distill-memory

Propose durable knowledge candidates for operator-approved inclusion in the knowledge corpus.

Updated Jun 21, 2026

Search Tags:#memory management #knowledge capture #operator approval #knowledge storage #fact validation

Ready to run

npx skills add https://github.com/apexradius/agentic-os --skill distill-memory-apexradius

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: distill-memory
Source: https://github.com/apexradius/agentic-os/tree/main/skills/distill-memory
Command: npx skills add https://github.com/apexradius/agentic-os --skill distill-memory-apexradius

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Ensures that only verifiable, durable facts, lessons, and preferences are captured as knowledge, reducing errors and improving accuracy in long-term knowledge storage.

Core Features & Use Cases

Durable Knowledge Capture: Captures facts, lessons, and preferences that persist across sessions.
Operator Approval: Ensures only knowledge approved by the operator is added to the knowledge corpus.
Layer Classification: Classifies knowledge into the appropriate memory layer to maintain accuracy.
Provenance and Freshness: Tags each piece of knowledge with its origin and recency.
Avoids Duplicate and In-flight State: Prevents the duplication of knowledge and the inclusion of transient state.

Quick Start

At the end of a session, use the distill-memory skill to propose a new fact for inclusion in the knowledge corpus.

Frequently Asked Questions about distill-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I capture durable knowledge from a session for long-term storage?▼

To capture durable knowledge, you can propose facts, lessons, or preferences for inclusion in the knowledge corpus. The system ensures they are sourced, classified into the appropriate memory layer, and tagged with provenance and freshness before storage.

What is the best way to prevent transient state from polluting my knowledge corpus?▼

Preventing transient state requires a validation process that proposes only durable knowledge candidates. The system avoids in-flight state and waits for operator approval before final inclusion, ensuring only verifiable facts are stored.

How does operator approval work for knowledge capture?▼

Operator approval works by requiring human confirmation before any proposed knowledge is added to the corpus. The system classifies candidates into memory, lessons, or user models, records their origin, and pauses for operator validation.

Can I classify captured knowledge into different memory layers?▼

Yes, you can classify captured knowledge into different memory layers. The system categorizes proposed knowledge specifically into memory, lessons, or user model layers to maintain accuracy and appropriate context.

Why does my knowledge storage need provenance and freshness tags?▼

Knowledge storage needs provenance and freshness tags to ensure long-term accuracy and verifiability. Tagging each piece of knowledge with its origin and recency helps maintain a reliable, durable knowledge corpus across sessions.

How do I avoid duplicating facts when adding to a knowledge corpus?▼

To avoid duplicating facts, the knowledge capture process evaluates proposed candidates against existing entries. It prevents duplication by validating durability and sourcing before submitting the knowledge for operator approval.