DEDUPED Hot AI repos, turned into use cases Get the Monday 5
100 stars · Python

How to use Loci: what you can do with it

loci is a Python tool that builds a local searchable knowledge base from notes and project docs, answers questions with file and section citations, and shares memory across AI tools through MCP and HTTP.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Search and ask questions across your own notes

    Index a notes folder, then get search hits and cited answers from the terminal.

    View prompt
    Using the IvenKooLab/loci repo, configure config.toml so [[sources]].path points to <notes-directory>, run loci ingest, then run loci ask with the question <question>. Expected output: an answer with file > section citations. Verify that each citation names a file that exists under <notes-directory>.

  • Share one memory store across MCP-connected AI tools

    Point several MCP clients at one LOCI_HOME so they read and write the same memories.

    View prompt
    Using the IvenKooLab/loci repo, add a loci entry to the MCP config of <client-name> with LOCI_HOME set to <absolute-instance-path>. Expected output: the client lists brain_search and brain_remember tools. Verify that a memory stored by one client is returned by brain_search in a second client.

  • Review what each coding agent remembers in a web console

    Discover agent memories on your machine and browse them in the built-in Web console.

    View prompt
    Using the IvenKooLab/loci repo, run loci harness in the instance at <instance-path> and then start loci serve-http. Expected output: a list of detected agent memories and a reachable console at 127.0.0.1:8765/ui. Verify that the console shows the same memory count as the loci harness output.

  • Keep notes indexed and check answers before you rely on them

    Watch changing files, save quick memories, and ask questions with claim verification.

    View prompt
    Using the IvenKooLab/loci repo, run loci watch in <instance-path>, then save a memory with loci remember and ask <question> using loci ask with --verify. Expected output: a cited answer with verification results. Verify that the memory saved with loci remember appears in loci search results filtered by --tag memory.

Quick start with Loci

  1. Check you have what it needs: Python 3.11 or newer; git and a terminal; An embedding endpoint that supports /embeddings, plus a chat endpoint (may be a local one).
  2. Open IvenKooLab/loci on GitHub and read the README and license.
  3. Run git clone https://github.com/IvenKooLab/loci.git and then cd loci.
  4. Run python -m pip install -e . and then cp config.example.toml config.toml.
  5. Edit config.toml: fill in [llm] and [embed], and set [[sources]].path to your notes directory.
  6. Run loci ingest to build the index.

These steps come from our top use case, Search and ask questions across your own notes, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for IvenKooLab/loci

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Loci alternatives · Best AI repos for Research

About this repo

  • Who it is forDevelopers and power users who keep notes or project docs in Markdown and use AI coding tools that support MCP.
  • Why it is hot100 stars, launched 51 days ago
  • LanguagePython
  • Sourcegithub.com/IvenKooLab/loci · Back to Hot repos

Requirements

  • Python 3.11 or newer
  • git and a terminal
  • An embedding endpoint that supports /embeddings, plus a chat endpoint (may be a local one)
  • A notes or project docs directory to index

Add this badge to your README

Maintain Loci? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/IvenKooLab/loci.svg)](https://dedupedai.com/use-cases/ivenkoolab-loci/?utm_source=github&utm_medium=badge&utm_campaign=IvenKooLab-loci)

HTML 

<a href="https://dedupedai.com/use-cases/ivenkoolab-loci/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=IvenKooLab-loci"><img src="https://dedupedai.com/badge/IvenKooLab/loci.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Loci

What is Loci?

loci is a Python tool that builds a local searchable knowledge base from notes and project docs, answers questions with file and section citations, and shares memory across AI tools through MCP and HTTP. It is an open-source project on GitHub: https://github.com/IvenKooLab/loci.

Who is Loci for?

Developers and power users who keep notes or project docs in Markdown and use AI coding tools that support MCP.

What can I do with Loci?

4 use cases so far, for example: Search and ask questions across your own notes; Share one memory store across MCP-connected AI tools; Review what each coding agent remembers in a web console. Each has steps and a copy-paste agent prompt.

What do I need to run Loci?

Python 3.11 or newer; git and a terminal; An embedding endpoint that supports /embeddings, plus a chat endpoint (may be a local one); A notes or project docs directory to index.

What are alternatives to Loci?

Other hot AI repos in Research: Trustworthy Agent Simulation, Kaas, By2 KB, Md2 HD, LT2 MD.

Is Loci safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.