RecallNest

Store a durable memory when the user shares a stable preference, identity fact, project entity, reusable pattern, or solved case that should survive future windows. Do not use this for transient task state; use it only for memory worth keeping.

Store a reusable workflow pattern as durable memory. Use this when you identify a repeatable process worth reusing across fresh windows, such as startup continuity, debugging routines, review flows, or handoff steps.

Set a prospective memory reminder that auto-triggers during future search_memory calls when the trigger keywords match. Side effect: stores a reminder entry. Use when you need a future nudge tied to a specific context.

Extract memory-worthy items from a conversation turn using lightweight heuristics (zero LLM calls). Detects preferences, identity facts, decisions, corrections, explicit memory instructions, and workflow patterns. Items that pass salience filtering are stored as durable memories. Use this when you want to analyze a block of conversation text and automatically capture any signals worth remembering.

Store a reusable case as durable memory. Use this when you identify a concrete problem-and-solution pair worth reusing across future windows, such as a debugging fix, continuity cleanup, migration lesson, or implementation recovery.

Promote an evidence memory into durable memory with an authority upgrade. Side effect: creates a new durable entry linked to the source evidence. Use when a transcript snippet or imported artifact contains a fact worth keeping across windows.

Store a compact checkpoint of the current work state. Use this when a task spans windows or terminals and you need the next session to recover decisions, open loops, and next actions without polluting durable memory.

Fetch the most recent saved checkpoint for a session or shared scope. Read-only. Use when you need to inspect current work state without running a full resume_context.

Compose startup context for a fresh window by combining durable memory, patterns, cases, and the latest checkpoint. Read-only. Use when entering a new session and you need to recover prior decisions, open loops, and next actions.

Search indexed memories by semantic similarity and return ranked results with optional temporal filtering. Read-only, but may fire stored reminders as a side effect. Use proactively at the start of tasks, when debugging, writing, or when the user references past work.

Explain why memories matched a query: retrieval path, freshness, scope, and matched terms. Read-only. Use when search results seem unexpected and you need to debug ranking or scope filtering.

Distill retrieved memories into a compact briefing with source map, key takeaways, and reusable evidence. Use this when you need a synthesized summary of stored knowledge on a topic rather than raw search results. Returns a structured briefing with citations. Read-only — does not modify stored memories.

Create a structured memory brief by retrieving and summarizing relevant memories, then persist it as a reusable asset indexed for future recall. Use this when you want to consolidate scattered knowledge on a topic into a single retrievable document. Side effect: writes a new brief asset to disk and indexes it in the vector store for future search.

Pin a retrieved memory as a high-importance reusable asset on disk. Side effect: boosts importance to 0.95, writes pin asset file, and indexes it. Use when a search result is critical and should be surfaced in future recalls.

Export a distilled memory briefing to a markdown or JSON file on disk. Side effect: writes an export artifact file. Use when you need an offline-readable snapshot of knowledge on a topic.

List recent structured memory assets (pinned memories and distilled briefs) sorted by creation date. Read-only. Use when you need an inventory of persisted knowledge artifacts — for example, before creating a new brief to avoid duplicates. Returns asset type, title, scope, creation date, and file path for each entry.

List pinned memory assets sorted by creation date, showing title, scope, importance score, and file path. Read-only. Use when you need to review high-value memories that were explicitly pinned via pin_memory, or to check if a topic already has a pinned reference before creating a new one.

Show aggregate statistics of the memory database: total entries, counts by source and category. Read-only. Use when you need an overview of memory store health or size.

Run health checks on the memory database: vector dimensions, orphans, tier distribution, and conflict backlog. Read-only. Use when diagnosing data quality issues or before a consolidation run.

Run a full memory consolidation cycle (Orient, Gather, Consolidate, Prune). Side effect: may archive low-value entries and generate insight memories. Use when memory count is high and you need periodic maintenance.

Retrieve the full or overview-level content of a single memory entry. Read-only. Use when search returned compact summaries and you need the complete text or L1 overview.

Store an executable skill with trigger conditions, implementation, and verification steps. Side effect: persists a new skill entry and indexes it. Use when you identify a reusable procedure worth automating across sessions.

Retrieve executable skills matching a task description by semantic similarity. Read-only. Use when you need a stored procedure to act on, not just recall knowledge.

List available RecallNest tools with one-line descriptions, filtered by tier. Read-only. Use when you need to discover advanced or governance tools beyond the core set.

Store multiple memories in a single call with deduplication. Side effect: persists up to 20 entries. Use when you have several facts to store at once, more efficient than repeated store_memory calls.