silentspikesilentspike/noaide/llms.txt

noaide

llms.txt0 starsChanged 9 months agoMITView on GitHub

Browser-based real-time IDE for AI coding agents (Claude Code, Gemini CLI, Codex). Rust backend + SolidJS frontend + WASM modules.

Create a free account to mount

Files

llms.txt

# noaide

> Browser-based real-time IDE for AI coding agents (Claude Code, Gemini CLI, Codex). Rust backend + SolidJS frontend + WASM modules.

## Core Documentation (read first)
- [README](README.md): Overview, quick start, architecture, configuration
- [Contributing](CONTRIBUTING.md): Development workflow, commit conventions, code style
- [Testing](TESTING.md): Test strategy, gate matrix, performance benchmarks
- [Security Policy](SECURITY.md): Vulnerability reporting, response timeline

## Architecture Decisions
| ADR | Decision | Rationale |
|-----|----------|-----------|
| ADR-1 | Rust backend (tokio + io_uring) | Zero-copy async I/O, memory safety |
| ADR-2 | SolidJS frontend (fine-grained reactivity) | No virtual DOM, 120fps at 1000+ messages |
| ADR-3 | Zenoh + SHM event bus | ~1us latency, zero-copy shared memory |
| ADR-4 | Limbo DB (io_uring, FTS5, async) | Async SQLite alternative, full-text search |
| ADR-5 | eBPF file watcher | PID attribution, kernel-level efficiency |
| ADR-6 | hecs ECS state engine | Struct-of-arrays, cache-friendly iteration |
| ADR-7 | FlatBuffers (hot) + MessagePack (cold) | Zero-copy hot path, compact cold path |
| ADR-8 | WebTransport-only (QUIC, 0-RTT) | Multiplexed streams, no head-of-line blocking |
| ADR-9 | PTY stdin + tmux send-keys | Session control without shell=true |
| ADR-10 | Catppuccin Mocha theme | Consistent dark theme, accessibility |
| ADR-11 | CodeMirror 6 editor | Modular, tree-sitter integration |

Download now (ZIP)

In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free