AgenticFleet Memory System Guide

Official

Persist and recall agent context across sessions.

AuthorQredence
Version1.0.0
Installs0

System Documentation

What problem does it solve?

AgenticFleet Memory System Guide introduces a two-tier memory system (Local + Chroma Cloud) to persist and recall agent context across sessions, enabling continuity and faster debugging.

Core Features & Use Cases

  • Hydrate and initialize local context at the start of a session to ensure memory is ready for reasoning.
  • Recall past decisions, solutions, and architectural notes using semantic search across local and cloud memory.
  • Learn and index new solutions by saving them as records in the memory store for future reuse.
  • Reflect at session end to summarize activity and keep memory history clean.

Quick Start

Initiate memory hydration, perform recall and learning steps, and reflect at the end of the session:

  • Hydrate local context: uv run python .fleet/context/scripts/memory_manager.py init
  • Recall information: uv run python .fleet/context/scripts/memory_manager.py recall "how to fix cors error"
  • Learn new skills: uv run python .fleet/context/scripts/memory_manager.py learn --file .context/skills/fix-auth-bug.md
  • End of session reflection: uv run python .fleet/context/scripts/memory_manager.py reflect

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: AgenticFleet Memory System Guide
Download link: https://github.com/Qredence/agentic-fleet/archive/main.zip#agenticfleet-memory-system-guide

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.