Open source. Open possibilities.

Minimal FastAPI proxy for OpenAI Chat Completions and Embeddings APIs. Supports multi-tenant key mapping, streaming, and official SDK compatibility without a database.

PDFMathTranslate is an open-source tool for translating scientific PDF documents while preserving their original layout, including formulas, charts, tables of contents, and annotations. It supports multiple translation services and offers CLI, GUI, Docker, and Zotero integration.

A curated open-source prompt library for GPT Image 2, featuring 2000+ prompts with preview images across 16 languages, designed for high-quality AI image generation with text rendering and cross-image consistency.

Orrery is an architect-first orchestration system for coding agents, ensuring precise model pinning, consented writes, and fail-closed operations. It delegates implementation to specialized AI roles (Astra, Terra) while the human architect retains control over requirements, architecture, and verification, with a read-only advisor (Sol) for final review.

OpenHands Agent Canvas is a self-hosted developer control center for managing coding agents and automations across local, remote, and cloud backends.

OmniRoute is an open-source MIT-licensed AI gateway providing one unified endpoint to access 352+ AI providers and 1200+ models (150+ free tiers). It features quota-aware auto-fallback, token compression saving 15–95%, and integrates with Claude Code, Cursor, Cline, and other coding agents.

Oh My OpenAgent (OmO) is an open-source AI coding agent toolkit with three editions: Ultimate for OpenCode, Light for Codex CLI, and standalone Senpi beta. It provides multi-model orchestration, ultrawork mode, parallel team agents, LSP/AST-Grep integration, and MCP support to automate and streamline software development workflows.

Self-hosted AI API gateway that gathers upstream LLM provider keys as channels, exposes unified OpenAI and Anthropic endpoints with automatic protocol conversion, and tracks token usage, cache hit rate and per-key statistics in real time. Go + React, shipped as one binary.

FastGPT is a knowledge base platform based on large language models, providing out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, supporting rapid construction and deployment of complex Q&A systems.

Open WebUI is a self-hosted, extensible AI platform that provides a user-friendly interface for local and cloud-based models, supporting Ollama and OpenAI-compatible APIs.

Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach the LLM, reducing token usage while preserving key information. Runs locally as a Python/TypeScript library, proxy, MCP server, or agent wrapper for Claude Code, Codex, Copilot, Cursor, and more.

A Chrome browser extension that translates YouTube English subtitles into a target language, supporting bilingual display, full-text comparison, and SRT file export.

Self-hosted multi-tenant AI platform combining a polished chat UI with an OpenAI-compatible LLM gateway: multi-provider channel routing with priority and weight-based load balancing, subscription and usage billing, admin dashboard, file parsing, and SearXNG web search.

LobeHub is an open-source AI agent platform that organizes agents into a 7×24 operation, enabling users to hire, schedule, and collaborate with AI teammates while self-hosting via Docker or Vercel.

CLIProxyAPI is a proxy server that exposes OpenAI/Gemini/Claude/Codex/Grok-compatible API endpoints for CLI AI coding tools. It supports OAuth login for Claude Code, ChatGPT Codex, Gemini, and Grok, multi-account load balancing, streaming, tool calling, multimodal input, a management API, and an embeddable Go SDK.

A curated collection of 107 foundational generative AI research papers with comprehensive summaries, learning roadmaps, glossaries, and decision guides—making cutting-edge AI research accessible to everyone.

Provider-neutral FastAPI gateway for LLM routing, retries, fallbacks, structured output, and usage/cost accounting. Supports Gemini and OpenAI with model aliases, retry policies, and persistent usage tracking.

vLLM is a high-throughput, memory-efficient library designed for Large Language Model (LLM) inference and serving.

MLflow is an open-source AI engineering platform designed for managing the lifecycle of agents, LLMs, and traditional ML models, focusing on observability, evaluation, and deployment.

gateway is a headless AI gateway for OpenAI, enabling secure multi-user access, cost tracking, rate limiting, and PII redaction with minimal setup.