Understand the project
Practical overview
When it fits
Use Neo.mjs when you want to explore how a JavaScript application runtime can work with a multi-model AI swarm, persistent memory and GraphRAG. It is especially relevant for experiments involving live application inspection or knowledge-graph-backed engineering coordination.
Who it is for
- JavaScript and frontend-runtime developers exploring AI-assisted engineering
- Teams investigating shared-context multi-agent systems
- Researchers and builders working with agent memory, GraphRAG or knowledge graphs
Documented uses
- Coordinate multiple AI models around shared engineering context
- Build or investigate memory-backed software-engineering workflows
- Connect agents with live application runtime state
- Explore frontend-integrated agent systems and self-healing development loops
Before you choose
Requirements & limits
The repository is public and lists an MIT license.
- Its documented architecture separates the application runtime (“Body”) from the agent operating system (“Brain”).
- The Neural Link concept is explicitly intended to connect the swarm with live applications, but implementation details and integration examples were not supplied.
- The project is JavaScript-based and its technical profile identifies web, cloud, self-hosted and server environments.
- The repository description covers DreamService and self-healing loops, while the evidence does not establish a complete deployment configuration.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 1 October 2026
- Original website title
- neomjs/neo · Official homepage title · retained in its source language