agent-recall-mcp

Open a new project phase (milestone) in the project's narrative spine.

Condense old daily journals into weekly summaries.

List available journal entries for a project.

Context cache — store or recall pre-computed analysis results.

[MID-SESSION — safe any time; for alignment, before risky decisions] Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent. Also call BEFORE a high-risk action — publish, deploy, delete, credential exposure, external send/message, or any other irreversible write — passing `action_description` (one sentence, what you're about to do). Returns matching corrections/rules/insights plus a `verdict`: `blocked` means an authoritative correction OVERRIDES the plan — read it before proceeding.

Close the currently active project phase with the three reflection fields:

Move entries older than N days to cold archive. Keeps a one-line summary per archived entry.

Read lessons from knowledge files. Used before starting work to learn from past mistakes.

Render the project's narrative spine on demand — phase count, day span, sessions,

Surface a contradiction between the human's current input and a prior statement/decision. Helps the human clarify their own thinking.

[ENTRY — call FIRST, before acting] Use when the user asks to start, load, continue, resume, or open memory for a project. Set mode='lite' for a ≤500-token briefing (good for fresh conversations where the agent will pull memory on demand via recall()).

Full-text search across all journal entries for a project.

Add insights to the awareness system. Call at end of session.

[RETRIEVE — use freely, any time] Use when the user asks to recall, search, find, or look up previous memory, context, or decisions.

Write a structured lesson to the knowledge palace room.

Call BEFORE any non-trivial action (publish, push, deploy, schema change, file delete,

Before starting a task, recall cross-project insights that apply.

Read a journal entry. Returns the full file content for agent cold-start. Use date='latest' for the most recent entry.

Full-text search across all palace rooms. Results are ranked by room salience.

Append content to the current journal entry (creates today's file if absent).

Record what the agent understood, its confidence, and any human correction. Measures the Intelligent Distance gap.

List all project phases (milestones) in order — the project's narrative spine.

[ON SAVE/EXIT — YOU must call this; nothing auto-saves] Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session.

Save a permanent IF-THEN behavior commitment for the project. Unlike insights (semantic facts)

Return the full content of the currently active project phase, or null if none is open.

Write a memory to a palace room. Triggers fan-out: cross-references are updated in connected rooms.

Health check: find stale memories, orphan rooms (no connections), low-salience entries,

Read a room overview or specific topic from the Memory Palace.

Returns a palace-first cold-start package.

Progressive context loading for cold-start.

Save a memory — the system classifies your content and routes it to the right store

Search ALL memory stores at once — palace, journal, and insights.

Layer 1: lightweight Q&A capture. Appends to today's log file without loading the full journal.

Layer 1: structured JSON session state. Faster than markdown for cold-start.

Generate L3 semantic synthesis from recent journals and palace rooms.

List all projects tracked by agent-recall on this machine.

[MID-SESSION WRITE — single fact/decision; saying it is not saving it] Use when the user asks to remember, store, note, or save a specific decision, fact, or insight.

unfenced fixture