#8787th of 107 in Coding agents and AI editors
neo
Multi-threaded browser UI engine, maintained by a cross-model team of AI agents
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- JavaScript
3,141 on 31 Mar 20263,294 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Neo.mjs is a zero-dependency, build-free JavaScript application engine that runs app logic, VDOM diffing, data and canvas work in separate Web Workers. Its README frames it as one part of an agent setup: a Neural Link lets AI agents inspect and mutate a live app's state, while memory and review tooling lives in the sibling neo-agent-brain repo. This repo is the UI runtime, not the agent backend.
Who it is for: Frontend engineers building multi-window apps; teams testing multi-agent upkeep
Strengths
- Off-main-thread design with App, VDom, Data, Canvas workers and SharedWorker for multi-window apps
- Native ES modules with no transpilation and zero runtime dependencies
- Neural Link exposes tools like get_component_tree and patch_code for agents to edit live apps
- Project's own maintenance record is public: 900+ merged PRs reported for June 2026
Weaknesses
- Agent memory, knowledge base and orchestration are in separate repos, not this one
- Fleet Manager (neo-agent-institution) is version 0.1.0 and awaits an outside operator's first run
- Requires adopting the Actor Model and Workers; not a drop-in swap for other UI frameworks
- README is mostly vision and claims; setup requirements for the agent stack are not stated here
What it needs
- Needs Node.js and npm (npx neo-app), neo-agent-brain (for agent features)
- Models: Claude, Gemini, GPT, Kimi
Also in Coding agents and AI editors
See all 107| Rank | Project | Score |
|---|---|---|
| 1 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 2 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 81 out of 100 |
| #4 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |
| #5 | gooseRust AI agent with desktop app, CLI and API, extended through MCP | 80 out of 100 |