Havuz

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

把 OpenAI Prism 折射成标准 API 的 Go 网关：OpenAI Chat / Responses、Anthropic Messages、Codex CLI 开箱即用，多账号池调度与内置管理控制台

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

Self-hosted LLM gateway in Rust: one OpenAI- and Anthropic-compatible endpoint for Claude, Codex, Qoder, Cline, Grok, Antigravity, CodeBuddy

🚀 One API gateway for GPT, Claude, Gemini, DeepSeek and more. OpenAI-compatible API for developers.

ModelFlux: OpenAI-compatible model traffic router with health-aware key-pool scheduling and failover

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

自托管的 AI API 中转站状态监控面板，支持 SUB2API / New API、余额与延迟采集、模型测速、可用率统计及飞书告警。

Declarative Python SDK for building AI inference platforms on Kubernetes — bare machines to a served model, composed rather than hand-assemb

CubicLM is a unified cross-platform AI workspace with local GPU acceleration (GGUF, LiteRT-LM). Supports on-device image generation, 23+ clo

Personal, local-first desktop AI gateway for Windows, macOS, and Linux. Connect Claude Code, Codex, and Gemini CLI to OpenAI, Anthropic, Gem

Rust port of earendil-works/pi — coding agent harness (pi-ai + pi-agent + pi CLI)

GLM-5.2 NVIDIA NIM Go 客户端 / OpenAI 兼容反向代理 — 自动化 hCaptcha 凭证池 + 流式推理，支持 Docker 部署。Go client & OpenAI-compatible proxy for NVIDIA Playground's

Multi-agent LLM pipeline for long-form novel continuation · 多 Agent 长篇小说续写流水线，19 轮迭代 + 全程 mock-first

Built an AI SaaS Platform that enables users to access multiple AI-powered tools through a unified dashboard, including content generation,

Adversarial LLM Reversal for hermes-agent

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

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.

🤖 多Agent求职系统 | Multi-Agent Job-Search Pipeline — 独立 Python 实现，3 个 AI Agent + 5 道安全护栏 + 工作流编排。支持 MCP 协议接入 OpenCode / Codex / Claude Code。Stan

High-performance LLM gateway in Go. 35x less RAM than Node.js version.

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

Free, open-source AI dictation for Windows & macOS & Linux. Hold a hotkey, speak, and cleaned-up text appears in any app - BYOK or local mod

Enterprise-grade capability-driven AI routing engine, proxy gateway, MCP server, developer CLI, and agentic skills aggregator for 19+ free-t

Developed a Multi-Agent Research Assistant that coordinates specialized AI agents to search, analyze, summarize, and synthesize information

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

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

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

A local-first Markdown workspace for planning, generating, and exporting article illustrations with OpenAI-compatible models.

Run local LLMs entirely in your browser, with no server, no install and no traces. A private, single-file AI chat UI and AGENT that also wor

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

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

Proof of concept: turn old Android phones into an LLM inference cluster. ADB zero-touch provisioning, llama.cpp on each phone, OpenAI-compat

Native iOS DeepSeek Harness port: BYOK inference, on-device Agent tools, iSH sandbox, Cordis plugins, and trajectory.

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

Deployment and verification tools for a Claude Code API server: systemd, real-completion health probes and end-to-end smoke checks.

Built a Data Research & Analysis platform that collects, cleans, and analyzes structured and unstructured data, generating visualizations, t

Developed a Document Intelligence platform that automates document processing using OCR, NLP, and AI to extract, classify, and validate stru

把 CodeArts Agent（华为云码道）桌面端的上游模型服务复刻成 OpenAI / Anthropic 兼容的 Go 网关 · 复用本机已登录凭据 · 纯标准库零依赖

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

IELTS Writing marker: band scores for all four criteria, every mistake marked in your text, and a plan for your next band using OpenAI API

Pocket-sized AI agent for embedded Linux in pure C — OpenAI-compatible, tool calling, streaming, ~550KB binary. Runs on routers (MT762X/Open

Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-c

Multi-format LLM proxy — translates OpenAI Chat, OpenAI Responses & Anthropic Messages. Works as a Claude Code LLM gateway with full model p

Built an AI-powered Resume Analyzer that evaluates resumes against job descriptions, extracts key skills and experience, provides ATS compat

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cl

DeepSeek Harness 模型管理插件：网关健康探测、模型目录发现与余额/配额展示。DSH plugin for LLM gateway health, model discovery and account balance monitoring.

OpenAI-compatible API proxy for ChatGPT web — expose ChatGPT as an MCP server, REST API, and OpenAI SDK endpoint via CDP-driven browser auto

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b