Show HN: peerd – AI agent harness that runs entirely in your browser

Broswer contains many security concerns, how do you solve privacy and security.

Author here. Some other technical tidbits:

- Fully typed checked with JSdoc, and Bun/TS for testing.

- stdlib-js is injected into every js runner and notebook for better math capabilities than vanilla js, and also charts etc.

- App dev tasks utilize mithril for making SPAs, a very small no-dependency framework that is very fit to purpose for the client side nature of peerd apps.

- Currently on main, tabs are global objects each chat session can freely mutate, which is not great. The new in progress model has one "resident" agent own every tab. Only they have the exposed capability to mutate it, and everything between agents/sessions is message based. This has some cool properties: further isolation between contexts, mirroring the web runner subagent. Explicit ownership and scope is cleaner and better for parallel ops. Context and system prompts can be reduced and focused to the specific context the session is exposed to. The orchestrator doesn’t have any low level tab interactions available to it. The tab residents have only the tab interaction tools relevant to it, and the instructions specific to the tab type (js notebook, linux vm, app dev, etc). Over time model usage can be tuned and optimized for each specific context etc.

Congratz on your project. Yet I feel that the browser extension part is doing damage to its discoverability hence democratization.

You might be interested in this browser-based agentic solution I'm currently building in the open: https://github.com/codename-co/devs

> The name is always lowercase: peerd.

Gotta love it when agent instructions get blurted out in user-facing documentation

That's cool. Sounds very impressive. What's the point of all this security though?

You don't want it to access your files, just give it its own Linux user. You don't even need a container.

Better yet, you can give it root on a $3 VPS (or $30 Thinkpad) and get a sysadmin for free :)

Although, Cheerpx... that seems to imply your agent can play Java and Flash games. Alright, you might be on to something!

> The bet is structural

Why has AI writing become so insufferable?

The project would be a lot more credible if the feature list wasn't so comically extensive and verbose [1]. Slop overload.

[1] https://github.com/NotASithLord/peerd/blob/main/FEATURES.md

If the web runners return summarized results and those are still treated as untrusted, what's stopping a summary itself from carrying the injection up to the main loop?

Lets collaborate! https;//www.threedeep.tech/