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]

Latest release v1.108.1 · 5 Nov 2026

5 files for Codex, OpenCode, Gemini CLI, GitHub Copilot and Claude Code: litellm AGENTS.md, litellm GEMINI.md, duplicate-issue-check, issue-classifier and 1 more — 4,445 tokens loaded in every session.

Open on GitHub docs.litellm.ai

▶ Run Claude Code with Local LLMs: Ollama + LiteLLM + OpenTelemetry Nerding I/O with Jd Fiscus · about BerriAI/litellm · on YouTube →

Instructions

litellm AGENTS.md AGENTS.md C 4,436 tok
litellm GEMINI.md GEMINI.md A 9 tok

Skills

database-access .agents/skills/database-access/SKILL.md A 29 tok

Commands

duplicate-issue-check .github/prompts/duplicate-issue-check.md A —
issue-classifier .github/prompts/issue-classifier.md A —

These files are BerriAI/litellm's own configuration — they tell Codex, OpenCode, Gemini CLI, GitHub Copilot and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.