DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use AMA: what you can do with it

What is AMA? AMA is a Python and TypeScript research codebase and agent memory skill that gives agents long-term memory through raw text, fact, and episode stores.

How do I use it? git clone https://github.com/Sherlockwz/AMA.git; then cd AMA; corepack enable pnpm. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Add AMA long-term memory policy to an agent harness

    Load the portable SKILL.md policy and bind AMA memory operations to your agent's tools.

    View prompt
    In the AMA repo at <path-to-AMA>, read SKILL.md and list each rule about when to retrieve prior context, capture turns, synthesize episodes, inspect state, and honor deletion requests. Expected output: a bulleted list of those rules with the heading each came from. Verify that every rule you list appears in SKILL.md text and none is invented.

  • Give an OpenClaw agent automatic recall and capture

    Install the OpenClaw AMA plugin to recall and capture memory automatically each turn.

    View prompt
    In the AMA repo at <path-to-AMA>, run `openclaw ama doctor` and report each check it prints as pass or fail. Expected output: the list of checks with their results. Verify that `sidecarAutoStart` is enabled in the plugin config before you report the sidecar as healthy.

  • Start the AMA memory sidecar and confirm it responds

    Launch the local AMA HTTP sidecar and check its health endpoint before wiring it in.

    View prompt
    In the AMA repo at <path-to-AMA>, start the sidecar with the uvicorn command from the README on port 8321, then call the /health endpoint. Expected output: the raw health response body. Verify that the server is bound to 127.0.0.1 and not a public interface before reporting success.

  • Reproduce AMA's LoCoMo and LongMemEval results

    Run the research pipeline on LoCoMo and LongMemEval_s to check the reported scores.

    View prompt
    In the AMA repo at <path-to-AMA>, follow docs/reproduction.md to set up the LoCoMo dataset and run one evaluation entry point from python/AdaptiveMemory/Core. Expected output: an overall LLM Score for the LoCoMo run. Verify that the dataset is placed where the guide specifies before comparing your score to the README's 0.774 reference.

Quick start with AMA

  1. Check you have what it needs: Python 3.10 or newer; Node.js 22.22.3 or newer (24.15 or newer also supported); pnpm 11 or newer.
  2. Open Sherlockwz/AMA on GitHub and read the README and license.
  3. git clone https://github.com/Sherlockwz/AMA.git
  4. cd AMA
  5. corepack enable pnpm
  6. ./scripts/setup.sh

These steps come from our top use case, Add AMA long-term memory policy to an agent harness, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Sherlockwz/AMA

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

AMA alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and agent builders who want to add long-term memory to an agent harness, run the OpenClaw reference adapter, or reproduce the paper's experiments.
  • Why it is hot113 stars, launched 65 days ago
  • LanguagePython
  • Sourcegithub.com/Sherlockwz/AMA · Back to Hot repos

Requirements

  • Python 3.10 or newer
  • Node.js 22.22.3 or newer (24.15 or newer also supported)
  • pnpm 11 or newer
  • An OpenAI-compatible chat-completions endpoint and embedding endpoint, with an API key
  • Git, to clone the repository

Add this badge to your README

Maintain AMA? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/Sherlockwz/AMA.svg)](https://dedupedai.com/use-cases/sherlockwz-ama/?utm_source=github&utm_medium=badge&utm_campaign=Sherlockwz-AMA)

HTML 

<a href="https://dedupedai.com/use-cases/sherlockwz-ama/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=Sherlockwz-AMA"><img src="https://dedupedai.com/badge/Sherlockwz/AMA.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about AMA

What is AMA?

AMA is a Python and TypeScript research codebase and agent memory skill that gives agents long-term memory through raw text, fact, and episode stores. It is an open-source project on GitHub: https://github.com/Sherlockwz/AMA.

How do I use AMA?

git clone https://github.com/Sherlockwz/AMA.git; then cd AMA; corepack enable pnpm. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is AMA for?

Developers and agent builders who want to add long-term memory to an agent harness, run the OpenClaw reference adapter, or reproduce the paper's experiments.

What can I do with AMA?

4 use cases so far, for example: Add AMA long-term memory policy to an agent harness; Give an OpenClaw agent automatic recall and capture; Start the AMA memory sidecar and confirm it responds. Each has steps and a copy-paste agent prompt.

What do I need to run AMA?

Python 3.10 or newer; Node.js 22.22.3 or newer (24.15 or newer also supported); pnpm 11 or newer; An OpenAI-compatible chat-completions endpoint and embedding endpoint, with an API key.

What are alternatives to AMA?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is AMA safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.