synapse

Store and recall structured memories with JSON Schema validation and keyword search.

Updated Feb 23, 2026
One-click install
npx skills add https://github.com/aromancev/synapse --skill synapse-aromancev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: synapse
Source: https://github.com/aromancev/synapse/tree/main
Command: npx skills add https://github.com/aromancev/synapse --skill synapse-aromancev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Synapse solves the challenge of reliably storing, validating, and retrieving structured memories for AI agents so they do not forget context, repeat mistakes, or lose associative links between items. It prevents unstructured note sprawl, reduces token waste by returning compact JSON read models, and enables reproducible rebuilds via an append-only event log.

Core Features & Use Cases

  • JSON Schema-driven storage: Define runtime JSON schemas to validate node payloads and keep stored memories consistent.
  • Nodes and Links graph: Create typed nodes, attach keywords, and connect nodes with bidirectional links for fast contextual expansion.
  • Event sourcing + projections: All changes are recorded as immutable events; projections rebuild queryable read models for efficient CLI consumption and jq-driven workflows.
  • Replication and restore: File-based JSONL replication and iterators enable safe backups and restoring into fresh databases.
  • CLI-first workflows: Lightweight commands to init, add schemas/nodes, search, traverse graphs, and run projections that integrate with shell tooling.

Quick Start

Initialize a local Synapse database with synapse init, add a JSON schema, create a node with synapse nodes add, and then search or list nodes to inspect the stored memory.

Frequently Asked Questions about synapse

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

FAQPage Schema
How do I store structured local memory for AI agents without losing context?

Store structured local memory for AI agents by using an append-only SQLite event store with runtime JSON Schema validation. This approach captures contextual nodes and bidirectional links, preventing context loss and reducing token waste.

Does event sourcing work with local agent memory management and CLI workflows?

Yes, event sourcing works with local agent memory management by recording all changes as immutable SQLite events. Projections rebuild queryable read models that integrate directly with CLI workflows and jq-driven shell tooling.

What is the best way to traverse a knowledge graph from the command line?

Traverse a knowledge graph from the command line by creating typed nodes with attached keywords and bidirectional links. You can then use lightweight CLI commands to search nodes and expand contextually across the graph.

How do I validate JSON schemas for local memory before saving to SQLite?

Validate JSON schemas for local memory by applying runtime JSON Schema validation to node payloads before they are recorded as append-only events in SQLite. This ensures stored memories remain consistent and structured.

Can I replicate an append-only event log to backup local agent memory?

Yes, you can replicate an append-only event log to backup local agent memory using file-based JSONL replication. Iterators enable safe backups and allow restoring the event store into fresh databases.

What are the limitations of using SQLite for local agent memory management?

Using SQLite for local agent memory management limits you to file-based local storage rather than distributed network databases. It is designed for local CLI workflows and single-agent contextual graph traversal rather than high-concurrency server environments.