memora

memory_absorb

Absorb new facts into memory by deduplicating, updating, and consolidating related information into richer memories.

Instructions

Intelligently absorb facts into memory with dedup and consolidation.

For each fact: searches for similar existing memories, classifies the relationship via LLM (duplicate/update/contradict/related/new), then takes the appropriate action. Related new facts are automatically consolidated into single, richer memories via LLM synthesis.

Args: facts: List of fact strings to absorb (can be granular — related ones get merged) source: Origin of facts — "manual", "session_end", "post_tool", "import" confidence: Caller's certainty about these facts (0.0-1.0, default: 0.8) context: Optional surrounding context to help disambiguate facts metadata: Optional metadata to attach to created memories tags: Optional tags to attach to created memories dry_run: If True, preview what would happen without writing anything project: Optional project these facts belong to (e.g. "clmux"). Recorded on every created memory as metadata.project and used for section and tag prefixing; suggested tags naming a different configured project are dropped. Without it, the project comes only from metadata.project or a tag naming a project configured in MEMORA_PROJECTS; it is never guessed from the text (issue #47).

Input Schema

TableJSON Schema

Name	Required	Default
`tags`	No
`facts`	Yes
`source`	No	manual
`context`	No
`dry_run`	No
`project`	No
`metadata`	No
`confidence`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.4.6Sep 24, 2026

addedInput schema / properties / project

Added value: +{
+  "default": null,
+  "title": "Project",
+  "type": "string"
+}

Addedv0.2.28May 3, 2026

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses the search/classify/consolidate workflow, dry_run behavior, and project resolution, but it does not specify what 'appropriate action' occurs for duplicates, updates, or contradictions. Whether existing memories get modified or deleted is left ambiguous, though 'dedup and consolidation' implies merging.

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?

The description is efficiently structured with a brief intro followed by an Args list. The project note is long but handles a nuanced behavior that would otherwise be unclear. No sentences are wasted, though the overall length is justified by the tool's complexity.

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

Completeness4/5

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

Given 8 parameters, no annotations, and an output schema that covers return values, the description is mostly complete. It explains the core algorithm, parameter semantics, and edge cases like project guessing. The main gap is the unspecified concrete actions for duplicate/update/contradict relationships, which is meaningful for a writing tool.

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

Parameters5/5

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

Schema description coverage is 0%, so the description fully compensates by explaining all 8 parameters: source values, confidence range/default, dry_run effect, project prefixing and tag-dropping rules, metadata/tags usage, and context disambiguation. This adds substantial meaning beyond the bare schema.

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?

The description opens with 'Intelligently absorb facts into memory with dedup and consolidation,' which states a specific verb, resource, and distinctive behavior. The detailed process of searching, classifying, and consolidating clearly differentiates it from simpler creation tools like memory_create or memory_create_batch.

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

Usage Guidelines3/5

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

The description explains what the tool does but does not explicitly state when to use it versus alternatives or when to avoid it. The mention that facts can be granular and get merged implies use cases, and the sibling list suggests memory_create_batch exists, but no direct comparison or routing guidance is provided.

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

Deploy Server