Zot Chrome Operator: Let Your Terminal AI Agent Drive the Browser via Side Panel

Zot Chrome Operator bridges your terminal-based coding agent zot with Chrome, letting zot operate browser tabs via a browser_action tool. The project by Patrice Eckhart provides a Chrome side panel for chatting with zot and a local WebSocket bridge that executes browser actions.
Installation
No changes to zot itself required. Run:
zot ext install https://github.com/patriceckhart/zot-chrome-operator node "$HOME/Library/Application Support/zot/extensions/zot-chrome-operator/bin/install-cli.js"
The second command creates a zot-chrome shim at ~/.local/bin/zot-chrome. Ensure that directory is on your PATH (add export PATH="$HOME/.local/bin:$PATH" to your shell profile if needed). The shim is auto-refreshed on next zot start, but running install-cli.js makes it available immediately.
Setup Steps
- Build the Chrome extension:
zot-chrome extprints the path to the unpacked build (e.g.,/Users/you/Library/Application Support/zot/extensions/zot-chrome-operator/dist). Load it in Chrome viachrome://extensionswith Developer mode enabled → Load unpacked. - Start the bridge:
zot-chrome startbuilds the extension if needed and starts the bridge in the background. The bridge runszot rpc --no-sessionand listens onws://localhost:9224. - Environment variables:
ZOT_PROVIDER=anthropic ZOT_MODEL=claude-sonnet-4-5 zot-chrome startorPORT=9225 zot-chrome startto customize.
Commands
zot-chrome start– Start the bridge server in backgroundzot-chrome stop– Stop the bridgezot-chrome status– Check bridge statezot-chrome logs– Tail bridge logszot-chrome ext– Print or build the unpacked extension path
Browser Capabilities
The registered zot tool can: list, create, switch, and close tabs; inspect page context; navigate; click; type into native and rich editors; select options; scroll; extract page text; and wait. No session is persisted — the bridge uses zot --no-session.
The bridge logs all actions, viewable with zot-chrome logs.
📖 Read the full source: HN AI Agents
👀 See Also

Helix: Open-Source Framework Turns Claude into Personal AI Agent for macOS
Helix is an open-source framework that connects Claude via Claude Code in Terminal to macOS through four MCP server plugins, enabling Claude to control applications, maintain persistent memory, run scheduled tasks, and operate with local voice processing.

Kios: An iOS Reader for Self-Hosted Kobo/Calibre Libraries with Progress Sync
Kios is an iOS app that reads books from self-hosted Kobo/Calibre servers and syncs reading progress via the Kobo protocol, OPDS 1.2/2.0, and kosync. Built with Claude Code.

LM Studio parser bugs break Qwen3.5 tool calling and reasoning
LM Studio's server parser has three interacting bugs that silently break tool calling, corrupt reasoning output, and make models appear worse than they are. The issues affect reasoning models like Qwen3.5 and DeepSeek-R1, with one bug reported over a year ago still unresolved.

Open-source multi-agent framework extracted from Claude Code leak
A developer extracted the multi-agent orchestration system from Claude Code's leaked source code and rebuilt it as a model-agnostic open-source framework with MIT license. The 8,000-line TypeScript framework includes task scheduling, inter-agent messaging, and built-in tools.