI-compatible API gateway backed by the ChatGPT.com web UI (patchright + real Chrome): chat completions, thinking modes, image generatio

Self-hosted, OpenAI-compatible AI gateway for organizations — multi-provider (Azure/OpenAI/Anthropic/Gemini), revocable per-allocation crede

本地多模型路由器：让 Codex 桌面端 / Claude Code / 任意 OpenAI 客户端在一个菜单里共用 GPT、DeepSeek、Kimi、GLM、Gemini、Claude、ChatGPT 订阅额度 | Local multi-model router: one

Use your Cursor subscription as an OpenAI-compatible API. Direct agent.v1 protocol — real tool_calls, streaming, multi-account. No cursor-ag

Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.

Free GPT/Claude/Mistral via duck.ai — Telegram bot + OpenAI-compatible API (no keys, no browser, pure JS)

AI-routed gateway for free LLM APIs — reads your prompt and routes it to the best free model (Gemini, Groq, Cerebras, NVIDIA NIM, Mistral, O

Hi Code — 本地优先的桌面编码 Agent 工作台 · a local-first desktop coding agent workbench for any OpenAI-compatible model

Local, OpenAI-compatible HTTP relay that drives your own muse.ai web chat through a real Chromium tab over the Chrome DevTools Protocol. Cha

Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, bil

Give non-multimodal Claude Code main models the ability to see pasted screenshots — a ~200-line UserPromptSubmit hook.

Agente de programación para la terminal, gratis y en español: usa las IA gratuitas de más de 20 proveedores (Gemini, NVIDIA, Cerebras, OpenR

The last agentic harness you'll ever need. Bring any model; Pennant does the rest on your Mac and iPhone, and asks before anything is sent,

🤖 Serverless AI Gateway Bot for Telegram — Connect to 9+ AI providers (Gemini, Groq, OpenRouter, DeepSeek, OpenAI...) via Cloudflare Workers

Weftcanvas 纬线 — 可直接连接中转站的开源 AI 无限画布。支持 BYOK、模型列表跟随与可配置协议；本地优先、自托管，AGPL-3.0 / 商业授权。交流 QQ 群 743378399

Open-source privacy firewall for AI agents: masks personal data in text, tool calls and images before it reaches the LLM, and restores it in

Free LLM API providers list: verified free tier limits, API keys with no credit card, and OpenAI-compatible endpoints for developers.

Fcitx5 voice input addon — PulseAudio/PipeWire capture, Silero VAD, OpenAI-compatible & Volcengine Doubao streaming ASR, AsrSession architec

Local-first Windows client for GPT Image generation, multi-reference editing and async task workflows

One command spins up Qwen3.8-27B (abliterated, NVFP4) on a rented Blackwell GPU at ~150 tok/s and wires it into your local coding agent via

把 Claude Code CLI (claude -p) 包装成 OpenAI 兼容端点，供 SillyTavern 的 Custom (OpenAI-compatible) 源直接调用

Local-first novel-to-comic generator — free, no GPU, pluggable providers.

Agent Switch: Claude Code, Claude Desktop, Codex CLI, Codex Desktop, Hermes, OpenCode, OpenClaw and AI agent config switcher, model router,

Unofficial self-hosted Cloudflare OS Home with Docker Compose, project-local LiteLLM, Tailscale, and an agent-first runtime.

deepseek-harness 便携式变体 | 即插即用 U 盘 AI 助手：免安装 LLM Web UI、离线可用、适配中国网络，支持 OpenAI 兼容网关（Ollama / 阿里云百炼 / OpenRouter），Windows / Linux / macOS 三端即开即

一句话生成 NovelAI 出图提示词：正向 danbooru 标签流 + UC 负向，生成后本地再跑「NAI 整理 + 提示词体检」（不调模型）。可编辑的置顶破限词、角色设定、细分标签与拼装板、设定集、历史与保存库。纯本地、零运行时依赖，直连任意 OpenAI 兼容接口。

Transparent LLM gateway trace recorder · sub2api / CLIProxyAPI / new-api 的 LLM 网关流量录制器

ClinePass provider plugin for Hermes Agent (Kimi K3, GLM, DeepSeek, and more)

MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and p

OpenAI- and Anthropic-compatible local gateway for ZCode plan quota. Single Go binary, stdlib only.

AHK v2 LLM text actions for selected text on Windows

面向中国用户的开源 Grok Bot 替代方案，默认简体中文，支持 Claude、Codex、GPT、Grok、Gemini 与 API 中转站。

Self-hosted MCP gateway and LLM proxy. Serve any MCP server or REST API behind OAuth 2.1, run stdio/git MCP servers on demand, and proxy AI

基于免费 Agnes AI 的自托管多模态 Web 客户端，支持 AI 对话、文生图/图生图、文生视频/图生视频。Vue 3 + FastAPI 全栈。

MacOS voice input with ASR transcription, LLM correction, and global hotkeys.

Open-Source Agentic Harness for Reliable Task Completion, even on small local models. 💻🧠🤖

A Cloudflare-based LLM gateway and proxy server. Literally the CLIProxyAPI (CPA) project, deployed as a Cloudflare Worker in one click.

🚀 Route OpenAI-compatible requests across multiple free LLM providers with automatic failover. Zero cost.

Run open AI models on your own computer — a friendly desktop app and local gateway for llama.cpp and more. Private, free, open source.

Hermes Agent on your phone — runs fully on-device (no server, no root) or connects to your own server. Kanban, MCP, skills, built-in Linux.

Self-hosted AI agent living inside Zalo (personal account). Multi-account, 15 tools + external MCP servers, web dashboard, scheduler, durabl

穿越小说模拟：AI互动小说，支持历史与自由世界、参考书籍、局部纠错和按需Agent助手。Android与Windows，自行配置AI服务，本机保存故事。

Unofficial OpenAI-compatible bridge for Factory Droid

Model-agnostic AI poster grid inspector: detect a poster's layout grid system with a vision model, view it overlaid, and export SVG guides /

Local OpenAI/Anthropic-compatible proxy using structured conversation state to reduce repeated context. Savings and compatibility depend on

模型路由器：在 Codex Desktop 和 Claude Desktop 使用 Claude、第三方 API 与自定义模型。Local LLM proxy for Codex & Claude Desktop: OpenAI Responses / Chat Completi

Distil an expensive LLM API call on a narrow task into a small local model: capture traffic, curate, LoRA fine-tune with MLX on Apple Silico