Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
brain_recallA

Search the agent's long-term memory: facts, patterns, decisions, corrections, session notes, raw sources, entity relations and the Claude Code session transcripts of this folder, across SQLite, the markdown vault, Hindsight and the graph, returned as one deduplicated list ranked by relevance and recency and capped at about 6k tokens. scope='transcript' searches only what past sessions said and ran.

    Use it before answering anything about past sessions, earlier decisions or the user's
    preferences, and before brain_remember to avoid writing a duplicate. Not for health
    checks (brain_status) and not for reading a file you already know the path of.

    Read-only. Partial results are normal: `stores` lists hits per store and names any store
    that was unreachable instead of failing the call. A value a `⚠ Fact changed` banner
    superseded is returned but ranked below the banner.
brain_rememberA

Write one memory item to every store in one call, in order: markdown vault, SQLite, Hindsight, and the entity graph (relations only).

    Use it the moment the user states a fact, decision, correction, preference or
    relationship worth keeping across sessions; one call per item. Not for whole documents
    or web pages (brain_distill) and not for the end-of-session summary (brain_session).

    Never deletes. A near-duplicate fact returns `status: duplicate` with the existing entry
    and writes nothing. A changed value is appended under a `⚠ Fact changed` banner with the
    old line kept, reported as `contradiction`. `layers` reports each store as
    written|exists|pending|failed|refused, so a dead store is visible, never silent. Text
    that looks like a secret is refused.
brain_sessionA

Open or close the agent's working session. Call phase='start' once at the beginning of every conversation, before any other brain tool; call phase='end' once when the user signals they are done. Not for single facts (brain_remember).

    start returns the whole context block: the cron daily brief with a stale flag,
    executive state (objective, missions, pending decisions), the configured Hindsight
    mental models, a recall per top mission, the staged-inbox count, and `recovery` when
    the previous session never closed.

    end drains the Hindsight queue, appends a close line to today's session archive,
    replaces executive_state, session_critique and the cross-agent sync file with the
    bodies you pass (or a stub built from this session's brain_remember calls), reports
    which trait signals moved, and writes the clean-close marker. A second end overwrites
    the first.
brain_distillA

Capture an external source into the agent's immutable raw/ folder as a dated markdown file with provenance: source, title, author, published, sha256, word count. This is step 1 of /distill; compiling the knowledge page from the raw file is your job afterwards.

    Use it for a web page (defuddle with a stdlib fallback), a GitHub repo README, YouTube
    subtitles via yt-dlp, a PDF saved as bytes, a local file, or pasted text. Not for short
    facts (brain_remember).

    Fetches over the network for URLs. The same source or body a second time returns
    `status: exists` and writes nothing. A `note` flags a thin capture (JS-only or paywalled
    page) so you can read it in a browser and call again with `text`.
brain_statusA

Report the agent's health in one read-only call: reachability of every store (vault, SQLite, Hindsight, graph), knowledge-wiki lint (pages missing from _index, index links to missing pages, pages without sources, raw files never compiled), always-loaded context size in tokens per file, the last session start and close ids with an unclosed flag, the pending-decision count, and the twelve trait signals.

    Use it when a store seems down, before maintenance, or when the user asks how the
    memory is doing. Not a search (brain_recall). `ok` is false when any store is down or
    lint found issues; `stores` names the failing one.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.6/5.0

Scored across 5 tools

Disambiguation5/5

Each tool occupies a distinct slot: search (brain_recall), ingest (brain_distill), write a fact (brain_remember), session lifecycle (brain_session), and health/diagnostics (brain_status). Every description ends with an explicit 'Not for X (brain_Y)' boundary statement, so an agent has no path to confuse one with another.

Naming Consistency4/5

All five tools share a strict `brain_` prefix followed by a single lowercase token, which reads as a coherent namespace. Minor deviation: recall/remember/distill are verbs while session/status are nouns, so the pattern is prefix-consistent but not uniformly verb_noun.

Tool Count5/5

Five tools is tight and each earns its place: with the memory domain you need read, write, ingest, session boundary, and diagnostics, and nothing is redundant. brain_session reasonably bundles start/end into one phase-parameterised tool rather than splitting into two.

Completeness4/5

The read/write/ingest/lifecycle/diagnostic loop is fully closed, including partial-failure reporting and duplicate/contradiction handling. The gap is that memory is strictly append-only: there is no forget/prune/retract or explicit edit path, so a user cannot remove an obsolete item, and brain_status hints at 'maintenance' for which no tool exists.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive