Back to directory

The Adam Framework

An open-source framework that gives an AI agent a persistent identity and memory stored entirely in local plain-text files, so its history and personality can survive a model change, a vendor shutdown or a wiped machine.

Visit website (opens in a new tab)strangeadvancedmarketing.github.io
The Adam Framework

The Adam Framework keeps an AI agent's continuity in files the user owns rather than in a vendor's servers: a SOUL.md file, a CORE_MEMORY.md file and a neural graph of Vault files, all plain Markdown on disk. The stated design goal is that swapping the underlying language model, or losing access to a vendor's service entirely, does not lose the agent's accumulated history, because the model reads from the Vault rather than storing state itself.

The maintainer describes recovering a full working setup from these files within about an hour after the machine running it was completely wiped, as a demonstration of this recovery approach rather than a guarantee. The framework itself is distributed as MIT-licensed open source, with an optional paid package sold separately that provides pre-filled templates and a setup guide for people who would rather not configure it themselves.

It is aimed at being used with agent harnesses such as OpenClaw, and is written in Python.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.