LinkLore

MCP server for project memory — lets AI agents record decisions, pitfalls, and specs as they work, and recall them next session with code context attached.

Built for agents, not humans: every tool here is designed for usability by an AI, not readability for a person.

Every new session, an AI agent starts from zero — decisions get re-litigated, pitfalls get rediscovered, and "why is it done this way?" gets answered by guessing. Markdown notes don't fix this: they're written for people, they drift from the code, and no agent reads them reliably.

LinkLore is structured memory that the agent itself reads and writes through MCP tools:

- Two record types—lore(decisions, pitfalls, journal) anddoc(specs, plans), bidirectionally linked to each other and to code files.
- Local-first— everything lives in a.linklore/SQLite store inside your project. No account needed to start.
- Code context— records link to source files; git-diff-based stale detection flags memory that the code has outrun.
- Cheap recall— query by meaning, tag, file, status, or period; a session-startbrief()returns open items and hotspots in a few hundred tokens.

Runs straight from PyPI — no install or clone (uvx llre).

Any other MCP client(Cursor, Codex, Windsurf, …) — add to the project's MCP config (e.g..mcp.json):

{ "mcpServers": { "llre": { "command": "uvx", "args": ["llre"] } } }

Then initialize, once, in the project root:

Or let your agent do all of it— this is a server meant to be set up by an AI agent rather than typed in by hand. Paste this as your first message to Claude Code, Cursor, Codex, or any other MCP-capable agent:

Set up LinkLore (an MCP server for project memory) in this repo. It's the PyPI packagellre, run viauvx llre— no install or clone needed. Register it as an MCP server for whichever client you are (Claude Code:claude mcp add llre -- uvx llre; otherwise add{"mcpServers": {"llre": {"command": "uvx", "args": ["llre"]}}}to this project's.mcp.json), then runuvx llre inithere. Ask me first before runninguvx llre login— it opens a browser for Google login and is only needed for personal backup or team sharing.

How an agent actually uses it, in order:

start a session → brief() open items, recent activity, hotspots about to touch code → show(file=..., query=…) decisions & pitfalls tied to that area decided / got burned → add(type='lore', …) record it, linked to the files involved spec or plan → add(type='doc', …) instead of a standalone .md something changed → edit(id=..., …) append, replace a section, or supersede memory getting messy → doctor() · cleanup() integrity check, duplicate detection back up / share → push() · openbox(…) your server space · invite-only shared boxes

23 tools. Call any of them withhelp=Truefor full usage.

The full guide shipsinside the product, as lore— LinkLore documents itself with itself. Afterinit(), your project carries it as a read-only source:

It updates with the package: upgradellreandbrief()tells you what changed.

- mcp/— the readable portion of the MCP server source (PyPI:llre)
- plugin/— Claude Code plugin wrapper

DOI:10.5281/zenodo.21216858· citation:CITATION.cff

Elastic License 2.0. Free to install and use; you may not provide the software as a competing managed service, circumvent license-key functionality, or remove licensing notices.

Team sync, cross-project sharing, and cloud backup are provided by the backend service atlinklore.io(not part of this repository).

Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.