New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Memory System

by Qredence in Qredence/agentic-fleet

Complete guide to the AgenticFleet memory system. An agent skill from Qredence/agentic-fleet.

MITAuto-check passedAI & LLM Engineering

Install Memory System

skills CLI
$ npx skills add Qredence/agentic-fleet --skill memory-system -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Qredence/agentic-fleet memory-system --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Qredence/agentic-fleet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.fleet/context .claude/skills/memory-system && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory-system
GitHub stars
111
Token cost
~1.2k tokens
SKILL.md length
244 words
Files
33 (incl. scripts)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Complete guide to the AgenticFleet memory system. An agent skill from Qredence/agentic-fleet.

  • Works in 6 steps: Initialize (first time only) → Setup Chroma Cloud (after editing config… → Verify Status → …
  • AI & LLM Engineering work in your project
  • SKILL.md covers Quick Start, Memory Hierarchy, Commands and Block Format, plus 3 more sections
  • Calls uv

What it does

Memory System is an agent skill from Qredence/agentic-fleet. Complete guide to the AgenticFleet memory system. Read this first.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including scripts (for example `.chroma/config.template.yaml`, `.neon/config.template.yaml` and `MEMORY.md`).

It sits in AI & LLM Engineering. The repository describes itself as: Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discord for suggestion or support ! https://discord.gg/ebgy7gtZHK. The licence is MIT.

When your agent uses it

  • AI & LLM Engineering work in your project

Example prompts

  • “/memory-system”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Initialize (first time only)
  2. Setup Chroma Cloud (after editing config with your API key)
  3. Verify Status
  4. Read Core Context (always do this first)
  5. Search Memory when you need information
  6. Create Skills after solving problems

What it can do on your machine

Read from SKILL.md and the folder at commit 46a254b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory System loads about 1.2k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Qredence/agentic-fleet at commit 46a254b, republished under its MIT licence (© Qredence). 244 words, ~1,159 tokens.

Download SKILL.mdSave it as .claude/skills/memory-system/SKILL.md (or your agent's skills folder). This skill also uses 32 other files; get the full folder from GitHub.
name
memory-system
description
Complete guide to the AgenticFleet memory system. Read this first.

AgenticFleet Memory System

A two-tier memory architecture enabling agents to learn, remember, and improve over time.

Quick Start

  1. Initialize (first time only):

    bash
    uv run python .fleet/context/scripts/memory_manager.py init

  2. Setup Chroma Cloud (after editing config with your API key):

    bash
    uv run python .fleet/context/scripts/memory_manager.py setup-chroma

  3. Verify Status:

    bash
    uv run python .fleet/context/scripts/memory_manager.py status

  4. Read Core Context (always do this first):

    • .fleet/context/core/project.md - Project architecture
    • .fleet/context/core/human.md - User preferences
    • .fleet/context/core/persona.md - Agent guidelines

  5. Search Memory when you need information:

    bash
    uv run python .fleet/context/scripts/memory_manager.py recall "your query"

  6. Create Skills after solving problems:

    bash
    uv run python .fleet/context/scripts/memory_manager.py learn --file .fleet/context/skills/new-skill.md

Memory Hierarchy

Core Memory (Always In-Context)

Location: .fleet/context/core/

BlockPurpose
project.mdArchitecture, tech stack, conventions
human.mdUser preferences, communication style
persona.mdAgent role, tone, guidelines
Topic Blocks (Reference On-Demand)

Location: .fleet/context/blocks/

CategoryBlocks
project/commands, architecture, conventions, gotchas
workflows/git, review
decisions/ADR-style decision records
Skills (Procedural Memory)

Location: .fleet/context/skills/

Learned patterns and solutions. Indexed to Chroma for semantic search.

Collections: semantic, procedural, episodic

Enables fuzzy search across all indexed content.

Commands

Claude Code Commands
/init              # Initialize memory system
/learn             # Learn a new skill
/recall            # Search memory semantically
/reflect           # Reflect on session, consolidate learnings
CLI Commands
bash
# Initialize system (creates local files)
uv run python .fleet/context/scripts/memory_manager.py init

# Setup Chroma Cloud collections
uv run python .fleet/context/scripts/memory_manager.py setup-chroma

# Check connection and collection status
uv run python .fleet/context/scripts/memory_manager.py status

# Semantic search across all collections
uv run python .fleet/context/scripts/memory_manager.py recall "query"

# Index skill to Chroma procedural collection
uv run python .fleet/context/scripts/memory_manager.py learn --file <path>

# Archive session to episodic collection
uv run python .fleet/context/scripts/memory_manager.py reflect

Block Format

All memory blocks use Letta-style frontmatter:

yaml
---
label: block-name
description: What this block contains and when to use it.
limit: 5000 # Character limit
scope: core|project|workflows|decisions
updated: 2024-12-29
---
# Content here...

Workflow

Starting a Session
  1. Read core blocks (project, human, persona)
  2. Check relevant topic blocks if needed
  3. Use /recall to search for relevant skills
During Work
  1. Reference blocks as needed
  2. Update human.md if you learn user preferences
  3. Note patterns worth remembering
Ending a Session
  1. Use /reflect to consolidate learnings
  2. Create skills for reusable solutions
  3. Index new skills with /learn

File Structure

.fleet/context/
├── SKILL.md                    # This file (entry point)
├── MEMORY.md                   # Detailed documentation
├── core/                       # Core memory blocks
├── blocks/                     # Topic-scoped blocks
│   ├── project/
│   ├── workflows/
│   └── decisions/
├── skills/                     # Learned skills
├── system/                     # Agent skill definitions
├── scripts/                    # Python memory engine
└── .chroma/                    # Chroma Cloud config
  • MEMORY.md - Detailed setup and architecture
  • skills/README.md - How to create skills
  • skills/SKILL_TEMPLATE.md - Skill template
  • blocks/decisions/001-memory-system.md - Architecture decision record

© Qredence, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 32 other files (scripts) in .fleet/context of Qredence/agentic-fleet.

  • SKILL.md
  • .chroma/config.template.yaml
  • .gitignore
  • .neon/config.template.yaml
  • MEMORY.md
  • blocks/decisions/001-memory-system.md
  • blocks/project/architecture.md
  • blocks/project/commands.md
  • blocks/project/conventions.md
  • blocks/project/gotchas.md
  • blocks/workflows/git.md
  • blocks/workflows/review.md
  • core/human.template.md
  • core/persona.md
  • … and 19 more

Open the folder on GitHubat commit 46a254b

Compare with similar skills

Memory System next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory System compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory System this skillQredence/agentic-fleet111—~1.2kAutomated safety check: PassMIT
Agent BuildershareAI-lab/learn-claude-code78k6 repos~1.2kAutomated safety check: PassMIT
Add Uint Supportpytorch/pytorch104k2 repos~2.3kAutomated safety check: PassCustom licence
Peft Fine TuningOrchestra-Research/AI-Research-SKILLs13k9 repos~3.1kAutomated safety check: PassMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k9 repos~3.3kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.8k15 repos~656Automated safety check: PassApache-2.0

Similar skills

  • Agent Builder

    shareAI-lab/learn-claude-code

    Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

    78k GitHub starsUsed in 6 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Peft Fine Tuning

    Orchestra-Research/AI-Research-SKILLs

    Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.

    13k GitHub starsUsed in 9 repos~3.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 9 repos~3.3k tokens
    AI & LLM EngineeringAuto-check passed

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.8k GitHub starsUsed in 15 repos~656 tokens
    AI & LLM EngineeringAuto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 8 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

More from Qredence/agentic-fleet

All 10 skills in this repo

  • Changelog Generator

    Qredence/agentic-fleet

    Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes.

    111 GitHub starsUsed in 20 repos~772 tokens
    Auto-check passed

  • Python Backend Reviewer

    Qredence/agentic-fleet

    Expert Python backend code reviewer that identifies over-complexity, duplicates, bad optimizations, and violations of best practices.

    111 GitHub stars~3.3k tokensUpdated 5 mo ago
    Auto-check passed

  • Recall

    Qredence/agentic-fleet

    Semantic search for memory. An agent skill from Qredence/agentic-fleet.

    111 GitHub stars~445 tokensUpdated 5 mo ago
    Auto-check passed

  • Dspy Agent Framework Quick Ref

    Qredence/agentic-fleet

    Quick reference card for DSPy + Agent Framework integration patterns: typed signatures, assertions, routing cache, and agent handoffs.

    111 GitHub stars~1k tokensUpdated 5 mo ago
    Auto-check passed

  • Fleet Agent

    Qredence/agentic-fleet

    Context-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB).

    111 GitHub stars~994 tokensUpdated 5 mo ago
    Auto-check passed

  • Initiate Memory

    Qredence/agentic-fleet

    Comprehensive guide for initializing or reorganizing agent memory and project context.

    111 GitHub stars~2k tokensUpdated 5 mo ago
    Auto-check passed

Categories

Questions about Memory System

What does Memory System do?

Complete guide to the AgenticFleet memory system. An agent skill from Qredence/agentic-fleet. Memory System is an agent skill from Qredence/agentic-fleet. Complete guide to the AgenticFleet memory system.

When should I use Memory System?

Memory System fits situations like: AI & LLM Engineering work in your project.

How do I install Memory System in Claude Code?

Run `npx skills add Qredence/agentic-fleet --skill memory-system -a claude-code`. Or copy the skill folder (.fleet/context in Qredence/agentic-fleet) into .claude/skills/memory-system in your project. Claude Code loads it when a task matches its description.

How do I install Memory System in Codex?

Run `npx skills add Qredence/agentic-fleet --skill memory-system -a codex`. Or copy the skill folder (.fleet/context in Qredence/agentic-fleet) into .agents/skills/memory-system in your project. Codex loads it when a task matches its description.

Can I use Memory System in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Qredence/agentic-fleet --skill memory-system -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-system, .gemini/skills/memory-system, .github/skills/memory-system and .opencode/skills/memory-system in your project.

What does Memory System need to run?

Going by SKILL.md and its folder, Memory System needs the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Memory System access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Memory System safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Memory System use?

Memory System is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory System use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory System?

Skills that share tags, products or a category with Memory System: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory System?

Qredence (a GitHub organization) maintains it in Qredence/agentic-fleet, which has 111 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on April 13, 2026.

Source: Qredence/agentic-fleet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.