timorunge

timorunge / lore

Public

Local knowledge base for 90+ document formats. CLI search + MCP server. No cloud, no API keys.

10
0
100% credibility
Found May 07, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

Lore is a local-first knowledge base that ingests documents from files, websites, git repos, and more into a searchable index accessible from the terminal or AI agents via MCP.

How It Works

1
🔍 Discover Lore

You hear about Lore, a simple tool that lets you search all your documents like man pages, right from your terminal.

2
📥 Get Lore

Download and install it easily with one command, no complicated setup needed.

3
📁 Open Your Project

Go to your folder with docs, notes, or code, and run a quick setup command.

4
Lore Finds Your Stuff

It automatically spots your documents, READMEs, and folders, creating a personal search setup just for you.

5
Build Your Search Base

Hit one button to gather and organize everything into a fast searchable collection.

6
🔎 Search Instantly

Type what you need, and get exact matches from your docs without opening files or browsers.

🎉 AI Gets Your Context

Share your knowledge base with AI helpers so they understand your project perfectly, no more repeating yourself.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is lore?

Lore is a Rust-built local knowledge base that ingests documents from 90+ formats—PDFs, Markdown, emails, git repos (local github repository), websites, YouTube transcripts, S3 buckets, and more—then indexes them for full-text CLI search or MCP server access. It solves the local knowledge problem by turning scattered project docs, vendor references, or team notes into a searchable "man page" alternative, all without cloud services or API keys. Run `lore init`, `lore ingest`, and `lore search` to get offline access or feed context to AI agents via MCP.

Why is it gaining traction?

In a world of cloud RAG tools, lore stands out as a single-binary local github copilot alternative: no embeddings, no vendors, just fast BM25 search over your book lore github or internal wikis. MCP integration lets Claude or Cursor query your project context directly, like a local github actions runner for knowledge. Devs dig the incremental updates, federation across configs, and zero-infra setup—perfect for local knowledge case study without lock-in.

Who should use this?

Backend devs indexing ADRs and runbooks for AI-assisted debugging; teams building shared local knowledge bases from git repos (local github server vibe); or docs-heavy roles needing offline search across PDFs and emails. Ideal for frontend teams tired of browser-hopping API refs, or anyone running local knowledge badge scouts-style audits on project lore.

Verdict

Promising early project (10 stars, 1.0% credibility score) with excellent docs, benchmarks, and fuzzing—try the Gutenberg example out-of-box. Maturity lags (low adoption), so test on non-critical local knowledge synonym needs before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.