open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API,...)
// category
Models & Inference
Language models, fine-tuning and training stacks, quantization, and the runtimes that serve inference.
These are our picks, not a scrape of GitHub trending: every repo here is one we covered in Repository Radar because we thought it worth tracking. Ranked by stars, with live metrics and a get-it block on each.
21 repos in this category. Browse or filter the full archive → · Compare all categories →
// the space
21 repos, our 6th-largest category (Agents & Orchestration leads with 92). Combined they're up 64% since we covered them, 9th-fastest-growing of our 9 categories. They hold 784k stars, 5k contributors and 4M weekly downloads between them. Strength runs broad, not top-heavy: the median repo (18k stars) sits close to the 37k average. 7 are breaking out and 19 still actively shipping, and Python leads on language.
total
- 784k
- stars tracked
- #3 of 9
- +306k
- stars added since covered
- #6 of 9
- 5k
- contributors
- #4 of 9
- 4M
- weekly downloads
- #4 of 9
- 559
- commits / week
- #4 of 9
- 7
- breaking out
- #6 of 9
- 19
- still shipping
- #6 of 9
per repo
- 18k
- median stars
- #9 of 9
- +15k
- stars added / repo
- #6 of 9
- +64%
- growth since covered
- #9 of 9
- 234
- contributors / repo
- #2 of 9
- 182k
- downloads / repo
- #4 of 9
- 27
- commits / repo
- #5 of 9
- 33%
- % breaking out
- #8 of 9
- 90%
- % shipping
- #8 of 9
ggml-org/llama.cpp
LLM inference in C/C++
karpathy/autoresearch
AI agents running research on single-GPU nanochat training automatically
hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
unslothai/unsloth
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
karpathy/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
janhq/jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
AlexsJones/llmfit
Hundreds of models & providers. One command to find what runs on your hardware.
toon-format/toon
🎒 Token-Oriented Object Notation (TOON), compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
allenai/olmocr
Toolkit for linearizing PDFs for LLM datasets/training
google/magika
Fast and accurate AI powered file content types detection
confident-ai/deepeval
The LLM Evaluation Framework
tensorzero/tensorzero
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
ostris/ai-toolkit
The ultimate training toolkit for finetuning diffusion models
skypilot-org/skypilot
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
oumi-ai/oumi
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!
flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
deepseek-ai/smallpond
A lightweight data processing framework built on DuckDB and 3FS.
huggingface/nanoVLM
The simplest, fastest repository for training/finetuning small-sized VLMs.
thinking-machines-lab/tinker-cookbook
Post-training with Tinker
mohsen1/yek
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption