NotASithLord/peerd

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK, no backend, no telemetry.

What it solves

peerd provides a way to run AI agents directly within the web browser rather than on a remote server or with full access to a user's operating system. It allows agents to interact with your active tabs, signed-in sessions, and web applications while maintaining security boundaries to prevent the agent from accessing the system host.

How it works

It is built as a browser extension for Chrome and Firefox that leverages browser primitives like Workers, sandboxing, WASM/WASI, and WebRTC. The system uses a "harness" that delegates tasks to separate, keyless actors scoped to specific environments (like a single tab). For inference, users can connect to hosted model providers, local models via localhost, or use experimental WebGPU models.

Who it’s for

Users who want an AI agent capable of driving their web browser and interacting with web apps but who prioritize security, privacy, and the ability to choose their own LLM provider.

Highlights

  • Browser-Native Execution: Runs entirely in the browser, accessing tabs and page content without needing a hosted browser environment.
  • Defense-in-Depth Security: Uses browser isolation and narrow tool exposure to ensure unsafe content is contained.
  • Local Compute: Supports running scripts, JavaScript Notebooks, and Linux WebVMs within browser boundaries.
  • Flexible Model Support: Compatible with various cloud providers (BYOK) and local model options.
  • P2P Capabilities: Preview builds include browser-to-browser discovery and agent-to-agent communication via WebRTC.

Related

  • Dispatch
    peerd: A Browser-Native AI Agent Harness

    peerd is a browser extension for Chrome and Firefox that runs a full AI agent loop entirely client-side, providing sandboxed compute and peer-to-peer sharing without a backend or telemetry.

  • Project
    Lum1104/dsh-browser

    A browser bridge and extension that connects DeepSeek Harness to Chrome or Firefox, allowing AI agents to operate within the user's active, logged-in browser sessions using a text-only interface.

  • Project
    platonai/Browser4

    An AI-native browser engine for autonomous agents and large-scale web automation, featuring zero-token ML extraction and high-performance swarm crawling.

  • Project
    browser-use/browser-use

    A framework that enables AI agents to control a web browser like a human, allowing them to perform tasks such as filling forms and extracting data through plain-language instructions.

  • Project
    abundantbeing/hermes-browser-extension

    A Chromium side‑panel extension that connects your browser to a Hermes Agent (local, cloud, or remote). It streams active‑tab context, supports multi‑agent switching, smart tab scoping, site‑aware drafting (Hermes Assist), page comments, and optional live tab control, all with transparent diagnostics and nine visual themes.