Soup alternatives

MakazhanAlpamys/Soup (8.9k stars, +392 this week): Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. Why it matters: useful plumbing for shipping LLM-powered features.

Below are 12 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics with Soup, ordered by how many topics overlap, then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

1. 1. hiyouga/LlamaFactory

   +70/wkest.

   Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). Why it matters: useful plumbing for shipping LLM-powered features.

   75k stars · Python · shared topics: fine-tuning, llm, lora, peft, qlora, transformers

2. 2. rohitg00/ai-engineering-from-scratch

   +1.1k/wkest.

   Learn AI Engineering! Learn it. Build it. Ship it for others. Why it matters: useful plumbing for shipping LLM-powered features.

   69k stars · Python · shared topics: llm, machine-learning, python, transformers

3. 3. huggingface/transformers

   +112/wkest.

   🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models… Why it matters: useful plumbing for shipping LLM-powered features.

   168k stars · Python · shared topics: llm, machine-learning, python, pytorch

4. 4. lyogavin/airllm

   +1.4k/wkest.

   AirLLM 2.8T LLM inference with single 4GB GPU. Why it matters: useful plumbing for shipping LLM-powered features.

   38k stars · Jupyter Notebook · shared topics: llm, lora, qlora

5. 5. unslothai/unsloth

   +119/wkest.

   Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Why it matters: useful plumbing for shipping LLM-powered features.

   78k stars · Python · shared topics: fine-tuning, llm, python

6. 6. mw00/project-maya

   +732/wkest.

   Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Why it matters: useful plumbing for shipping LLM-powered features.

   767 stars · C++ · shared topics: llm, local-llm

7. 7. Tencent/WeKnora

   +679/wkest.

   Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. Why it matters: useful plumbing for shipping LLM-powered features.

   34k stars · Go · shared topics: llm, ollama

8. 8. harry0703/MoneyPrinterTurbo

   +602/wkest.

   Generate HD short videos from a topic or keyword with an automated AI workflow. Why it matters: useful plumbing for shipping LLM-powered features.

   131k stars · Python · shared topics: llm, python

9. 9. BlenderGPT3D/blender-ai-addon

   +581/wkest.

   Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code. Why it matters: useful plumbing for shipping LLM-powered features.

   211 stars · Python · shared topics: llm, python

10. 10. headroomlabs-ai/headroom

    +315/wkest.

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. Why it matters: useful plumbing for shipping LLM-powered features.

    75k stars · Python · shared topics: llm, python

11. 11. can1357/oh-my-pi

    +266/wkest.

    ⌥ Coding agent with the IDE wired in. Built by Stencil Labs. Why it matters: useful plumbing for shipping LLM-powered features.

    35k stars · TypeScript · shared topics: cli, llm

12. 12. rtk-ai/rtk

    +252/wkest.

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies. Why it matters: useful plumbing for shipping LLM-powered features.

    83k stars · Rust · shared topics: cli, llm

More: all trending LLM tooling repos · compare Soup with the top 2