atomicstrata

atomicstrata / atomicmemory-sdk

Public

Open-source AtomicMemory TypeScript SDK

agent-memory agents ai ai-agents ai-memory
10
0
100% credibility
Found May 15, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

TypeScript SDK for adding persistent, semantic memory to AI applications with pluggable backends, local embeddings, and storage adapters.

How It Works

1
🔍 Discover Smart Memory

You hear about a simple tool that helps AI chatbots remember user details like favorite seats or preferences without forgetting.

2
📦 Add to Your App

You easily add the memory helper to your project with one quick command.

3
🔌 Connect Memory Service

You link it to a free local memory brain so your AI can store facts securely.

4
🚀 Launch Your Memory

With one click, your AI's memory comes alive and is ready to learn.

5
💬 Teach Your AI

You share simple facts like 'I prefer aisle seats on long flights' and it remembers instantly.

6
🔍 Ask and Recall

Later, you ask 'What seat do I like?' and it pulls up your exact preference perfectly.

🎉 Perfect Recall Achieved

Your AI now remembers everything reliably, making conversations feel personal and smart.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is atomicmemory-sdk?

AtomicMemory SDK is a TypeScript library for adding persistent memory layers to AI apps, letting you ingest conversations or text, search semantically, and package contexts for agent prompts. It solves vendor lock-in by supporting pluggable backends like self-hosted AtomicMemory core, Mem0, or Hindsight via HTTP adapters, plus local embeddings with transformers.js and IndexedDB/in-memory storage. Developers get a unified API for memory ops without managing vectors or LLMs directly.

Why is it gaining traction?

It stands out as an open-source GitHub alternative for memory tools, with self-hosted providers dodging proprietary costs and privacy issues—pair it with open-source GitHub Actions alternatives for CI/CD or Codespaces-like dev envs. Local semantic search and embedding caching work offline, and the Apache 2.0 license fits open-source GitHub lists perfectly. Early adopters like its no-fuss ingest/search/package flow over raw vector DBs.

Who should use this?

TypeScript devs building AI agents or chat apps needing scoped user memory, especially those self-hosting to avoid SaaS bills. Ideal for backend teams integrating with LLMs like Ollama, or frontend devs proxying memory ops in trusted webapps. Skip if you need massive scale—it's for prototypes to mid-tier production.

Verdict

Worth a spin for TypeScript AI projects wanting open-source, self-hosted memory without reinventing embeddings or search; docs and quickstart shine. At 10 stars and 1.0% credibility, it's pre-1.0 experimental—test thoroughly, but the pluggable design scales well for open-source GitHub Copilot alternatives.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.