multi-provider
ArcReel
AI Agent 驱动的开源可自部署视频工作台:将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿,支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production
- 6.7k
- Python
- AGPL-3.0
- 1 d ago
otari
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
- 957
- Python
- Apache-2.0
- 9 h ago
senpi
pi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork of badlogic/pi-mono with extension-first additions. ganbare ganbare senpi 頑張れ頑張れ先輩
- 523
- TypeScript
- MIT
- 23 h ago
emperor-agent
Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.
- 219
- TypeScript
- MIT
- 5 d ago
Gozar
Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.
- 129
- Python
- 4 mo ago
AI-Worker-Proxy
OpenAI-compatible AI proxy: Anthropic Claude, Google Gemini, GPT-6, Cloudflare AI. Free hosting, automatic failover, token rotation. Deploy in 1 minute.
- 111
- TypeScript
- MIT
- 2 mo ago
litellm-rs
Self-hosted Rust LLM gateway with OpenAI-compatible APIs, load balancing, failover, and a reusable Rust kernel.
- 124
- Rust
- MIT
- 2 d ago
cc-copilot-bridge
V1 (Bash). Multi-provider routing for Claude Code CLI: your Copilot subscription, Ollama offline, or Anthropic Direct. V2 coming soon.
- 63
- Shell
- MIT
- 4 wk ago
outrider
Coding-agent harness for continuous contribution — discovers, implements & validates your next high-fit change as a review-ready draft PR you decide on.
- 26
- Python
- Apache-2.0
- 5 d ago
grob
LLM proxy with built-in DLP and regulatory compliance. Redacts secrets before they reach the API. EU AI Act, GDPR, HDS/PCI DSS ready. Multi-provider failover, live TUI, virtual keys, fan-out. 6 MB, zero deps. Rust.
- 25
- Rust
- Apache-2.0
- 2 d ago
DevCommandCenter
Workspace-first AI coding hub for managing agents, reviews, terminals, and task flows across multiple providers.
- 20
- Rust
- Apache-2.0
- 10 h ago
pixelrelay
The open-source, self-hosted unified API for generative media. One webhook-native endpoint across Fal, Replicate, and more — bring your own keys, get persistent jobs and automatic provider failover for free.
- 19
- Python
- 4 mo ago
omega
Self-hosted AI agent platform - modular Go core, TUI, multi-provider LLM routing. Started as a Pi/Tau port, long since its own project.
- 10
- Go
- MIT
- 1 d ago
new-api
Backend powering unorouter.com. Unified AI gateway aggregating 12+ providers with billing, channel routing, and OpenAI/Claude/Gemini compatible relay.
- 6
- Go
- AGPL-3.0
- 2 d ago
litellm-rust
Minimal Rust SDK port of LiteLLM – unified async client for OpenAI, Anthropic, Gemini, and xAI
- 8
- Rust
- MIT
- 20 h ago
SpindleStudio
A lightweight, Threads-style image generation studio for parallel ideas.
- 4
- TypeScript
- MIT
- 5 d ago
comfyui-gpt-image-bridge
ComfyUI 多供应商 GPT 图片生成与编辑桥接节点,支持 Codex OAuth、OpenAI API 和兼容 API。 | Multi-provider GPT image generation and editing bridge for ComfyUI with Codex OAuth, OpenAI API, and compatible APIs.
- 3
- Python
- MIT
- 4 mo ago
ai-gateway-cookbook
Runnable, framework-focused recipes for the Ferro Labs AI Gateway: build LangChain & LangGraph agents that route across OpenAI, Anthropic & Gemini through one endpoint — docker compose up and go.
- 3
- Python
- Apache-2.0
- 4 mo ago
aster-dns
Self-hosted multi-provider DNS management platform with a Go backend and SolidJS web console.
- 3
- Go
- Apache-2.0
- 3 mo ago
xidao-python-examples
OpenAI-compatible Python SDK examples — chat completions, embeddings, streaming, retries, and multi-provider base_url switching. Works with XiDao, OpenRouter, Together, and any OpenAI-compatible API.
- 2
- MIT
- 6 mo ago
custom-api-usage
Display token/quota usage from any JSON API in the VSCode status bar
- 0
- JavaScript
- MIT
- 2 mo ago
crabai
Minimal multi-provider LLM CLI. Single static binary, no runtime dependencies. Pipe stdin through any of 8 LLM providers (OpenAI, Anthropic, Google, Groq, and more) and get the response on stdout. Built for Unix pipelines and composable shell workflows.
- 0
- Rust
- Apache-2.0
- 9 mo ago







