9 alternatives to FastChat

lm-sys/fastchat — An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. (39,551 stars, Apache-2.0, ai, files, integration).

These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It also serves 128 licence-cleared components from lm-sys/fastchat itself.

The alternatives in detail

• simonw/llm
  Access large language models from the command-line
  score 8.0/10 · Apache-2.0 permissive · 12,673 stars · 16 components · search them
• nousresearch/nanotron
  Minimalistic large language model 3D-parallelism training
  score 4.9/10 · Apache-2.0 permissive · 9 stars · 69 components · search them
• qwenlm/qwen
  The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
  score 4.6/10 · Apache-2.0 permissive · 22,001 stars · 33 components · search them
• nousresearch/torchtitan
  A PyTorch native library for large model training
  score 4.8/10 · BSD-3-Clause permissive · 30 stars · 254 components · search them
• mcgill-nlp/llm2vec
  Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
  score 7.6/10 · MIT permissive · 1,728 stars · 20 components · search them
• optimalscale/lmflow
  An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
  score 5.8/10 · Apache-2.0 permissive · 8,482 stars · 138 components · search them
• openlmlab/moss-rlhf
  Secrets of RLHF in Large Language Models Part I: PPO
  score 5.6/10 · Apache-2.0 permissive · 1,428 stars · 15 components · search them
• alfredfrancis/ai-chatbot-framework
  A python chatbot framework with Natural Language Understanding and Artificial Intelligence.
  score 5.3/10 · MIT permissive · 2,167 stars · 63 components · search them
• nousresearch/lm-evaluation-harness-pretraining
  A framework for few-shot evaluation of language models.
  score 4.5/10 · MIT permissive · 2 stars · 651 components · search them

Licence data: JustClaw-It's per-repo licence policy. Is FastChat still maintained? Check it. Licence details: licence checker. Ranking data from 2026-11-05T20:19:43Z.