Repositories
48
Net stars gained, last 7 days
+34,025
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Oct 12, 2026 +7,785 net stars (median day +2,409)
- Ebony-Vinyl/dsh-our-free-model+2,528 (32%)
- Alishahryar1/free-claude-code+1,364 (18%)
- yetone/magpie+1,010 (13%)
- 2
Oct 13, 2026 +6,926 net stars (median day +2,409)
- Ebony-Vinyl/dsh-our-free-model+2,076 (30%)
- yetone/magpie+1,288 (19%)
- Alishahryar1/free-claude-code+835 (12%)
- 3
Oct 19, 2026 +7,257 net stars (median day +2,409)
- Ebony-Vinyl/dsh-our-free-model+3,024 (42%)
- yetone/magpie+1,033 (14%)
- tashfeenahmed/freellmapi+604 (8%)
- 4
Oct 20, 2026 +8,646 net stars (median day +2,409)
- Ebony-Vinyl/dsh-our-free-model+3,060 (35%)
- deepseek-ai/deepseek-recipe+1,325 (15%)
- yetone/magpie+905 (10%)
- 5
Oct 21, 2026 +7,536 net stars (median day +2,409)
- Ebony-Vinyl/dsh-our-free-model+3,441 (46%)
- yetone/magpie+746 (10%)
- tashfeenahmed/freellmapi+633 (8%)
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.
Largest
Most stars in total now.
description:
Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models
readme:
aggregates multiple accessible providers and interfaces to make working with modern LLMs and media-generation models easier and more flexible
readme:
Route any supported harness to models from any supported provider.
readme:
Open Source AI Gateway for 100+ LLMs. Self-hosted. Enterprise-ready. Call any LLM in OpenAI format.
readme:
OpenAI 兼容转发端口——本机其它工具通过 base URL 与 Key 即可调用这些模型
readme:
CLIProxyAPI is a proxy server that provides OpenAI/Gemini/Claude/Codex/Grok compatible API interfaces for CLI.
description:
Self-hosted LLM gateway with OpenAI-, Claude- and Gemini-compatible APIs, model routing, access control, usage tracking and cost accounting.
description:
All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys.
readme:
AI API Gateway Platform for Subscription Quota Distribution
readme:
各类模型all-in-one，协议统一使用openai标准协议，其他厂商模型仅需更换模型名称，接入便捷
Newest Admissions
Entered the index by the rising rule, newest first.
readme:
organizes complementary models to work together, choosing which model to call as task needs and remaining budgets change
description:
RouterHub gives developers one OpenAI- and Anthropic-compatible key for 37 frontier and open-weight models
description:
A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection.
readme:
RouterHub is an OpenAI- and Anthropic-compatible gateway for exactly that workflow.
readme:
An async gateway that exposes the muse.ai web app as an OpenAI-compatible API
readme:
将 **muse.ai** 网页端的前沿多模态能力逆向工程封装为标准的 **OpenAI 兼容 RESTful API**
readme:
A local gateway for Claude Code, Codex and other AI clients, on macOS, Windows and Linux.
description:
one key for Claude, GPT, Gemini, Grok, DeepSeek, GLM, Qwen and Kimi
description:
a local OpenAI-compatible gateway for Claude Code, Codex, Cursor, Cline and OpenCode
readme:
基于 Rust 的自托管 AI API 中转，为你的模型、账号和客户端密钥提供统一管理入口。
How a repository gets this Tag
An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.