oumi

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

oumi-ai/oumi

View on GitHub ↗

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

oumi grew +0.4% in the last 30 days, ranks 13th of 825 in Evaluation & Guardrails, actively maintained, last commit today.

Star trajectory

142 days tracked
2026-06-219.4k stars today2026-11-12
Momentum

+0.4% in 30d, below the Evaluation & Guardrails median of +1.3%.

Maintenance

Last commit today, fresher than the median of 12d.

How it compares in Evaluation & Guardrails

oumi
9.4k
stars
+0.4% 30d
commit today
Evaluation & Guardrails median
237
stars
+1.3% 30d
commit ~12d ago
Leader · impeccable
108.5k
stars
+0.0% 30d
commit today

Ranked 13th of 825 by stars.

Ranked by shared tags, then keywords, then stars

Where oumi sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating…

    +2 (+0.1%) in 30d · Committed 821d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails

  2. OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    +222 (+25%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails

  3. The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and…

    +12 (+1.1%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails

  4. Framework for enhancing LLMs for RAG tasks using fine-tuning.

    -1 (-0.1%) in 30d · Committed 27d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails

  5. The platform for continuously improving AI agents.

    +107 (+16%) in 30d · Committed today · Python · AGPL-3.0

    Shares Evaluation & Guardrails

  6. [ICLR 2025 Spotlight] An open-sourced LLM judge for evaluating LLM-generated answers.

    +0 (+0.0%) in 30d · Committed 638d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails

  7. Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding…

    -2 (-0.5%) in 30d · Committed 1,075d ago · Jupyter Notebook · Apache-2.0

    Shares Evaluation & Guardrails

  8. Official code for Agent-Reflex: Teaching Language Agents to Act Reflectively

    Committed 23d ago · Python · MIT

    Shares Evaluation & Guardrails

  9. Autonomous Qwen3-VL training-code research on the official DocVQA benchmark. main: NVIDIA multi-GPU, mlx…

    +0 (+0.0%) in 30d · Committed 12d ago · Python · MIT

    Shares Evaluation & Guardrails

  10. RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning

    +6 (+3.5%) in 30d · Committed 14d ago · JavaScript · Apache-2.0

    Shares Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
63
Forks
798
Watchers
61
Open issues
1
Releases
27
Created
2024-05-07
Stars this week
+6

You've seen where oumi stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain oumi?

Claim this page to add your own call-to-action.

Claim this page