Havuz

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

From K12 price radar to CPA proxy operations: a local-first console for offers, subscriptions, quotas, GPT Plus, and SMS.

Memory-aware GGUF inference runtime with OpenAI-compatible serving

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

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible

Local-first desktop coding agent with BYOK, MCP, and OpenAI-compatible / Ollama hosts

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Local-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.

Let Your AI Play Detroit：Become Human

Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style up

OpenAI- and Anthropic-compatible API gateway for Grok CLI with multi-account OAuth pooling, streaming, retries, and model-aware scheduling.

Unified interface to call OpenAI and Anthropic compatible LLM APIs from Rust and other languages

Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet

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

本地 AI 订阅与 API 网关：统一管理多家服务商账号，为桌面应用和编程工具提供接口。

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboar

System-wide AI text transformation for Windows

开源、本地优先的 AI 长篇小说创作引擎：多智能体世界推演、按弧规划、RAG 长程记忆、逐章审核与断点恢复 | Open-source AI novel generator for long-form fiction.

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

Aizen is an AI coding agent that lives on your PC or VPS. Control it from your phone while it autonomously fixes code, runs tests, and repor

Open-source AI model aggregation platform with web/admin dashboard, agents, image/video/audio generation, OpenAI-compatible API, wallet bill

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

OpenAI / Anthropic 兼容的自托管 AI 聚合网关与反向代理 · Antigravity / Codex / Kiro / Claude / Gemini / DeepSeek 多账号池统一接入

Cross platform GLM proxy for AutoClaw's Zhipu AI models. Provides OpenAI-compatible Chat Completions and Anthropic Messages APIs for Claude

帮你的 Claude Science 一键接入你自己的 API：DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点

Agnes AI model integration skills for OpenAI-compatible text, image, video, and agent workflows.

让 Claude Science 一键接入 DeepSeek、硅基流动 Kimi、OpenAI 等第三方 API 的 macOS 本地代理与安装器

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.

OpenAI-compatible Go gateway for Vertex AI Gemini with explicit model routing, live catalog refresh, and Cloud Run setup.

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Ultimate LLM API Integration Cookbook 2026 for Cursor & AI Agents

Proxy CodeBuddy with OpenAI-compatible and Anthropic-compatible APIs for Codex, Claude Code, and standard SDK clients.

Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 https:

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

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。

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

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

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

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

🚀 Run Meta AI FREE with Hermes Agent — No API Keys, No Limits. Muse Spark LLM from Telegram, WhatsApp & Web.

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

Open-source Fugu: the open-source LLM orchestration brain.

Intelligent multi-LLM router with task-aware routing strategies, cost optimization, and production safety controls — drop-in OpenAI-compatib

Run RKLLM only in one docker command. Already converted models here.

Free unlimited Gemini API for any OpenAI-compatible app.

Convert CodeBuddy/WorkBuddy (Tencent coding assistant) subscription into an OpenAI-compatible API. Use CodeBuddy GLM-5.2/Kimi/DeepSeek model

面向 PRD、业务规则、SOP、流程文档和产品截图的证据型 RAG 知识库。

Your AI intranet: network the computers you already own for inference and training.

TiyGate is a lightweight gateway for highly available LLM services. 一款致力于提供高可用 LLM 服务的轻量级网关。