BerriAIBerriAI/litellm/.github/AGENTS.md

litellm

AGENTS.md63k starsChanged 58 days agoLicence not identifiedView on GitHub

Integration groups and replica runs remain in workflows/test-integration.yml. Do not duplicate them in another workflow. CI helpers used by existing workflows live in scripts/ci/. Jobs that need merge bases check…

Sep 13, 2023Add support for Ollama, Palm, Claude-2, Cohere, Replicate Llama2 CodeLlama (100+LLMs) - using LiteLLM — OpenBMB/ChatDev92 reactions · 34 comments
May 12, 2024Support tools in OpenAI-compatible API — ollama/ollama81 reactions · 22 comments
Jun 25, 2025[Feat] Allow setting `baseUrl` to use gemini-cli with LiteLLM Proxy — google-gemini/gemini-cli53 reactions · 19 comments
Oct 4, 2023Add support for Ollama, Palm, Claude-2, Cohere, Replicate Llama2, CodeLlama, Hugging Face (100+LLMs) - using LiteLLM — microsoft/autogen45 reactions · 47 comments
Feb 17, 2025feat: add support for copilot models — Aider-AI/aider24 reactions · 9 comments

38 more on GitHub

Apr 23, 2025Support many model providers & local models through litellm — rowboatlabs/rowboat17 reactions · 8 comments
Dec 7, 2025Gemini 3 Pro support and cross-model conversation compatibility — openai/openai-agents-python16 reactions · 10 comments
Aug 11, 2025litellm: missing prisma client — NixOS/nixpkgs14 reactions · 5 comments
May 7, 2025Add support for adding custom models via LiteLLM — Trae-AI/TRAE14 reactions · 1 comment
Mar 28, 2026issue: reasoning_content is stripped from assistant tool call messages, breaking multi-turn tool calling with reasoning models (Kimi K2.5, etc.) — open-webui/open-webui9 reactions · 11 comments
Mar 24, 2026[Notice] LiteLLM Supply Chain Attack — stanfordnlp/dspy9 reactions · 1 comment
Apr 5, 2024Using LiteLLM to support more models — SWE-agent/SWE-agent8 reactions · 15 comments
Aug 4, 2023Add support for Llama 2, Palm, Anthropic, Cohere Models - using litellm — FoundationAgents/MetaGPT8 reactions · 9 comments
Apr 3, 2026Suggestion: expose upload-time metadata for uv exclude-newer — pypiserver/pypiserver7 reactions · 2 comments
Mar 24, 2026Restrict litellm version to <=1.82.6 — stanfordnlp/dspy6 reactions
Jan 1, 2025Add LiteLLM - support for Ollama, Vertex AI, Gemini, Anthropic, Bedrock (100+LLMs) — microsoft/graphrag4 reactions · 9 comments
Aug 16, 2024Add prompt caching (Sonnet, Haiku only) — OpenHands/OpenHands4 reactions · 19 comments
Sep 13, 2026IPI-1200 · PR-REVIEW-V2-001 — Run Automatic PR Reviews on Free NVIDIA Models — amoai-tech/ipixai3 reactions · 3 comments
Jun 17, 2026chore(deps): bump the uv group across 1 directory with 2 updates — jaylfc/taOS3 reactions · 3 comments
Jun 16, 2026build(deps): bump the uv group across 1 directory with 2 updates — jaylfc/taOS3 reactions · 4 comments
Apr 23, 2026Feature: Add LiteLLM provider (unified interface to 100+ models) — laravel/ai3 reactions · 1 comment
Apr 20, 2026deps(pip): bump the pip-patch-minor group with 24 updates — hashgraph-online/hol-guard3 reactions · 2 comments
Apr 16, 2026fix: restore clientHeaders passthrough in chatCore (regression from #1227) — cheaper-inference/OmniRoute3 reactions
Apr 13, 2026fix: forward client x-initiator header to GitHub Copilot upstream — cheaper-inference/OmniRoute3 reactions · 1 comment
Feb 19, 2026fix(codex): fallback when gpt-5.3-codex pricing entry is zero — ccusage/ccusage3 reactions · 4 comments
May 14, 2025fix: Vertex AI model names use vertex_ai/ prefix — Aider-AI/aider3 reactions · 2 comments
Jan 2, 2025Fix Google Gemini bug with finish_reason — jekalmin/extended_openai_conversation3 reactions · 4 comments
Oct 22, 2023Add support for Bedrock, Ollama, Palm, Claude-2, Cohere, Replicate Llama2, CodeLlama, Hugging Face (100+LLMs) - using LiteLLM — letta-ai/letta3 reactions · 8 comments
Sep 7, 2023Add support for Ollama, Palm, Claude-2, Cohere, Replicate Llama2 CodeLlama (100+LLMs) — openinterpreter/openinterpreter3 reactions · 6 comments
Sep 7, 2023Add support for Palm, Claude-2, Cohere Llama2, CodeLlama (100+LLMs) — weaviate/Verba3 reactions · 5 comments
Nov 6, 2026chore: refresh model metadata from LiteLLM 1.108.1 — stanfordnlp/dspy2 reactions · 3 comments
Oct 31, 2026chore(deps): bump litellm from 1.102.1 to 1.102.2 — JWEB0689/pr-agent2 reactions · 5 comments
Oct 1, 2026Update dependency litellm to v1.103.2 — Jonathan-Harris1975/RAMS2 reactions · 3 comments
Sep 17, 2026chore(deps): bump litellm from 1.83.0 to 1.101.0 in /adapters/ml_dev_bench — bespokelabsai/harbor2 reactions · 2 comments
Jul 26, 2026build(deps): bump litellm from 1.83.14 to 1.93.0 in /cookbook/litellm-ollama-docker-image in the pip group across 1 directory — CaffeeLake/litellm2 reactions · 1 comment
Jul 24, 2026build(deps): bump the uv group across 2 directories with 2 updates — CaffeeLake/litellm2 reactions · 2 comments
Jul 22, 2026build(deps): bump the uv group across 3 directories with 15 updates — CaffeeLake/ragflow2 reactions · 1 comment
Jul 17, 2026build(deps): bump the uv group across 5 directories with 14 updates — CaffeeLake/ragflow2 reactions
Jun 17, 2026chore(deps): bump litellm from 1.83.7 to 1.84.0 in /backend/agent — galyarderlabs/galyarder-agent2 reactions · 1 comment
Apr 3, 2026chore(deps): bump litellm from 1.74.9 to 1.83.0 in the uv group across 1 directory — https-quantumblockchainai-atlassian-net/autonomous-crewai-constellation-codex-guardians2 reactions · 2 comments
Apr 3, 2026Bump litellm from 1.69.1 to 1.83.0 in /deep_research — cicero-im/zenml-projects2 reactions · 3 comments
Apr 3, 2026Bump litellm from 1.57.8 to 1.83.0 — cicero-im/DarconDocker2 reactions · 2 comments
Aug 19, 2023Add support for Llama2, Palm, Cohere, Anthropic, Replicate, Azure Models - using litellm — pyspark-ai/pyspark-ai2 reactions · 8 comments

On YouTube · 24

Mar 28, 2025LiteLLM - Simplify AI API Management With One Library — Better Stack40k views · 14 comments
Jul 26, 2026Stop Managing Multiple LLM APIs: The LiteLLM Setup Guide — Simple Tech1.8k views
Sep 15, 2026Enterprise MCP with LiteLLM: auth, tool permissions and budget — LiteLLM AI Gateway915 views · 1 comment
Oct 10, 2026LiteLLM: One API for 100+ LLMs — CLI Stack898 views
Jul 7, 2026LiteLLM GitHub Explained: Enterprise AI Gateway With Fallback Routing — Alex Hitt769 views

19 more on YouTube

Jul 24, 2026Kill Your ChatGPT Bill: Open WebUI + Ollama + LiteLLM — Open Codes552 views
Sep 24, 2026How to get started building with Jev in 5 mins using LiteLLM — LiteLLM AI Gateway435 views
Oct 9, 2026LiteLLM: Access 100+ AI Models with a Single OpenAI‑Style Request — Next Horizon404 views · 1 comment
Sep 5, 2024GitHub - BerriAI/litellm: Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format ... — GitHub Daily Trend AI Podcast260 views
Mar 7, 2026Are your AI project costs out of control? Use litellm to precisely track LLM costs and find the ... — DevCovery251 views
Oct 5, 2026Budgets, Rate Limits, and Kill Switch for Agents in LiteLLM — LiteLLM AI Gateway166 views
Oct 10, 2026Getting started with Guardrails in LiteLLM — LiteLLM AI Gateway134 views
Sep 23, 2026LiteLLM: call 100+ LLM APIs through one OpenAI-format endpoint — AI Signal124 views
Aug 10, 202656K ⭐ One Gateway for Every AI Model — LiteLLM — Github God Eng102 views
Jul 24, 2026Python開発者向け｜LiteLLM(BerriAI)で100以上のLLMを1つのAPIに統一するAIゲートウェイ入門 — さつきのOSS研究室68 views · 1 comment
Oct 9, 2026BerriAI/litellm — The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in O — Top Github64 views
Oct 10, 2026Tired of wrestling with countless LLM APIs? Get LiteLLM. — Readme reels44 views
Sep 7, 2026LiteLLM Flaw Lets Unauthenticated Requests Reach AI Tools (CVE-2026-59822) — AISLabs AI44 views · 1 comment
Jun 28, 2026LiteLLM Flaw Can Expose Your AI Gateway Credentials (CVE-2026-42208) — AISLabs AI38 views · 1 comment
May 5, 2026⭐ litellm — 45,759 GitHub Stars — Observe AI25 views
Jul 3, 2026LiteLLM Flaw Lets Low-Privilege Users Run Host Commands (CVE-2026-42271) — AISLabs AI23 views · 1 comment
Jun 11, 2026BerriAI LiteLLM Command Injection Vulnerability — CVE-2026-42271 Exploited in the Wild #cve #cisakev — SS7 Stack Sentinel23 views
Oct 13, 2026LiteLLM Proxy on AWS: OpenAI-Compatible Gateway for Claude on Bedrock — Software Sushi - David22 views
Oct 14, 2026LiteLLM CVE-2026-59822: Patch MCP Authentication Bypass — dailytechhackglobal7 views

On Bluesky · 16

Jan 5, 2025Litellm est un projet de sdk et de proxy permettant d'adresser de nombreux services de LLM avec le format d'API OpenAI, permettant ainsi… — @ponceto91.bsky.social11 likes and reposts
Jan 4, 2025📦 BerriAI / litellm ⭐ 15,699 (+37) 🗒 Python Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock,… — @github-trending.bsky.social4 likes and reposts
Nov 26, 2024Its very similar to another package from the litellm team. They too offer a openai style standard API interface. And much more.… — @ananthan2k.bsky.social4 likes and reposts
Nov 18, 2025LiteLLM: Python SDK and Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails,… — @lcheylus.bsky.social2 likes and reposts
Apr 25, 2025📦 BerriAI / litellm ⭐ 21,346 (+86) 🗒 Python Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock,… — @github-trending.bsky.social2 likes and reposts

11 more on Bluesky

Dec 31, 2024proxy http adapter for LLMs even #huggingface to #openai json spec req/res formats, neat github.com/BerriAI/lite... — @jkone27.bsky.social2 likes and reposts
Dec 7, 2024👀 The folks at Posit seem to be throwing their hat in the ring to back a framework that standardizes LLM calls. github.com/posit-dev/ch...… — @brocktibert.com2 likes and reposts · 1 reply
Oct 9, 2026📦 BerriAI / litellm ⭐ 60,459 (+95) 🗒 Python The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or… — @github-trending.bsky.social1 likes and repost
Mar 26, 2026BerriAI/litellm Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails,… — @llms.activitypub.awakari.com.ap.brid.gy1 likes and repost
Mar 25, 2026Universal LLM API that makes switching between GPT-4, Claude, Bedrock, and 100+ other AI models as simple as changing one parameter - with… — @arifsolmaz.bsky.social1 likes and repost
May 15, 2025github.com/BerriAI/lite... — @detroitpro.bsky.social1 likes and repost
Dec 6, 2024📦 BerriAI / litellm ⭐ 14,664 (+41) 🗒 Python Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock,… — @github-trending.bsky.social1 likes and repost
Sep 4, 2024📦 BerriAI / litellm ⭐ 11,846 (+24) 🗒 Python Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure,… — @github-trending.bsky.social1 likes and repost
Apr 2, 2024Call all #LLM #APIs using the #OpenAI format. Use #Bedrock, #Azure, #OpenAI, #Cohere, #Anthropic, #Ollama, #Sagemaker, #HuggingFace,… — @michabbb.bsky.social1 likes and repost
Mar 17, 2024📦 BerriAI / litellm ⭐ 6,146 (+31) 🗒 Python Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic,… — @github-trending.bsky.social1 likes and repost
Mar 25, 2026🚀 Skyrocketing！ 🚀 (200+ new stars) 📦 BerriAI / litellm ⭐ 40,435 (+289) 🗒 Python Python SDK, Proxy Server (AI Gateway) to call 100+ LLM… — @github-trending.bsky.social0 likes and reposts · 1 reply

On Hacker News · 9

Mar 24, 2026Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised938 points · 500 comments
Mar 24, 2026Malicious litellm_init.pth in litellm 1.82.8 PyPI package – credential stealer739 points · 1 comment
Aug 12, 2023Show HN: liteLLM Proxy Server: 50+ LLM Models, Error Handling, Caching140 points · 34 comments
Jul 27, 2023Show HN: Litellm – Simple library to standardize OpenAI, Cohere, Azure LLM I/O62 points · 17 comments
Jul 24, 2025LiteLLM Python SDK Proxy Server LLM Gateway Call 100 LLM APIs in OpenAI Format5 points

4 more on Hacker News

Oct 21, 2026Litellm 1.107.0 on PYPI Compromised3 points
Sep 24, 2026Code shouldn't know which LLM provider you're using2 points
Sep 30, 2026New LiteLLM Vulnerability: Privilege Escalation to Proxy Admin and RCE1 point
Aug 16, 2023Llama2 on Replicate faster than ChatGPT?1 point · 2 comments

In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md

The file

Create a free account to mount

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free