Python
BerriAI/litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
★ 62.8k
Stars
13k forks · 5.7k open issues
+66/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
63.8
Momentum / 100
see the breakdown below
3y ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 34.9 | +66/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.94× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 13.9 | 62.8k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 63.8 | sum of the above |
Detail
| Topics | ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai |
| Matched on | LLM & Inference (llm) |
| Short window | +460 stars over 7 days = 65.7/day |
| Long window | +1.8k stars over 26 days = 69.8/day |
| Lifetime average | 52.41 stars/day over 1,198 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |