<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> Octogent addresses the complexity of managing multiple AI coding sessions by providing an orchestration dashboard for agents like Claude Code. It targets developers seeking to streamline multi-agent workflows on codebases, offering structured context management, task delegation, and inter-agent communication to reduce chaos and improve developer headspace.

How It Works

<2-4 sentences on core approach / design (key algorithms, models, data flow, or architectural choices) and why this approach is advantageous or novel.> The core concept uses "tentacles," scoped directories with markdown files (CONTEXT.md, todo.md) for specific tasks. This provides agents durable, local context beyond chat histories. Tasks in todo.md can spawn child agents, establishing parent-worker relationships. Octogent facilitates inter-agent messaging for status updates and handoffs, supported by a local API/UI for monitoring and orchestration, making multi-agent development more manageable.

Quick Start & Requirements

• Primary install / run command (pip, Docker, binary, etc.).
• Non-default prerequisites and dependencies (GPU, CUDA >= 12, Python 3.12, large dataset, API keys, OS, hardware, etc.).
• Estimated setup time or resource footprint.
• If they are present, include links to official quick-start, docs, demo, or other relevant pages.

For local development, install with pnpm install and run pnpm dev. For a global CLI install from a clone: pnpm install, pnpm build, npm install -g ., then octogent. Octogent is not yet published to npm. Prerequisites include Node.js 22+, Claude Code (or supported provider), git, gh, and curl. Official documentation links are available for Docs Home, Installation, Quickstart, Mental Model, etc.

Highlighted Details

• "Tentacles" act as context layers, isolating agent work to specific markdown files.
• todo.md serves as a visible, trackable execution surface for task delegation.
• Supports concurrent execution of multiple Claude Code terminals.
• Enables spawning child agents from tasks, creating a concrete source of truth for parallel work.
• Facilitates inter-agent messaging for reporting completion, blockers, and handoff notes.
• Provides a local API and UI for managing terminal lifecycle, persistence, and orchestration.

Maintenance & Community

The project maintains an active community presence via Discord (https://discord.gg/vtJykN3t) and is open to contributions, with guidelines available in CONTRIBUTING.md. Updates can be followed on X (https://x.com/Hesamation).

Licensing & Compatibility

The specific open-source license is not explicitly stated in the provided README. Compatibility is primarily demonstrated with Claude Code, with mention of support for other providers.

Limitations & Caveats

PTY sessions are not persistent across API restarts, though they survive browser reloads. The project is currently focused on Claude Code, and installation requires local building as it is not yet published to the npm registry.