Skip to main content
Glama
vbcherepanov

total-agent-memory

by vbcherepanov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_recall

Read-onlyIdempotent

Search all past sessions for decisions, solutions, facts, and lessons to retrieve relevant context before starting a task.

Instructions

Search ALL memory: decisions, solutions, facts, lessons from ALL past sessions. 6-stage pipeline: FTS5+BM25 → semantic → fuzzy → graph → (optional) CrossEncoder → (optional) MMR. Default: hybrid mode (BM25 + semantic + RRF). Use BEFORE starting any task. v11.0: routes to fast hot path when MEMORY_MODE=fast (default). Use memory_search_fast / memory_explain_search for explicit fast routing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoProgressive-disclosure mode: 'search' (default) = normal results, 'index' = ultra-compact metadata only (id+title+score+type+project+created_at, ~40-60 tok/hit, no cognitive expansion, use memory_get(ids=...) to fetch full content), 'timeline' = chronological compact view; 'context' = source excerpts; 'evidence' = indexed passage search with bounded follow-up retrievalsearch
typeNoall
limitNo
queryYesWhat to search for
branchNoFilter by git branch (also includes branch-agnostic records)
detailNoLevel of detail: 'compact' ~50 tokens/result (id+title+score), 'summary' truncates content to 150 chars, 'full' returns everything, 'auto' picks based on query complexity (paths/urls/code → full, short → compact). Ignored when mode!='search'.full
fusionNoScore fusion method: 'rrf' = Reciprocal Rank Fusion (better multi-tier ranking), 'legacy' = original additive scoringrrf
intentNoFilter by classified intent (question|procedural|fact|decision|problem|solution|incident|plan)
rerankNoEnable CrossEncoder re-ranking for higher precision (adds ~30ms latency)
topicsNoFilter results to records tagged with any of these topics (from deep enrichment)
diverseNoEnable MMR diversity to reduce redundant results (useful for broad queries)
projectNoFilter by project name
entitiesNoFilter by extracted entity names (technology/person/project, case-insensitive)
neighborsNoTimeline/context modes: records before/after each hit; context accepts 0–3.
fill_budgetNoContext mode: search deeper (up to 100 hits) and keep whole hits in rank order until context_max_chars is used, instead of excerpting the top `limit` hits to fit. Neighbours default to 0 here; pass `neighbors` to keep each hit with the records around it.
expand_budgetNoMax number of additional records to include via graph expansion
decisions_onlyNoReturn only structured decisions (v8.0): type=decision AND tags contain 'structured'. Results include parsed schema payload under 'decision'.
expand_contextNoAdd graph-related records (1-hop neighbors via knowledge graph) as 'expansion' results
missing_relationNoEvidence mode: missing relation; subject must occur in the original question.
context_max_charsNoContext character budget; evidence mode uses the same value as a stricter UTF-8 byte budget.
evidence_followupNoEvidence mode: allow one search for an explicitly supplied missing_relation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv14.7.0
    • addedInput schema / properties / fill_budget
      Added value: +{
+  "default": false,
+  "description": "Context mode: search deeper (up to 100 hits) and keep whole hits in rank order until context_max_chars is used, instead of excerpting the top `limit` hits to fit. Neighbours default to 0 here; pass `neighbors` to keep each hit with the records around it.",
+  "type": "boolean"
+}
  2. Changed6 schema fields changedv14.0.0
    • addedInput schema / properties / context_max_chars
      Added value: +{
+  "default": 24000,
+  "description": "Context character budget; evidence mode uses the same value as a stricter UTF-8 byte budget.",
+  "minimum": 512,
+  "type": "integer"
+}
    • addedInput schema / properties / evidence_followup
      Added value: +{
+  "default": true,
+  "description": "Evidence mode: allow one search for an explicitly supplied missing_relation.",
+  "type": "boolean"
+}
    • addedInput schema / properties / missing_relation
      Added value: +{
+  "additionalProperties": false,
+  "description": "Evidence mode: missing relation; subject must occur in the original question.",
+  "properties": {
+    "relation": {
+      "type": "string"
+    },
+    "subject": {
+      "type": "string"
+    },
+    "time": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "subject",
+    "relation"
+  ],
+  "type": "object"
+}
    • changedInput schema / properties / mode / description
      Previous value: -"Progressive-disclosure mode: 'search' (default) = normal results, 'index' = ultra-compact metadata only (id+title+score+type+project+created_at, ~40-60 tok/hit, no cognitive expansion, use memory_get(ids=...) to fetch full content), 'timeline' = top-K hits expanded with ±neighbors from same session (chronological)"New value: +"Progressive-disclosure mode: 'search' (default) = normal results, 'index' = ultra-compact metadata only (id+title+score+type+project+created_at, ~40-60 tok/hit, no cognitive expansion, use memory_get(ids=...) to fetch full content), 'timeline' = chronological compact view; 'context' = source excerpts; 'evidence' = indexed passage search with bounded follow-up retrieval"
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "search",
-  "index",
-  "timeline"
-]New value: +[
+  "search",
+  "index",
+  "timeline",
+  "context",
+  "evidence"
+]
    • changedInput schema / properties / neighbors / description
      Previous value: -"Timeline mode only: how many records before/after each hit to include."New value: +"Timeline/context modes: records before/after each hit; context accepts 0–3."
  3. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the 6-stage pipeline, the default hybrid mode (BM25 + semantic + RRF), and the MEMORY_MODE=fast hot-path routing behavior. It stops short of describing result volume or latency trade-offs of the optional stages.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with scope and the imperative use case, then pipeline details and routing. Five sentences is dense but each carries information; minor redundancy in listing pipeline stages that the mode parameters also imply.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 21-parameter, no-output-schema tool, the description supplies the search scope, default behavior, routing rules, and sibling alternatives that an agent needs to call it correctly. Return-shape specifics are delegated to the mode parameter's own enum documentation, which is appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 90%, so the baseline is 3; the description adds meaning on top by explaining the default hybrid fusion mode and the environment-driven fast-path routing, which are not encoded in the schema. It doesn't walk through individual parameters, but the schema already does that thoroughly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource scope (ALL memory: decisions, solutions, facts, lessons from ALL past sessions), and explicitly distinguishes itself from siblings by naming memory_search_fast and memory_explain_search. An agent can tell it apart from the fast-path tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear imperative ('Use BEFORE starting any task') and names the alternative tools for explicit fast routing when MEMORY_MODE=fast. However, it does not state when NOT to use this tool (e.g. narrow lookups better served by memory_get or memory_search_by_tag), leaving some routing decisions to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools