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]

938 best points · 554 comments · 9 Hacker News posts · 62,844 GitHub stars · View on GitHub

Hacker News discussions

• Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised (938 points, 500 comments, by dot_treo, 2026-03-24)
• Malicious litellm_init.pth in litellm 1.82.8 PyPI package – credential stealer (739 points, 1 comments, by theanonymousone, 2026-03-24)
• Show HN: liteLLM Proxy Server: 50+ LLM Models, Error Handling, Caching (140 points, 34 comments, by ij23, 2023-08-12)
• Show HN: Litellm – Simple library to standardize OpenAI, Cohere, Azure LLM I/O (62 points, 17 comments, by ij23, 2023-07-27)
• LiteLLM Python SDK Proxy Server LLM Gateway Call 100 LLM APIs in OpenAI Format (5 points, 0 comments, by Bluestein, 2025-07-24)
• Litellm 1.107.0 on PYPI Compromised (3 points, 0 comments, by kykeonaut, 2026-10-21)
• Code shouldn't know which LLM provider you're using (2 points, 0 comments, by yyyysa, 2026-09-24)
• Llama2 on Replicate faster than ChatGPT? (1 points, 2 comments, by ij23, 2023-08-16)
• New LiteLLM Vulnerability: Privilege Escalation to Proxy Admin and RCE (1 points, 0 comments, by ajackfox, 2026-09-30)