What language is litellm written in?

litellm is written in Python: 5,630 files and 4,405,837 written lines.

What framework does litellm use?

litellm is built with Next.js, React, FastAPI, Flask, and axum.

What database does litellm use?

litellm stores its data in Redis and Postgres.

Yes. litellm uses AI through OpenAI and Anthropic.

Does litellm have tests?

Yes. litellm has 6,741 test files.

Which repos have a stack like litellm's?

The ones that share most of its stack: Significant-Gravitas/AutoGPT, lobehub/lobehub, and bojieli/ai-agent-book.

Technologies

What is litellm built with?

litellm is a Python repo built with Next.js, React, FastAPI, Flask, and axum. It stores its data in Redis and Postgres, uses AI through OpenAI and Anthropic, and uses Claude. It has 5,630 files and 4,405,837 written lines, with 6,741 test files.

Read on October 30, 2026, at commit ef9385c. Read it as markdown

Frontend

The base

litellm5,630 files

Backend

The base

Data

Services

OpenAI15 files · ui/litellm-dashboard/src/components/chat/runChatRequest.ts, line 1
Claude2 files · cookbook/anthropic_agent_sdk/agent_with_mcp.py, line 10
Anthropic1 file · ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/anthropic_messages.tsx, line 2

Other repos with a similar stack

Ordered by how much of its stack they share with litellm, then by stars.

Significant-GravitasAutoGPT
187.8k
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
8 of 10 in commonCompare →
lobehublobehub
83.6k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
6 of 10 in common · TypeScriptCompare →
bojieliai-agent-book
56.6k
《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
6 of 10 in commonCompare →
vectorize-iohindsight
56.3k
Hindsight: Agent Memory That Learns
6 of 10 in commonCompare →
langgeniusdify
159.9k
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
5 of 10 in commonCompare →
datawhalechinahello-agents
85.3k
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
5 of 10 in commonCompare →

Frequently asked questions

What language is litellm written in?: litellm is written in Python: 5,630 files and 4,405,837 written lines.
What framework does litellm use?: litellm is built with Next.js, React, FastAPI, Flask, and axum.; The proof: in package.json
What database does litellm use?: litellm stores its data in Redis and Postgres.; The proof: litellm-rust/crates/cache-redis-semantic/src/cache.rs, line 49
Does litellm use AI?: Yes. litellm uses AI through OpenAI and Anthropic.; The proof: ui/litellm-dashboard/src/components/chat/runChatRequest.ts, line 1
What services does litellm use?: litellm uses Claude.; The proof: cookbook/anthropic_agent_sdk/agent_with_mcp.py, line 10
Does litellm have tests?: Yes. litellm has 6,741 test files.
Which repos have a stack like litellm's?: The ones that share most of its stack:Significant-Gravitas/AutoGPT lobehub/lobehub bojieli/ai-agent-book

What is your repo built with?

Paste your public repo and see it drawn.

Free, no account.

Or look inside SeeRepo's own →

Is it your repo? Add its badge, keep it up to date or take it down →