basemind is the full context layer for this repository, served over MCP. It pre-indexes the repo into a content-addressed blob store + Fjall inverted index (and, when enabled, a LanceDB vector store) so structural, historical, and semantic questions resolve in milliseconds — without you reading wh

basemind has two equally-weighted surfaces: MCP (interactive tool calls) and CLI (scriptable commands). They share the same `.basemind/` index and are safe to run alongside each other. Reach for the CLI when you're scripting, batching queries, running in headless environments, or CI.

basemind pre-indexes the repo into a tree-sitter code map across 300+ languages. Structural questions — where a symbol lives, what calls it, what shape a file has — resolve from the index in milliseconds and return **paths, line numbers, and signatures, not file bodies**. That is a fraction of t

You may be one of several agents working this repo. On start, check `room_list` + `inbox_read` (and recent `room_history`); `room_history` / `inbox_read` return front-matter only (subject / from / id) — call `message_get` with an id for a body. Post a concise `room_post {room, subject, body, reply

Use this when basemind isn't behaving: MCP tools aren't available or return errors, the statusline says **no index**, queries come back empty when they shouldn't, or the `basemind serve` MCP server appears dead. Every step here uses the **CLI**, so it works even when the MCP server is down.

basemind extracts 90+ file formats (PDF, Office, HTML, email, images via OCR) into a LanceDB vector store and answers meaning-based queries with cross-encoder reranking. Web pages scraped or crawled into the same store are searchable the same way. This is the surface for "find the passage about X",

basemind indexes git history and resolves blame and diffs at **symbol** resolution, backed by a `gix` history index. History queries return commits, authors, paths, and line/symbol attributions — structured and capped — for a fraction of the cost of parsing `git log` / `git blame` output.

basemind answers code-map questions from an index under `.basemind/`. That index is built by `basemind scan`. This skill runs the scan via the **CLI**, so it works even when the MCP server (`basemind serve`) is not running — which is exactly the situation when basemind reports **"no index"** or **

Show a quick dashboard of basemind activity in this session: how many code-map tool calls have run, the per-tool histogram, and the estimated tokens saved vs a hypothetical grep+Read baseline. Use when the user asks "what has basemind done?", "how much is basemind helping?", "show me basemind stats", or invokes `/basemind-stats` directly.

Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.