7-e1even
Featured
learn-agent
A step-by-step, zero-dependency tutorial series that distills production-proven engineering patterns from a real open-source desktop coding agent into runnable single-file code.
BossConsole
BOSS is an open-source, multi-platform desktop harness for AI agents that provides a governed environment with an embedded browser, terminal, code editor, plugin system, and over 100 MCP tools, allowing any agent to operate autonomously while the user stays in control.
Stars
184
7-day growth
No data
Forks
5
Open issues
9
License
Apache-2.0
Last updated
2026-07-25
Why it is worth attention
It is the first open-source, multi-platform harness for AI agents, built natively on the JVM with true multi-threading and live hot-reload, offering per-tool governance and a plugin ecosystem that can be evolved by the agents themselves.
Who it is for
- Developers using AI coding agents like Claude Code, Codex, Gemini, or OpenCode
- Researchers and scientists needing governed AI automation with real tools
- Enterprises requiring fine-grained RBAC and kill-switches for agent actions
- Power users who want a customizable, extensible desktop workspace for AI-assisted work
Use cases
- Run any AI coding agent with a real browser, terminal, editor, and secret management
- Share a live terminal session to a phone via QR code or to teammates with end-to-end encryption
- Scaffold and evolve custom plugins using AI agents, with hot-reload and PR integration
- Automate multi-step workflows with robotic process automation (RPA) and MCP tool orchestration
Strengths
- Open source (Apache-2.0) and cross-platform (macOS, Windows, Linux x64+ARM64)
- Native JVM runtime with true multi-threading and live plugin hot-reload
- Over 100 built-in MCP tools across ~20 plugins for terminal, browser, git, secrets, and automation
- Robust governance: server-enforced RBAC, per-tool kill-switch, user-scoped secrets, and signed plugins
Considerations
- MCP server is loopback-only and single-user (local machine), not designed for multi-user remote access
- Plugins run in-process with crash isolation but no OS-level sandboxing
- Embedded browser (Fluck) requires a JxBrowser license key for development builds
README quick start
🔬 The operator's console for AI agents — and the scientists who direct them
The first open-source, multi-platform harness for AI agents — an evolvable toolbox for agents and the humans they work with.
🧪 Built for enterprises, science, and research.
⚡ Natively multi-threaded — built on the JVM, not Electron — with live hot-reload and laptop-to-supercomputer scale.
Bring your own agent — Claude Code, Codex, Gemini, or OpenCode — and give it a real browser, terminal, editor, secrets, and automation. Then decide exactly what each one is allowed to touch. Run it on your own machine, hand a live terminal to your phone with a QR code, and reshape any tool — by hand or by the agent itself — while the app keeps running.
⬇ Download · 📊 Compare · 🤖 Run an agent · 🔐 Governance · 🧰 Toolbox · 🖥️ BossTerm
Just want to download BOSS? Head to BossConsole-Releases for pre-built installers.
Built with Kotlin Multiplatform and Compose Multiplatform, BOSS unifies an embedded browser, a blazing-fast shareable terminal, a code editor, an extensible Toolbox of plugins, and a governed MCP tool layer into one desktop workspace for complex, AI-assisted work.
How BOSS compares
Every other AI-agent desktop app and agentic IDE — Claude Desktop, OpenAI Codex, Google Antigravity, Cursor, and Windsurf/Devin — is closed source, and most lock you to a single vendor's model. BOSS is the first open-source, multi-platform harness in the category: Apache-2.0, cross-platform, and built to run any agent.
The deeper difference: BOSS is both the agent's home and an agent-operable app. The same MCP layer your agent uses to do work also exposes BOSS itself — its tabs, terminals, browser, editor, git, secrets, and automation — as 100+ mcp__boss__* tools. Read-only tools (list tabs, read a pane's output, tail the console, snapshot performance, inspect git) give an agent live **situational awareness of the works
Description
Open-source, multi-platform harness for AI agents — a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 100+ MCP tools. Built for enterprises, science & research.
Related repositories
Similar projects matched by category, topics, and programming language.
NousResearch
Featured
hermes-agent
Hermes Agent is an open-source, self-improving AI agent with a built-in learning loop that creates skills from experience, runs across platforms, and supports any LLM provider.
ogulcancelik
Featured
herdr
herdr is a terminal-based agent multiplexer that lets you monitor, manage, and interact with multiple AI agents in a single terminal session, with detachable sessions, a socket API for agents, and a plugin system.