Home Projects atomicmemory
atomicmemory
TypeScript

atomicmemory

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

by atomicstrata · GitHub
Stars
Forks
Trending
Created
Last commit
Language
Likely
Self-hostable
agent-infrastructureagent-memoryai-agentsTypeScriptSelf-hostable
View on GitHub
In plain words

Embed a memory system in your AI applications to retain knowledge across different sessions.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
atomicmemory — GitHub preview card
📈 Star history
448420
2026-07-202026-08-31
📈 Track atomicmemory

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

atomicmemory has 429 stars on GitHub. It has been forked 36 times. atomicmemory is written mainly in TypeScript. It has been in active development since 2026. Its main topics are agent-infrastructure, agent-memory, ai-agents, ai-memory.

Frequently asked questions

What is atomicmemory?

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Is atomicmemory open source?

atomicmemory is an open-source project.

Is atomicmemory free?

Yes. atomicmemory is free and open source — you can use, modify and self-host it.

What language is atomicmemory written in?

atomicmemory is written mainly in TypeScript.

🏅 Maintainer of this project?
olud.ai badge — atomicmemory

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=atomicstrata-atomicmemory)](https://olud.ai/project/atomicstrata-atomicmemory.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.