Home / Open source / oumi

oumi

MCP client

oumi-ai/oumi · Enterprise stack · Enterprise

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

Verified via GitHub API

  • dpo
  • fine-tuning
  • inference
  • llama
  • llms
  • sft
  • gpt-oss
  • agentic-ai
  • gemma
  • grpo
  • llm
  • llm-as-a-judge
  • llm-evaluation
  • lora
  • pytorch
  • qwen
  • reinforcement-learning
  • synthetic-data
  • tool-calling
  • vlm

Data from GitHub API, refreshed Oct 17, 2026

Stars
9401
Forks
795
License
Apache-2.0
Language
Python
Last commit
Oct 15, 2026
Latest release
v0.9
Release date
Sep 16, 2026
Contributors
54
Open issues
0
GitHub Project website

Works with — from README

MCP
MCP client
Models
Claude, DeepSeek, Llama, Mistral, OpenAI, Qwen

Source: README.md keyword match (stated in README)

oumi FAQ

Is oumi free?

oumi is open source under the Apache-2.0 license. Hosted services and infrastructure may have separate costs.

How popular is oumi?

oumi has 9401 GitHub stars as of Oct 17, 2026.

Is there a hosted version of oumi?

A hosted alternative for oumi is unknown (—) in this data.

What does oumi work with?

From README: MCP client, Claude, DeepSeek, Llama, Mistral, OpenAI, Qwen.