ai-agent

Awesome-Agent-Memory: Boost LLM Context & Retrieval

A curated collection of systems, benchmarks, and papers on long‑term memory for LLMs/MLLMs, helping founders build smarter agents with better context and reasoning.
670 stars+22★ this week127 forksPythonGuide quality 8/10 · reviewed Oct 7Updated 10/11/2026100% free · open source
What it does

Awesome-Agent-Memory provides curated systems, benchmarks, and papers on memory for Large Language Models (LLMs) to help founders improve long-term context, retrieval, and reasoning in AI agents

When to use it
  • •When designing an AI agent that requires complex, long-term memory and context understanding
  • •When evaluating and comparing different LLM architectures for a specific use case
  • •When researching and implementing memory-augmented AI systems for improved reasoning and decision-making
Ready-to-paste prompt
Search for papers on 'external memory' using `grep -r 'external memory' papers/`
Heads up: Note that this repository is a collection of resources and does not provide executable code, so you will need to implement and integrate the concepts and systems described in your own project
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/awesome-agent-memory && curl -fsSL https://workflowstacks.com/api/skills/awesome-agent-memory/claude-skill -o ~/.claude/skills/awesome-agent-memory/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Awesome-Agent-Memory: Boost LLM Context & Retrieval works
Codeflow
Free to inspect

Awesome-Agent-Memory: Boost LLM Context & Retrieval is mostly documents (4 doc files, 3 small scripts) — something you read, not something you run. There is nothing to install. Last commit this month, Apache-2.0 license.

Size
Mostly documents
4 documents · 3 small scripts · 29 min skim
Setup
Nothing to install
A guide / curated list. Just read it and follow the links.
Runs on
Nowhere — you read it
A reading resource, not a program.
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
What's in each folder
scripts/Helper scripts3 files
.github/CI / automation (GitHub Actions)5 files
assets/Images & static assets5 files
READMEDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
TeleAI-UAGI
Language
Python
Category
ai-agent
Published
10/30/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/awesome-agent-memory.svg)](https://workflowstacks.com/skills/awesome-agent-memory?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.