Agent Friendly Code

BerriAI/litellm

GitHub
https://github.com/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]

  • ai-gateway
  • anthropic
  • azure-openai
  • bedrock
  • gateway
  • langchain
  • litellm
  • llm
  • llm-gateway
  • llmops
  • mcp-gateway
  • openai
  • openai-proxy
  • rust
  • rust-ai
  • vertex-ai
Stars:
62.7k
Language:
Python
Default branch:
main
Last scored:
Overall

At a glance

Rank
#27 of 401
Top 7% · #9 of 56 Python repos
Checks passed
11 of 17
Full list below
Best set up for
Kimi Code CLI
Score 90.4
Needs most work for
Aider
Biggest fix: .aider.conf.yml (+14.1 pts)

What it has

What it's missing

What to fix first

Pick an AI agent

Showing fixes for Claude Code

  1. 1
    Pre-commit / git hooks
    Set up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.
    +5.3 pts
  2. 2
    Manageable size
    If possible, split into smaller modules or carve out a focused entry path. Document where to start in AGENTS.md.
    +5.3 pts

Score for each AI agent

Each agent weighs the checks by its own docs. Under each score are its top three. How each agent is scored →

Kimi Code CLI
#22 of 401
90.4
  • ✓AGENTS.md / CLAUDE.md
  • ✓Test suite
  • ✓Dependency manifest
Codex
#23 of 401
89.9
  • ✓AGENTS.md / CLAUDE.md
  • ✓README
  • ✓Test suite
Claude Code
#43 of 401
89.5
  • ✓AGENTS.md / CLAUDE.md
  • ✓Test suite
  • ✓Reproducible dev env
Pi
#24 of 401
89.3
  • ✓AGENTS.md / CLAUDE.md
  • ✓Test suite
  • ✓Linter / formatter config
Gemini CLI
#5 of 401
85.9
  • ~GEMINI.md
  • ✓README
  • ✓Test suite
Devin
#37 of 401
84.8
  • ✓Reproducible dev env
  • ✓Dependency manifest
  • ✓Test suite
Cursor
#29 of 401
81.4
  • ✗Cursor rules (.cursor/rules)
  • ✓README
  • ✓Type configuration
OpenHands
#41 of 401
78.4
  • ✓CI configuration
  • ✓Dependency manifest
  • ✓Reproducible dev env
Aider
#43 of 401
77.2
  • ✗.aider.conf.yml
  • ✓Linter / formatter config
  • ✓Test suite

Does BerriAI/litellm have agent instructions?

An AGENTS.md (or CLAUDE.md) at the root tells AI coding agents how to build, test and work in the repo. A few agents also read a file of their own.

AGENTS.md / CLAUDE.md
AGENTS.md (new tab) · 19,742 characters
Agent-specific files
GEMINI.md (new tab) (37 characters), .agents/skills (new tab) (1 skill)No .cursor/rules, .openhands/setup.sh or .aider.conf.yml
Repos that have one
29 of 56 Python repos · 221 of 401 repos on the leaderboard · See examples →

All 17 checks · 11 passed

Skills (.agents/skills)· 100% pass
1 skill in .agents/skills/
.agents/skills/database-access/SKILL.md
AGENTS.md / CLAUDE.md· 100% pass
Substantive (19,742 characters)
AGENTS.md
.aider.conf.yml· 0% pass
No .aider.conf.yml at repo root
CI configuration· 100% pass
40 GitHub Actions workflows
.github/workflows
CONTRIBUTING guide· 100% pass
Guide present
CONTRIBUTING.md
Cursor rules (.cursor/rules)· 0% pass
No .cursor/rules/*.mdc or .cursorrules
Dependency manifest· 100% pass
Manifest present
package.json
Reproducible dev env· 100% pass
4 env artifacts (Makefile, .devcontainer/devcontainer.json)
Makefile
GEMINI.md· 50% pass
GEMINI.md exists (37 characters) — thin
GEMINI.md
License file· 100% pass
License present
LICENSE
Linter / formatter config· 100% pass
Config detected
ruff.toml
.openhands/setup.sh· 0% pass
No .openhands/setup.sh
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
README· 100% pass
README detailed (40,221 characters)
README.md
Manageable size· 20% pass
10000+ files — very large
Test suite· 100% pass
Found /tests
tests
Type configuration· 100% pass
Type config present
pyrightconfig.json

How BerriAI/litellm compares

vs leaderboard average
18.4 pts above
Average 66.8
vs Python average
14.2 pts above
Average 71.0
Stars among Python repos
#21 of 56

Missing here, and how many repos have it

  • Pre-commit / git hooks · passed by 29% of leaderboard repos, 71% of Python repos
  • Cursor rules (.cursor/rules) · passed by 4% of leaderboard repos, 7% of Python repos

Passes checks most repos miss

  • Skills (.agents/skills) · only 17% of repos pass it
  • Reproducible dev env · only 22% of repos pass it

One fix for the most agents: Pre-commit / git hooks would raise the score for all 9 agents, by up to 6.0 points.

Similar repos

Same language and host as this repo, closest in overall score.

All Python repos →

Same topics, any language

Repos tagged with the same GitHub topics, most shared first.

Add a badge to your README

Paste this at the top of the README. It shows the score, and links back to this page.

Agent friendly score for github/BerriAI/litellm
[![Agent Friendly](https://agentfriendlycode.com/api/badge/github/BerriAI/litellm.svg)](https://agentfriendlycode.com/repo/github/BerriAI/litellm)

Check the score on every pull request

A GitHub Action posts one comment per pull request with how the score changed and why.