# BerriAI/litellm

> Open-source AI gateway and Python SDK that calls 100+ LLM providers (OpenAI, Anthropic, Bedrock, Azure, VertexAI, etc.) through a single OpenAI-compatible interface with cost tracking, guardrails, load balancing, and logging.

- Magnitude: 3.2 out of 10 — Steady
- Stars: 60,473 total · +24 stars measured 2026-10-09, 11:35–13:11 UTC, ≈ 52 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2023-07-27 · Last push: 2026-10-09
- GitHub: https://github.com/BerriAI/litellm · Homepage: https://docs.litellm.ai/docs/ · Page: https://gitnova.dev/en/r/BerriAI/litellm

## Useful for

- Replace direct calls to multiple LLM SDKs with a single OpenAI-format API
- Deploy a self-hosted proxy with virtual keys and spend tracking for a team
- Connect MCP servers and A2A agents to any LLM through the gateway

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 11:35–13:11: 60449 → 60473 stars (+24). This is the change over that interval.
- Estimated end-of-day forecast: about +52 stars, using observed gains and the previous day.
- GitHub Trending today: #7, +95 stars.
- GitHub Trending Python today: #2, +95 stars.
- About 39 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 12,172
- Issues and pull requests: 44,562
- Watchers: 236
- Average over the last week: 62 per day
- Usual pace: 76 per day
- Stars in the last hour (measured): 16
- Latest release: v1.106.0-dev.2 (2026-10-08)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-10 … 2026-10-09: 77, 63, 66, 73, 90, 91, 105, 99, 80, 75, 93, 102, 74, 82, 68, 64, 54, 72, 77, 75, 61, 82, 47, 43, 39, 59, 72, 80, 90, 24

## Spotted in now

- GitHub Trending today: #7, +95 stars
- GitHub Trending Python today: #2, +95 stars

## Similar by description

1. **maximhq/bifrost** — 2.5 · Steady · Language models · Go · +21 stars measured 2026-10-09, 00:09–13:14 UTC, ≈ 38 by evening
   High-performance Go AI gateway that unifies 23+ LLM providers (OpenAI, Anthropic, Bedrock, etc.) behind a single OpenAI-compatible API with fallbacks, load balancing, and semantic caching.
   Full card: https://gitnova.dev/en/r/maximhq/bifrost.md
2. **songquanpeng/one-api** — 1.5 · Steady · Language models · JavaScript · +0 stars measured 2026-10-09, 11:36–13:18 UTC, ≈ 3 by evening
   LLM API management and key redistribution system: unifies OpenAI, Azure, Anthropic, Gemini, DeepSeek and dozens of other providers under a single OpenAI-compatible API. Single binary, Docker-ready, suited for proxying and reselling keys.
   Full card: https://gitnova.dev/en/r/songquanpeng/one-api.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-09 13:25 UTC, updated every 30 minutes.