Skip to content
View MarcellM01's full-sized avatar
6 followers · 5 following

Achievements

Achievement: Starstruckx2Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Achievements

Achievement: Starstruckx2Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Pull SharkAchievement: YOLO

Block or report MarcellM01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MarcellM01/README.md

Hey! 👋

I build practical open-source AI infrastructure around retrieval, search, local LLMs, and agent workflows.

Current OSS projects:

  • TinySearch: lightweight web research for MCP agents
  • TinyContext: token-light memory for local LLMs and agents
  • Query Autocomplete: local typeahead/autocomplete for RAG and chat apps

I’m especially interested in local-first AI, smaller-model workflows, better retrieval, and reducing the amount of context we waste just to get useful answers.

Most of what I build is practical infrastructure: small tools that do one thing well, are easy to run, and can be used by other developers without a heavy platform around them.

Want to test, contribute, or suggest an idea?
Email me · Medium

Pinned Loading

  1. TinySearch TinySearch Public

    Shrink the web for your local LLMs!

    Python 154 8

  2. TinyContext TinyContext Public

    Context that fits your local LLMs! Token-light memory for agents.

    Python