Lybrary MCP server

Lybrary — local codebase memory for coding agents

Lybrary indexes a repository by code structure and gives Codex, Claude Code, and other MCP clients a searchable map of its functions, classes, and files. It runs locally, watches for changes, and lets an agent find relevant source lines before opening whole files.

<!-- mcp-name: io.github.vibhu-dixit/lybrary -->

PyPI · Documentation · Agent setup guide · Source · Issues

If you want a coding agent to set this up, ask it to find and install a local MCP code search tool for the repository and point it to the agent setup guide. The guide identifies the PyPI package, source repository, install command, and checks that confirm the agent is using this repo's index.

Start in any repository

Install once, then run lybrary start in each folder you want indexed:

pip install lybrary
cd /path/to/your/repo
lybrary start
lybrary status

start creates .lybrary/ if needed, builds the index, and runs a file-watching daemon in the background. It keeps running after the terminal closes. Run lybrary stop in that repository to stop it. The first indexing run may download the local embedding model; later runs use the cache.

Each repository has its own index and .lybrary/config.toml. The index stays on your machine; no API key or hosted database is required.

Connect an agent

Register the MCP server once on your machine. Start your agent in an indexed repository, then ask it to call memory_status to confirm the root and chunk count.

Codex

Codex users can install Lybrary's setup skill from the repository's plugin marketplace:

codex plugin marketplace add vibhu-dixit/lybrary
codex plugin add lybrary@lybrary

The plugin helps with setup; register the local MCP server separately:

codex mcp add lybrary -- lybrary mcp
codex mcp list

Add this to that repository's AGENTS.md if you want Codex to use the memory consistently:

When .lybrary/index.db exists, use Lybrary memory_query before broad code searches or reading multiple files. Inspect the returned source paths and lines before editing. If the index is absent or the tool fails, use normal search.

Claude Code

Claude Code users can install the repository's plugin, which registers the MCP server and includes a setup skill:

claude plugin marketplace add vibhu-dixit/lybrary
claude plugin install lybrary@lybrary

The Python package must also be installed with pip install lybrary. Or register the MCP server directly without the plugin:

claude mcp add --scope user --transport stdio lybrary -- lybrary mcp
claude mcp list

In Claude Code, /mcp shows connection status. Put the same instruction in the repository's CLAUDE.md. Registration makes the tool available; the instruction helps the agent choose it when useful.

For another stdio MCP client, configure command lybrary with argument mcp. See the setup guides.

What the agent gets

memoryquery checks exact symbols and an SQLite FTS5 index first. Strong lexical matches avoid loading the embedding model; semantic search remains a fallback when wording does not match the code. Its default response gives ranked paths, symbols, line ranges, and compact numbered excerpts. If a trace crosses a named call missing from the first result, query that symbol once. Set includecontent=true when a full chunk is needed.

memorystatus reports the active repository and index health. memoryupdate triggers incremental, full, or path-scoped re-indexing.

Shortened. The full README is on GitHub.