Directory
AI memory systems, at a glance.
What each one is for, where your memories live, and how it compares with the 11 ways human memory works. In plain language, checked against each system’s own docs and code.
What are the 11 mechanisms?
Encoding
Salience Decides what's worth keeping, and how much, as a memory is written.
Emotion Gives memories written with feeling more weight.
Storage
Forgetting Lets unused memories fade over time on its own.
Interference When a new memory closely matches an old one, notices and lets the newer one win.
Retrieval
Retrieval Remembering something makes that memory stronger.
Association Links memories, so recalling one brings its neighbours.
Prospective Brings a memory back at the right time without being asked.
Transformation
Consolidation Reworks memories between sessions: strengthening, merging, reorganising.
Reconsolidation Corrects a memory when it's contradicted, and keeps what it used to say.
Gist Turns many specific moments into general knowledge.
Schemas Forms beliefs about people and projects, and weighs new facts against them.
Counterparts★ 3
Gives Claude its own memories, which fade and strengthen the way yours do.
- Lives
- Needs
- Works with
Letta★ 3.6k
An AI agent that keeps its own memory as files, and tidies them up while idle.
- Lives
- Needs
- Works with
ChatGPT memory
ChatGPT's built-in memory: it learns about you from your chats and keeps that picture up to date.
- Lives
- Needs
- Works with
Claude (app memory)
Claude remembers your work, your people and your preferences from chat to chat, and lets you see and edit every topic.
- Lives
- Needs
- Works with
Claude Code memory★ 150.6k
Plain notes files a coding agent reads every session: rules you write, plus notes it keeps for itself.
- Lives
- Needs
- Works with
claude-mem★ 100.4k
A Claude Code plugin that quietly takes notes on your coding sessions and hands them back next time.
- Lives
- Needs
- Works with
trusty-memory★ 22
A local memory server for coding agents, with searchable notes, a small knowledge graph and a background tidy-up pass.
- Lives
- Needs
- Works with
Cognee★ 32.2k
An open-source memory that turns documents, code and chats into a knowledge graph your agents can search.
- Lives
- Needs
- Works with
Hyperconsciousness★ 7
An encrypted, append-only notebook that syncs across your devices and lets an agent read or write only the slice you grant it.
- Lives
- Needs
- Works with
Mem0★ 67.1k
A plug-in memory layer that pulls facts out of AI chats and hands back the relevant ones later.
- Lives
- Needs
- Works with
Supermemory★ 31.2k
A memory service that turns chats and files into a web of facts that stays current.
- Lives
- Needs
- Works with
Zep★ 31.7k
A memory that keeps facts on a timeline: when each became true, and when it stopped.
- Lives
- Needs
- Works with
The data is open, under CC BY 4.0: JSON · CSV · the repo on GitHub. To cite it: “The Counterparts directory, https://counterparts.ai/directory/”.
Add your system
Build a memory system that isn’t here? Add it.
- Every page is one small file in a public GitHub repo. Copy the template, fill it in, and open a pull request. Rather not write YAML? Open an issue with links, and we’ll make the change.
- An automatic check tells you within a minute if anything is missing or mistyped.
- We read it against the sources you link. Every “built” or “partly built” grade needs a link that shows it, and every system is graded by the same written rules, ours included.
- Once it’s merged, the page updates a minute or two later. Changes from a system’s own team get a “Confirmed by its makers” mark.