🐼 OpenPanda

The Open-Source, Local-First Multi-Agent Orchestration OS

English · 简体中文 · 日本語 · Español · Deutsch

About

OpenPanda organizes terminal AI coding agents (Claude Code, OpenAI Codex, Grok Build, DeepSeek Harness, OpenCode, and more) together with your devices into a single execution crew. You issue one instruction; it handles intent classification, task decomposition, dispatch, execution supervision, and result verification — all locally, with zero cloud dependency.

┌─────────────────────────────────────────────────────────────┐
│                      You: One Command                       │
│           (Terminal TUI / Web Console / CLI Script)         │
└──────────────────────────────┬──────────────────────────────┘
                               │
                  ┌────────────▼────────────┐
                  │     🐼 OpenPanda OS     │
                  │   Route, Orchestrate,   │
                  │     Verify & Secure     │
                  └────────────┬────────────┘
                               │ Direct P2P WebSocket (no cloud relay)
     ┌─────────────────────────┼─────────────────────────┐
     │                         │                         │
┌────▼──────────────┐   ┌──────▼────────────┐   ┌────────▼────────────┐
│  MacBook (Worker) │   │  Linux Build Box  │   │  Raspberry Pi / SBC │
│  - Claude Code    │   │  - Codex / Docker │   │  - 24/7 Daemons     │
└───────────────────┘   └───────────────────┘   └─────────────────────┘

The project evolves along two tracks:

✨ Features

Agent Orchestration

• Intent classification & task decomposition — the engine distinguishes chat, management queries, and executable tasks; multi-stage work is first split into a plan with artifact wiring between stages.
• Supervision loop — the entry model continuously judges task completion and re-dispatches with the failure reason attached, until done or the round budget (5 rounds by default) is spent.
• Transparent failover — quota exhaustion or dead credentials (401/403) trigger automatic fallback-model injection; the task continues instead of dying halfway.
• Transparent execution — every Bash command, file edit, and tool call, along with the responsible agent and underlying model, streams live to your terminal and console.
• Tiered approval — reversible operations run autonomously; irreversible actions (git push, production database changes) suspend for explicit human confirmation.
• Circuit breakers — loop detection and retry breakers stop runaway agents from burning tokens.

Memory & Skills

• Dual-layer memory — user preferences (USER.md) and project facts (MEMORY.md) are strictly separated.
• Self-evolving skills — successful workflows are distilled into SKILL.md playbooks that accumulate over time.
• Skills Hub & autonomous discovery — a curated offline catalog (panda skill hub), importing from a path, URL, or archive (panda skill import), and an assistant that finds and installs the skill a task needs mid-flight.
• Traveling context — delegated tasks carry project memory and a workspace digest to the executing node.

Multi-Device Collaboration (Preview)

• Capability cards — each node auto-declares its hardware and tool profile (CPU, RAM, OS, available agents).
• P2P mesh — nodes communicate over authenticated, encrypted WebSocket; data never leaves your private network.
• Capability-based routing — the scheduler scores nodes and routes each task to the best match.

Interfaces & Runtime

• Terminal TUI (Bubble Tea): full-screen alternate-screen mode with keyboard navigation, first-run onboarding wizard, live progress, mid-turn steering.
• Web console: zero-config kanban, real-time SSE streaming, skills management, session cancellation, automatic browser login.
• Scriptable CLI: panda ask drops straight into automation scripts.
• Featherweight: single static Go binary, ~20MB RSS, no external runtime dependencies.

📦 Installation

macOS / Linux:

curl -fsSL https://raw.githubusercontent.com/Xustalis/OpenPanda/main/scripts/install.sh | sh

macOS (Homebrew):

brew tap Xustalis/openpanda
brew install openpanda

Windows (PowerShell):

irm https://raw.githubusercontent.com/Xustalis/OpenPanda/main/scripts/install.ps1 | iex

🚀 Quick Start

Initialize your node (interactive setup for device name, model providers, and the local capability card):

panda init

Then pick an entry point:

panda                                                # interactive terminal TUI
panda web                                            # web console, opens browser automatically
panda ask "check system status and summarize tasks"  # one-shot command

To connect a second device (preview capability): run panda pair on device A to get a pairing code, then panda nodes add <device-A-address> on device B.

🛠️ CLI Cheat Sheet

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│ cmd/panda      Interactive TUI · Web Console · CLI          │
├─────────────────────────────────────────────────────────────┤
│ askengine      Intent classification · management tools     │
│ plan           Multi-stage decomposition & artifact wiring  │
│ commander      3-Tier execution: Native · Agent · Manual    │
│ defense        Tiered gating · circuit breakers · anti-loop │
│ memory         Dual-layer memory (User/Project) + Skills    │
├─────────────────────────────────────────────────────────────┤
│ scheduler      Multi-device scoring & task routing          │
│ bus / ledger   P2P WebSocket transport · HMAC auth · ledger │
│ storage        Pure Go SQLite (WAL mode)                    │
└─────────────────────────────────────────────────────────────┘

🗺️ Roadmap

🔭 Vision

OpenPanda's architecture is designed for large-scale heterogeneous clusters: drone swarm control, communication scheduling for deep-space satellite constellations, and coordinated autonomous-vehicle fleets. These scenarios share one fundamental problem — every node has different compute, different capabilities, and different jobs, yet all need to be coordinated, scheduled, and supervised together.

Today, OpenPanda serves a developer's devices and agents. The long-term goal is to extend the same orchestration kernel to autonomous nodes at cluster scale.

🤝 Contributing

1. Read CONTRIBUTING.md for code standards and workflow.
2. Check SECURITY.md for security guidelines.
3. Abide by the CODE_OF_CONDUCT.md.
4. Run make gate locally before submitting a PR.

📄 License

MIT License