AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Browser Automation/
vessel-browser
vessel-browser logo

vessel-browser

Active·★ 84·MIT·Updated 2026-05-29
★ Trending★ Workflow Automation★ API Integration

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.

Vessel is an open-source browser runtime for persistent web agents on Linux. It provides a real browser with durable state, MCP control, and a human-visible supervisory UI. It is built for long-running workflows where the agent drives and the human audits, intervenes, and redirects when needed.

#ai-browser#ai-browser-automation#ai-browser-control#ai-native-linux#ai-tools#autonomous-agents#byok#hermes-agent
$ Install
$ npm install -g @quanta-intellect/vessel-browser
↗ Visit site★ GitHub
01

Features

01Agent-first browser model — designed for an agent driving the browser while a human watches and intervenes
02Human-visible browser UI — pages render like a normal browser, keeping agent activity legible
03Command Bar (Ctrl+L) — secondary operator surface for harness-driven workflows and runtime commands
04Supervisor Sidebar (Ctrl+Shift+L) — live supervision with four tabs: Supervisor, Bookmarks, Checkpoints, and Chat
05Chat Assistant — built-in conversational AI with support for multiple providers and full browser tool access
02

Compatibility

Linux
Linux (x64)
Verified via docs
03

Quick start

1
$ npm install -g @quanta-intellect/vessel-browser
04

Use cases

↳Persistent web agent automation with human oversight for long-running tasks
↳Integration with agent harnesses like Hermes Agent or OpenClaw for browser control
↳Human-in-the-loop workflows where an agent performs actions and a human audits and intervenes
05

Alternatives

CopilotKit logo
CopilotKit★ 31.8k
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend.
vs →
mcp-chrome logo
mcp-chrome★ 11.8k
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
vs →
Auto-claude-code-research-in-sleep logo
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
vs →
awesome-claude logo
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
vs →
initrunner logo
initrunner★ 38
Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
vs →
qveris-agent-toolkit logo
qveris-agent-toolkit★ 229
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.
vs →
ninjaone-mcp logo
ninjaone-mcp★ 16
MCP server for NinjaOne — device monitoring, patching, scripting, and alert management tools for AI assistants
vs →
pilot-shell logo
pilot-shell★ 1.7k
How real engineers run Claude Code: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make Claude Code production-ready.
vs →
See all alternatives →

Related searches

vessel-browser AlternativesBest Browser Automation Tools 2026Open Source Browser Automationvessel-browser Tutorialvessel-browser Vs Competitorsai-browserai-browser-automationai-browser-control

Comments

Log in to leave a comment
  • O
    Oaklyn NguyenMay 12, 2026

    Browser built ground-up for agents rather than adapted from human-focused tools

  • S
    Sage JohnsonApr 22, 2026

    Open-source approach means you can inspect and trust what the agent is doing

  • M
    Marlowe KimApr 22, 2026

    Used for web research automation workflows, much more reliable than Playwright-based approaches

  • M
    Morgan WilsonMar 14, 2026

    The agent-native design avoids the fragility of WebDriver-based automation

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Stats
GitHub Stars★ 84
Last commit1d ago
StatusActive
LicenseMIT
CategoryBrowser Automation
Trend (30d)
+3.3↑ 0.7%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.