3d0b4d19b7
* feat: chroots * wip * Update workspace templates and Playwright tests * Fix thinking panel close button not working during active thinking The auto-show useEffect was including showThinkingPanel in its dependency array, causing the panel to immediately reopen when closed since the state change would trigger the effect while hasActiveThinking was still true. Changed to use a ref to track previous state and only auto-show on transition from inactive to active thinking. * wip * wip * wip * Cleanup web search tool and remove hardcoded OAuth credentials * Ralph iteration 1: work in progress * Ralph iteration 2: work in progress * Ralph iteration 3: work in progress * Ralph iteration 4: work in progress * Ralph iteration 5: work in progress * Ralph iteration 6: work in progress * Ralph iteration 1: work in progress * Ralph iteration 2: work in progress * Ralph iteration 3: work in progress * Ralph iteration 4: work in progress * Ralph iteration 5: work in progress * Ralph iteration 6: work in progress * Ralph iteration 7: work in progress * Ralph iteration 1: work in progress * Ralph iteration 2: work in progress * improve readme * fix: remove unused file * feat: hero screenshot * Update README with cleaner vision and hero screenshot Simplified the vision section with "what if" framing, removed architecture diagram, added hero screenshot showing mission view.
Open Agent
Self-hosted control plane for AI autonomous agents
Isolated Linux workspaces and git-backed Library configuration
Vision · Features · Ecosystem · Screenshots · Getting Started
Vision
What if you could:
Hand off entire dev cycles. Point an agent at a GitHub issue, let it write code, test by launching a Minecraft server, and open a PR when tests pass. You review the diff, not the process.
Run multi-day operations unattended. Give an agent SSH access to your home GPU through a VPN. It reads Nvidia docs, sets up training, fine-tunes models while you sleep.
Keep sensitive data local. Analyze your sequenced DNA against scientific literature. Local inference, isolated containers, nothing leaves your machines.
Features
- Mission Control: Start, stop, and monitor agents remotely with real-time streaming
- Isolated Workspaces: Containerized Linux environments (systemd-nspawn) with per-mission directories
- Git-backed Library: Skills, tools, rules, agents, and MCPs versioned in a single repo
- MCP Registry: Global MCP servers running on the host, available to all workspaces
- Multi-platform: Web dashboard (Next.js) and iOS app (SwiftUI) with Picture-in-Picture
Ecosystem
Open Agent is a control plane for OpenCode, the open-source AI coding agent. It delegates all model inference and autonomous execution to OpenCode while handling orchestration, workspace isolation, and configuration management.
Works great with oh-my-opencode for enhanced agent capabilities and prebuilt skill packs.
Screenshots
Real-time monitoring with CPU, memory, network graphs and mission timeline
Git-backed Library with skills, commands, rules, and inline editing
MCP server management with runtime status and Library integration
Getting Started
Prerequisites
- Rust 1.75+
- Bun 1.0+
- OpenCode server
- Linux host (Ubuntu/Debian for container workspaces)
Backend
export OPENCODE_BASE_URL="http://127.0.0.1:4096"
cargo run --release
Dashboard
cd dashboard
bun install
bun dev
Open http://localhost:3001
Status
Work in Progress — This project is under active development. Contributions and feedback welcome.
License
MIT