Comments URL: https://news.ycombinator.com/item?id=47717690

Points: 35

# Comments: 2

I've been working on something in this space too. I built https://sonars.dev specifically for orchestrating multiple Claude Code agents working in parallel on the same codebase. Each agent gets its own workspace/worktree and there's a shared context layer so they can ask each other questions about what's happening elsewhere (kind of like your Librarian role but real-time).

The "ask the architect" pattern you described is actually built into our MCP tooling: any agent can query a summary of what other agents have done/learned without needing to parse their full context.

In those 27 years, I've worked on game engines at EA DICE, done rendering research at OTOY and Embark, and now run a graphics R&D company that does work for AMD, Intel, and Meta. I've seen plenty of new tools come and go.

When AI coding tools started blowing up, I needed to figure out: is this something my company should invest in, or something we can safely ignore for another few years?

I decided to settle it: go all-in for a few weeks. Build something real, outside of our existing codebase, with agentic AI—not just autocomplete, but actually letting Claude Opus write files, run commands, and commit code.

3 weeks later, I have my answer.

Sonars went from zero to launch in 3 weeks. One developer. Pure agentic AI. And once the core was working, I used Sonars to build Sonars.

The problem I kept hitting with other tools: Claude made changes directly in my working directory. One experimental prompt and my branch was a disaster—half-finished features, broken tests, merge conflicts with myself.

The fix was obvious in hindsight: Git worktrees. Every AI session in Sonars runs in complete isolation. Claude can go wild—read files, write code, run tests, commit changes—and your main branch stays untouched until you explicitly merge.

Features: - Claude reads files, writes code, runs terminal commands, commits changes - Every session isolated in a Git worktree - Real-time streaming with extended thinking mode - Visual diff viewer with syntax highlighting - Native Rust + Dioxus app

Tech stack: Rust + Dioxus (frontend), Axum (backend), SQLite + PostgreSQL, gix (pure Rust Git).

Free tier available: https://sonars.dev

After 27 years and shipping game engines, I don't say this lightly: this is the most productive I've ever been. The answer to my original question? This isn't something to ignore.

Happy to answer questions about the architecture, the worktree approach, or what building Rust with agentic AI is actually like.

Comments URL: https://news.ycombinator.com/item?id=46581314

Points: 4

# Comments: 0

Full disclosure: I do run the company behind Evolve.

Comments URL: https://news.ycombinator.com/item?id=44962361

Points: 58

# Comments: 5

Comments URL: https://news.ycombinator.com/item?id=44696947

Points: 3

# Comments: 0

[0]: https://github.com/Traverse-Research/gpu-allocator/

[1]: https://www.evolvebenchmark.com/