Memory infrastructure for AI agents.
Sub-200ms
retrieval latency
3-scope hierarchy
Merchant, Visitor, Conversation
The Problem
Agents forget. Every time.
Most agents are stateless by design. Each session starts from zero. LLMs don't retain context between calls. RAG retrieves documents — it doesn't remember users.
No session continuity
Every conversation starts cold. The agent has no idea what was discussed last time.
RAG isn't memory
Retrieval over documents answers factual questions. It doesn't track what a user said last week.
Memory management is undefined
No framework for what to retain, what to update, or when memory stops being relevant.
Home-built systems break at scale
Conversation history in a list works for demos. It fails at thousands of users.
The Solution
A dedicated layer for what agents need to remember.
agents-memory handles memory storage, retrieval, and lifecycle — so you don't have to build it yourself. It sits between your agent and your LLM, storing what happened, who said it, and what matters.
It's not a database you query manually. It's memory that works automatically: collected, intelligently retrieved, and scoped to the right user.
01
Conversation scope
Redis STM — active session context, last N turns, auto-TTL
02
Visitor scope
Episodic memory — personal profile consolidated across conversations
03
Merchant scope
Shared knowledge base accessible to all agents in your tenant
04
Retrieval engine
Hybrid semantic + recency + frequency scoring — ranked and ready to inject
How It Works
Three steps. No plumbing.
01 • Capture
Your agent sends interactions to AgentFoundry via API — messages, events, extracted facts. Stored across three scopes: Merchant (shared KB), Visitor (personal profile), and Conversation (session context).
02 • Retrieve
Before each LLM call, query AgentFoundry. Get back ranked context via hybrid semantic + recency + frequency scoring. Contradiction detection flags stale facts automatically.
03 • Evolve
Each retrieval reinforces neural pathways — frequently accessed memories resist forgetting. Unused facts decay along the Ebbinghaus curve. The agent grows sharper over time.
<< agents memory >>
Pricing
Get started with our simple pricing
Blog
Get the latest from our dev team
Testimonials
Early Bird Users Love Us
FAQ
Frequently Asked Questions
Will I need to re-download the app after early access ends?
Nope! You’ll get a regular update when the official version is released. Your data and settings will carry over.
What should I expect from the early version?
The app is still under development, so you may encounter bugs or unfinished features. Your input helps shape the final version.
Is the early access version free?
Yes, early access is completely free. All we ask is for your feedback to help us improve.
How can I join early access?
You can sign up through our website or app landing page. Spaces are limited, so it’s first come, first served!
What is early access to the app?
Early access lets users try a preview version of the app before the official launch. It helps us test features, gather feedback, and make improvements.