#openai-compatible Repositories
Discover 53 active open source GitHub repositories tagged with #openai-compatible, accumulating 274,924 total stars (averaging 5,187 stars per project). Leading this topic is Ebony-Vinyl/dsh-our-free-model with 82,790 stars.
53 repositories total
Just install this plugin in dshโno login, registration, or API key required, and you can use cutting-edge models including DeepSeek V4.1 Flash and Kimi K3. Completely free, with no usage limits.
An open-source coding agent for your terminal, written in Rust. It works with any model, can split one task across several agents, and every line of it is yours to read.
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200ยตs of overhead at 5k RPS.
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat โ all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
Local-first AI agent workspace for coding, writing, design, research, and automation โ one runtime for desktop GUI and TUI.
โก Pure-Rust WebGPU inference engine โ OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
๐ค Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
Open-source GEO content engineering and multi-site distribution platform with AI quality inspection, illustrated admin help, hosted sites, browser-assisted publishing, and signed updates.
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4ร faster than Apple's MLX (mlx-lm) on the same weights.
A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health.
FuXi is a fast, self-contained AI coding agent that lives in your terminal โ edit code, run commands, and drive tools, with cost-aware routing across LLM providers.
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor.
Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
Local AI routing gateway with Agent client takeover โ reuse existing client logins, access quotas from 50+ AI providers through a single base URL, with unified OpenAI / Anthropic / image-generation APIs, multi-account routing, check-ins, balance management, and request reports.
VCP is deployed between AI model APIs and frontend applications, serving as an industrial-grade infrastructure demonstration project for AGI OS development and exploration. Through a unified instruction protocol, multi-level persistent memory, a distributed plugin engine, and a multi-agent collaboration framework, it transforms 'stateless, memoryless, and tool-incapable' large language models into complete intelligent agent systems possessing permanent self-awareness, physical world operational capabilities, and collective collaborative intelligence.
Scrape the latest articles from the 90 top technical blogs recommended by Andrej Karpathy, filter them with AI multi-dimensional scoring, and generate a daily curated digest. More details can be found in the official account: 'ๆ็นๅฟAI'.
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Source-available agent platform for Global ร China enterprises โ wire every system through one agent core. Self-hosted, any LLM.
Standalone CliProxyAPI usage tracker with SQLite persistence and built-in dashboard.
AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.
Self-hosted search gateway for AI agents. Unified search, news, and page extraction with provider fallback. REST API, MCP server, and TypeScript library.
74 free LLM API providers & 450+ free models (limits, no-card options) + Free-LLM Router: all of them behind one OpenAI/Anthropic-compatible endpoint with instant failover. Run Claude Code, Codex, Cursor, Aider on free models. Gemini, Groq, Mistral, DeepSeek, Qwen & more. Synced daily.
ReachAI Enterprise AI Agent Development Platform: Quickly and securely modernize existing business systems with AI, enabling AI to query data, fill out forms, and handle business tasks directly within OA, ERP, CRM, and other existing business applications.
Gemini web โ OpenAI-compatible + native Gemini API, self-hosted, no API key. Gemini 4 Argon from a paid account cookie, strict_model (429 instead of a silent downgrade), cookie pool with auto-renewal, proxy pool, admin panel, image & video generation, single Go binary ยท Reverse-proxy the Gemini website as an OpenAI-compatible / native Gemini API; use Gemini 4 Argon directly with a cookie from a paid account.
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
Yichuang: a purely local, open-source desktop app for AI web novel writing, supporting novel creation, AI-assisted writing, BYOK, and custom prompts.
โก Self-hostable YesCaptcha-compatible captcha solver built with FastAPI, Playwright, and OpenAI-compatible multimodal models.
FreeTheAi (Free The AI): free OpenAI-compatible AI API with 50+ models, Discord key signup, streaming, tools, images, Messages, and Responses. No credit card.
Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.
A local-first, multi-model AI image generation workbench supporting GPT Image, Gemini, image editing, an asset library, templates, and concurrent tasks.
Bridge OpenCodeโs free models to WorkBuddy โ isolated runtime, concurrency detection, verdict caching, one-click import, and a local OpenAI-compatible proxy endpoint
<10 MB โ a self-hosted AI novel writer in a single Go binary with a web UI. Turn ideas into outlines and chapters with review, foreshadowing, fact-checking, and full-book polishing. OpenAI-compatible APIs; Chinese and English.
Free MIT AI coding agent โ no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust.
[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.
OpenAI-compatible gateway configurator for Claude Code, OpenCode, and Codex CLI. Zero-dependency, interactive + CI, atomic backup + restore, config preservation, built-in self-test.
Uncensored AI API and models โ one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen and Kimi, with uncensored and abliterated variants where available. OpenAI- and Anthropic-compatible. Pay per token.
Community-driven, reusable components for distributed, durable, and agentic AI applications across all cloud service providers
Local AI chat for iPhone, iPad and Mac. Connect Ollama, LM Studio or any OpenAI-compatible server, or run MLX models on-device. Includes tools and web search.
Frequently Asked Questions
What is the most popular #openai-compatible repository on GitHub?
The top ranked open source #openai-compatible project on GitHub is Ebony-Vinyl/dsh-our-free-model with 82,790 stars. Just install this plugin in dshโno login, registration, or API key required, and you can use cutting-edge models including DeepSeek V4.1 Flash and Kimi K3. Completely free, with no usage limits.
Which programming languages are most used in #openai-compatible repositories?
Among the top ranked #openai-compatible projects on GitHub, the most common programming languages are Python, Go, TypeScript, JavaScript.
How is the #openai-compatible repository ranking calculated?
We track 53 active open source repositories tagged with #openai-compatible (500+ stars), totaling 274,924 stars with an average of 5,187 stars per repository. Rankings update daily from the GitHub API.