Vectorize is an open-source agent memory system that provides persistent, per-user context and fast recall for AI agents. It is model-agnostic, supports cross-session persistence, and enables agents to learn from mistakes. Designed for AI developers building advanced agent frameworks, it is MIT licensed and available as a CLI and API.
In the AI & ML space, Vectorize takes a focused approach. It focuses on enabling AI agents to retain persistent, structured memory and learn from user interactions across sessions. It is built as an open-source project for AI developers and agent framework builders. Vectorize is open source under the MIT license. It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by Vectorize Contributors, and the product first shipped in 2025. Development happens publicly on GitHub with 17.8k stars and 1.1k commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Vectorize occupies a relatively distinct niche. Key capabilities include agent memory, cross-session persistence, and fast recall. It exposes integrations via a public API.
Latest indexed changes and source events
Vectorize Io discovered by the PulseGate indexer
Other apps tracked under the same category.
