# neomjs/neo

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

Repository: https://github.com/neomjs/neo
Canonical: https://ross.abutalabs.com/products/neomjs-neo
Homepage: https://neomjs.com
Language: JavaScript
License: MIT
License Family: permissive
Topics: agent-memory, ai-agent, ai-memory, context-engineering, frontend, frontend-runtime, graph-rag, javascript, json, knowledge-graph, llm, long-term-memory, mcp, mcp-server, multi-agent-systems, rag, scene-graph, semantic-search, web-workers, ai
Last push: 2026-08-26T22:28:05+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 79, longevity 100
- inputs: {"age_days": 2488, "days_push": 7, "days_rel": 61, "gap_med": 1.0, "n_releases_24m": 191}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3260, forks 231 (observed 2026-08-28T04:07:52.591523+00:00)

## What it is
Neo.mjs is a JavaScript frontend framework built on a multi-threaded web-workers architecture, now evolving into an AI-driven engineering platform where a multi-model agent swarm inhabits live applications via a 'Neural Link' runtime interface. It combines a component-based UI runtime with agent memory, Active Hybrid GraphRAG, and self-healing development loops.

## Use cases
- build multi-threaded web apps with web workers
- let AI agents inspect and mutate a running app's UI state
- run a multi-model agent swarm for code review and development
- add long-term agent memory and graph-based RAG to apps
- build JSON-driven frontend applications without heavy build tooling
- create conversational UIs where agents act inside the application

## When to choose
- you want a web-workers-based frontend framework with fine-grained multithreading
- you want AI agents to operate directly inside a live application runtime
- you're experimenting with multi-agent development workflows and shared agent memory
- you prefer JSON-driven component configuration over JSX

## When to avoid
- you need a mainstream framework with a huge ecosystem and easy hiring pool
- your team is new to web workers and multi-threaded UI architecture
- you only need a simple static site or standard SPA with minimal learning curve
- you want battle-tested enterprise adoption over an evolving, opinionated project

## Facets
- artifact type: framework
- maturity: active
- function: frontend-framework, web-framework, agent-framework, rag, mcp, state-management
- domain: web-development, frontend, artificial-intelligence, developer-tools
- platform: browser, cross-platform
- tags: web-workers, multi-threaded, multi-agent, graph-rag, knowledge-graph, agent-memory, semantic-search, json-driven, ai-swarm, self-healing, ai-agents, retrieval-augmented-generation, javascript, nodejs, web-server

## Member repositories
- neomjs/neo (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:52.591523+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:23:13.628153+00:00, confidence not recorded.
  - readme: https://github.com/neomjs/neo (fetched 2026-08-28T04:07:52.591523+00:00, sha 8049e519e3ba)
  - homepage: https://neomjs.com (fetched 2026-08-29T09:36:59.426037+00:00, sha 728dc2095602)
- Data as of 2026-08-30T08:39:29.467469+00:00.