Refolk

Top Python LLM repositories on GitHub

Large language model frameworks, agents, runtimes, and inference servers. Filtered to projects whose primary language is Python.

Ranked by stars across 4,700 Python repositories tagged llm. Refreshed daily.

  1. 1
    NousResearch/hermes-agent246,991 · ⑂ 51,830

    The agent that grows with you

    • ai
    • ai-agent
    • ai-agents
    • llm
    • anthropic
    • chatgpt
  2. 2
    Significant-Gravitas/AutoGPT187,441 · ⑂ 46,006

    AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

    • ai
    • openai
    • python
    • artificial-intelligence
    • autonomous-agents
    • llama-api
  3. 3
    huggingface/transformers166,317 · ⑂ 34,627

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

    • nlp
    • natural-language-processing
    • pytorch
    • pytorch-transformers
    • transformer
    • model-hub
  4. 4
    open-webui/open-webui152,520 · ⑂ 22,315

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

    • ollama
    • ollama-webui
    • llm
    • webui
    • self-hosted
    • llm-ui
  5. Live search

    Find the people behind these repos

    Stars rank the projects. I can rank the engineers - maintainers, top contributors, and the people they work with. Fire one of these to see how it works.

    500 free credits on sign-up, no card needed.

  6. 5
    langchain-ai/langchain146,641 · ⑂ 24,522

    The agent engineering platform.

    • ai
    • anthropic
    • gemini
    • langchain
    • llm
    • openai
  7. 6
    harry0703/MoneyPrinterTurbo124,638 · ⑂ 19,307

    利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

    • python
    • tiktok
    • ai-video-generator
    • content-creation
    • ffmpeg
    • instagram-reels
  8. 7
    Graphify-Labs/graphify119,461 · ⑂ 11,550

    Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

    • claude-code
    • graphrag
    • knowledge-graph
    • codex
    • openclaw
    • skills
  9. 8
    browser-use/browser-use115,226 · ⑂ 12,683

    Agents that use the browser.

    • llm
    • ai-agents
    • ai-tools
    • browser-automation
    • python
    • browser-use
  10. 9
    TauricResearch/TradingAgents107,531 · ⑂ 20,569

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    • agent
    • finance
    • llm
    • multiagent
    • trading
  11. 10
    vllm-project/vllm92,143 · ⑂ 22,402

    A high-throughput and memory-efficient inference and serving engine for LLMs

    • gpt
    • llm
    • pytorch
    • model-serving
    • transformer
    • llm-serving
  12. Live search

    Who is hiring in this space?

    I read hiring signals across LinkedIn, GitHub, and the open web - so a topic list becomes a warm outreach list. Try one live.

    500 free credits on sign-up, no card needed.

  13. 11
    bytedance/deer-flow82,673 · ⑂ 11,415

    An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

    • agent
    • agentic
    • agentic-framework
    • agentic-workflow
    • ai
    • ai-agents
  14. 12
    datawhalechina/hello-agents79,837 · ⑂ 9,926

    📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

    • agent
    • tutorial
    • llm
    • rag
  15. 13
    shareAI-lab/learn-claude-code77,161 · ⑂ 12,407

    Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

    • agent
    • claude-code
    • teaching
    • agent-development
    • ai-agent
    • claude
  16. 14
    unslothai/unsloth76,407 · ⑂ 6,974

    Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

    • fine-tuning
    • llama
    • llms
    • gemma
    • unsloth
    • llm
  17. 15
    hiyouga/LlamaFactory74,870 · ⑂ 9,172

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    • fine-tuning
    • llama
    • llm
    • peft
    • transformers
    • rlhf
  18. 16
    headroomlabs-ai/headroom72,999 · ⑂ 5,611

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    • agent
    • ai
    • anthropic
    • compression
    • context-engineering
    • context-window
  19. Live search

    Turn any brief into a list like this

    I run natural-language searches across GitHub, LinkedIn, and the open web. Describe who you want and I'll build the shortlist.

    500 free credits on sign-up, no card needed.

  20. 17
    FoundationAgents/MetaGPT70,495 · ⑂ 8,961

    🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

    • agent
    • gpt
    • llm
    • metagpt
    • multi-agent
  21. 18
    mem0ai/mem065,624 · ⑂ 7,700

    The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

    • ai
    • chatgpt
    • llm
    • python
    • rag
    • long-term-memory
  22. 19
    ZhuLinsen/daily_stock_analysis65,273 · ⑂ 54,603

    LLM 驱动的多市场股票智能分析系统:多源行情、实时新闻、决策看板与自动推送,支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.

    • aigc
    • llm
    • quant
    • quantitative-trading
    • a-stock
    • ai-agent

Find Python engineers shipping LLM

The list above ranks the most-starred public Python repositories tagged with the LLM topic, drawn from the public GitHub graph. Across 4,700 matching repositories, the contributors are a tight cluster of engineers with both Python chops and real LLM experience.

That overlap is rare. Most Python engineers haven’t shipped LLM, and most LLM maintainers don’t write Python. The people on this list’s contributor graph are the ones who do both.

Refolk turns this list into a search. Ask for Python LLM maintainers hiring” or Python engineers shipping LLM in 2025” and Refolk returns a ranked shortlist with the commits, profiles, and projects behind each name.

How this list is built

Refolk searched GitHub for public Python repositories tagged with the LLM topic, ranked them by stargazer count, and kept those with at least 25 stars. The list refreshes once a day.

Last refreshed: Sat, 19 Sep 2026 08:19:54 GMT

Search this list

Need a more specific search?

Refolk runs natural-language searches across GitHub, LinkedIn, and the open web. Try one of these:

500 free credits on sign-up, no card needed.

Related lists

See all repository lists.

Or zoom out

Common questions

How are these repositories ranked?

By stars, with forks and recent activity as tiebreakers, read from the public GitHub API. The methodology section above has the details.

How fresh is the data?

The ranking re-renders at least daily. Last refreshed: Sat, 19 Sep 2026 08:19:54 GMT.

Can I find the maintainers and contributors behind these repos?

Yes. Stars rank the projects; I can rank the engineers - maintainers, top contributors, and the people they work with. You start with 500 free credits, no card required.

Can I use this list for hiring?

That's the point. I read hiring signals across GitHub, LinkedIn, and the open web, so a repo list turns into a shortlist of engineers worth talking to.

Try it on the search you came here for

Stop building boolean strings. Just describe the person.

Type one sentence. I plan the search, read GitHub, public LinkedIn and Crunchbase records, and the open web as it is right now, and hand back a ranked list with the reason next to every name.

  1. 01Describe them

    One plain sentence. Role, city, stack, stage, whatever matters to you.

  2. 02I read the web live

    GitHub, public LinkedIn and Crunchbase records, the open web. Not a database that went stale last quarter.

  3. 03You read the shortlist

    Ranked, with the reasoning under every name. Open a profile, ask a follow-up, narrow it down.

  • No boolean, no filters, no seat to buy. One box.
  • Read at search time, so a profile updated yesterday counts today.
  • Every step visible as it runs, every name with its reason.

500 free credits on sign-up. No card, no demo call. See real searches.

Keep exploring