skills.rest
linenoize
linenoizeCOMMUNITY
Explore all skills by this author →
GitHub

neural-memory

Capture and retrieve cross-session project memory via semantic memory MCP operations.

1|Updated May 18, 2026
Search Tags:#recall#mcp#memory#ai coding#hypothesis tracking#context persistence#session bridge
One-click install
npx skills add https://github.com/linenoize/topia --skill neural-memory-linenoize
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neural-memory
Source: https://github.com/linenoize/topia/tree/main/skills/neural-memory
Command: npx skills add https://github.com/linenoize/topia --skill neural-memory-linenoize

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents valuable context from disappearing between sessions by capturing decisions, errors, patterns, and preferences into a persistent cognitive layer.

Core Features & Use Cases

  • Recall before work: Load relevant project memory at session start so planning and implementation begin with prior context instead of guesswork.
  • Capture after completion: Save learnings after builds, debugging, reviews, incidents, or ADRs so solutions and root causes compound over time.
  • Track uncertainty and health: Create hypotheses, collect evidence, verify outcomes, and run maintenance checks to keep the memory graph useful and current.
  • Use Case: A coding agent can reopen a project, recall earlier architectural choices, preserve a newly discovered bug fix, and reinforce the same pattern for future tasks.

Quick Start

Ask the skill to recall relevant project memories before you begin work, then capture the key decisions and lessons once the task is complete.

Frequently Asked Questions about neural-memory

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

FAQPage Schema
How do I persist AI coding context across sessions?▼

Cross-session project memory captures decisions, errors, patterns, and insights into a persistent cognitive layer. It uses semantic memory MCP operations to remember and recall context, maintaining continuity across AI coding workflows.

How do I track coding hypotheses and verify root causes over time?▼

Hypothesis tracking in AI coding involves creating memory entries for uncertain assumptions, collecting evidence during debugging, and verifying outcomes after fixes. This keeps the memory graph useful and current for future project work.

When should I flush or consolidate project memory before context compaction?▼

Flush or consolidate project memory before context compaction to permanently save key learnings and reduce graph size. Running maintenance health checks and consolidation operations preserves critical decisions while optimizing memory storage.

Does this cross-session memory tool require a specific MCP server setup?▼

Yes, cross-session memory requires semantic memory MCP operations for remember, recall, evidence updates, and verification. It applies to AI coding workflows using project-prefixed queries to isolate data across different projects.

What is the best way to capture bug fixes and architectural decisions for AI agents?▼

Capture bug fixes and architectural decisions by saving learnings immediately after builds, debugging, or reviews. This stores solutions and root causes in a persistent cognitive layer so they compound over time for future AI agent tasks.

Related Skills

Explore More Software Engineering Skills→
rhpdsrhpds

03-memory-mcp

Configure persistent Memory MCP knowledge graph storage for Claude Code sessions.

Official
Advanced
Heretek-AIHeretek-AI

memory-consolidation

Consolidate episodic memories into semantic storage and archive outdated data.

Official
Advanced
wallterwallter

trw-learn

Record, update, or retire learnings in TRW's memory via a learn API.

Community
Intermediate
GainInsightDevGainInsightDev

af-architecture-expertise

Create, document, and review architectural decisions using ADR methodology.

Official
Advanced