Cortex is live on GitHub.Repo

ICE V3: OUT NOW

ICE V3 is ready and out. GoingMerry is coming soon.

Introducing ICE V3

Intelligence,
Engineered.

Add persistent memory to any LLM in 3 lines of code.

ICE Logo

Indexless Memory

Developers never touch a vector index. ICE handles embedding, storage, and retrieval entirely under the hood.

Zero-Conf Local Mode

Boots instantly with an embedded DuckDB file (~/.ice/ice_memory.db). No Docker, Postgres, or daemons required.

Drop-In SDK Middleware

Wraps standard AsyncOpenAI or Anthropic Python clients in exactly 3 lines of code. No new API paradigms to learn.

Developer First

One import.
Persistent Memory.

ICE wraps standard LLM client libraries to automatically handle embedding, database storage, and context retrieval. No database setup, chunking logic, or index management needed.

Transparent LLM Client Wrapper

Zero-Conf Local DuckDB Storage

Multi-Platform Native Core C-Extension

main.py
1

import ice

2

import asyncio

3

import os

4

 

5

# 1. Set your signed license key

6

os.environ["ICE_LICENSE_JWT"] = "your_signed_jwt_here"

7

 

8

async def main():

9

    # 2. Ingest documents into memory

10

    await ice.ingest("s3://data-lake/architecture.pdf")

11

 

12

    # 3. Query with automatic memory retrieval

13

    response = await ice.query(

14

        prompt="Analyze this.",

15

        model="gpt-4o"

16

    )

17

    print(response)

18

 

19

asyncio.run(main())

Core Capabilities

The architectural advantages of Persistent Context Engineering

Velocity. Pure.

Low latency context retrieval and management. Native intelligence at speed.

Identity. Persistent.

Transform stateless interactions into evolving, stateful agent identities.

Reliability. Absolute.

Secure, isolated, and scalable memory architecture for the next decade of B2B.

The Ecosystem

Built for each other.

ICE

Indexless Context Engine. Perfect memory and context ingestion for every model.

Explore ICE

Cortex

Hardened Runtime. A stable, high-performance engine for deploying complex agent ecosystems.

Explore Cortex

GoingMerry

Fastest & Efficient Local AI Runtime. Run any model privately on your machine.

Explore GoingMerry