#openai-compatible

Browser-based Android phone agent using WebADB/WebUSB and OpenAI-compatible vision models

Never hit a rate-limit again. Route Claude Code, Cursor & 40+ providers through the subscription you already pay for, cut 40-80% tokens (RTK), stay un-banned. Self-hosted LiteLLM / OpenRouter / 9router alternative — one Go binary, anti-ban + sovereign P2P mesh.

1200+ AI models in your GitHub Copilot Chat — free & forever free. VS Code extension powered by OmniRoute: 330+ providers (90+ free) — Kimi, Claude, GPT, Gemini, GLM, DeepSeek, Qwen — with agent mode, tool calling, vision and quota-aware auto-fallback. MIT.

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

Local bridge for using OpenAI-compatible LLM providers with Codex and Claude coding clients.

OpenAI and Anthropic compatible LLM proxy for Ollama Cloud — panel→judge→synth fusion + smart routing, with task-specialized presets for coding, research, and agents.

🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.

🦀 Ultra-minimalist, high-resilience LLM routing gateway in Rust. OpenAI-compatible with auto-retry, backoffs, circuit breakers, SIGHUP hot-reloads, and open telemetry. Ideal for free provider surfing.

Explainable World Cup prediction workbench with a FLUX-10 inspired open baseline, backtesting, and OpenAI-compatible AI explanations.

Local MLX tuned models through OpenAI compatible LLM, image generation and audio inference on Apple Silicon — Rust + PyO3 + MLX

Local-first AI gateway. One OpenAI-compatible endpoint, 16 providers, free-first smart routing with automatic fallback. Every routing decision is stored and explained.

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Local AI model pool proxy with OpenAI/Anthropic-compatible routing and automatic failover.

AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust controls.

Local-first browser agent — attaches to existing Chrome via CDP, runs fully on local LLMs (LM Studio, Ollama, vLLM). Loop detection, multi-action chaining, data-agent-ref grounding.

Boost LLM reliability with dynamic sampling, retry logic, and a lightweight Go‑based proxy.

OpenAI-compatible HTTP API for Needle 2, Cactus Compute's 45M-parameter tool-calling model. Drop-in for any OpenAI client.

Released local Responses API gateway bringing Google Antigravity Claude Opus/Sonnet, Gemini, and BYOK providers to OpenAI Codex CLI/Desktop.

WiFi for AIs — drop-in skill that lets any AI publish a discoverable, controllable endpoint. Bidirectional: AI sees its connected clients and their capabilities.

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

Automated upkeep for a repository — triage, translation and the duties after them, with any OpenAI-compatible model, inside an authority you wrote down and it cannot exceed.

Open-source AI research workspace built with Electron and FastAPI, featuring provider-neutral agent workflows for DeepSeek, GLM, and other OpenAI-compatible models.

Translate GitHub issues and pull requests with any OpenAI-compatible model — model fallback, multi-draft scoring, and a sanitiser that assumes the thread is hostile.

Install Claude Code on your machine with one click to use DeepSeek models via domestic mirrors without needing a VPN.

TTS voice-cloning API with Chatterbox, VibeVoice, and Dia backends. Per-model isolated venvs, Cloudflare tunnel, OpenAI-compatible endpoint.

Local OpenAI-compatible text gateway backed by Codex App Server and your own ChatGPT/Codex login

OpenAI API wrapper for your AI subscription

Run local coding-agent tool loops against OpenAI-compatible Chat Completions providers.

OpenAI-compatible AI gateway examples for Cursor, Codex CLI, Aider, OpenHands, Flowise, SDKs, Responses API, and GitHub Actions.

Reproducible OpenAI-compatible AI API gateway benchmark with API NODE defaults, latency metrics, success rate, and GitHub Actions results.

A small self-learning local coding agent for LM Studio — single static Go binary, plan/auto modes, skills, permissions, in a Claude-Code-style TUI.

Multi-agent AI orchestrator that runs on free models — self-improving, MCP, token streaming, DAG, WebUI

MCP server for the GONKA network: run cheap LLM inference through the server (free trial or your own key), get multi-model second opinions, and compare live prices — for any AI agent.

Session-scoped launcher connecting coding harnesses (Claude Code, Codex, OpenCode, Pi) to model providers without permanent config mutation. TogetherLink fork → provider-neutral layer.

Self-hosted AI gateway for Claude Code & Codex — route to DeepSeek, Qwen, Kimi, GLM, Gemini, Groq with your own API key. Up to 97% cheaper. 7-day free trial.

Standalone Chutes model-provider plugin for Hermes Agent

AI-powered daily standup reporter in your terminal — log tasks, pull your git commits, and generate yesterday/today reports via any OpenAI-compatible endpoint, with a fully offline mode. Single static binary

Self-hosted, OpenAI-compatible AI gateway that splits your control plane (auth, guardrails, budgets, encrypted key vault, cost & observability) from the translation engine - swap Bifrost / LiteLLM / Portkey / Direct per provider at runtime. Own your keys; contain a compromised engine to one in-flight request.

Ruvicode AI API gateway core in Go. Key validation, rate and spend limits, streaming chat completions, and usage billing with an OpenAI-compatible endpoint. Provider identity masked.