multica
Multica is an open-source, agent-first kanban board designed to orchestrate multiple AI coding agents across various runtimes. It provides a visual workspace where users can create tasks, assign them to different agents, and monitor progress in a card-based interface. The platform supports a leader-worker model, allowing a central 'leader' agent to decompose complex projects into sub-tasks and delegate them to specialized worker agents, each potentially running on different underlying language models and runtimes such as Claude Code, Codex, or Gemini CLI. Built for extensibility, Multica enables users to define custom agent skills (e.g., web design guidelines) and attach relevant context or files to tasks. It includes robust attachment handling with secure download endpoints, support for self-hosted S3-compatible object storage, and configurable download modes for private deployments. All interactions and transcripts are timestamped, providing a detailed audit trail of agent activities. Multica is designed to be self-hosted, with Docker Compose files and extensive environment variable configuration available. It features a Go backend, React/TypeScript frontend, and CLI/desktop/mobile client interfaces, ensuring accessibility from multiple environments. The system emphasizes agent identity management, task queuing, and real-time updates via WebSockets, making it suitable for teams that need a private, customizable agent orchestration layer. Key features include a drag-and-drop kanban board, multi-runtime agent execution, skill integration, user management, and fine-grained control over how agents interact with file storage. Its active development community (over 36k GitHub stars and 3.5k commits) continuously expands capabilities like improved transcript visibility and multi-platform client support.
- Category
- AI Agents
- Pricing
- Open Source
Problem solved
Development teams and individuals leveraging AI coding agents face difficulty coordinating multiple agents working on concurrent or interdependent tasks. Without a centralized management layer, tracking progress, sharing context, and ensuring consistent outputs becomes chaotic. Multica solves this by providing a visual kanban board where tasks can be created, assigned to specific agents (each with its own runtime and skills), and moved through custom workflows. It centralizes agent communication, attachments, and transcripts, enabling teams to orchestrate complex coding projects efficiently while maintaining full control over their data through self-hosting.
Use cases
- Orchestrating a swarm of AI agents to refactor a monolithic codebase into microservices, with one agent managing architecture and others handling individual services.
- Assigning web design enhancement tasks to multiple agents, each using a predefined design-guidelines skill to ensure visual consistency.
- Managing a bug-fixing sprint where agents automatically pick up reported issues from the kanban 'Backlog' column, generate patches, and move cards to 'Review'.
- Self-hosting an enterprise agent workspace that complies with data residency requirements, with all attachments and transcripts stored on a private S3 bucket.
- Using the CLI client to script agent task creation and integrate Multica into existing CI/CD pipelines for automated code generation and review.
- Teaching a team new to AI agents by providing a visual interface to assign simple coding tasks and gradually increase complexity as confidence grows.
Audience
- Developers
- ML Engineers
- Data Scientists
- Enterprise
Pros
- Full control over data and infrastructure through self-hosting
- Visual kanban board simplifies multi-agent task management
- Supports multiple language model runtimes out of the box
- Extensible with custom skills and attachment handling
- Active development with regular updates and strong community
Cons
- Requires technical expertise for initial setup and configuration
- Documentation is sparse and mostly inferred from source code
- Lacks built-in cloud SaaS option, limiting quick adoption for non-technical users
Official website: https://github.com/multica-ai/multica
Canonical LambdaBase page: https://www.lambdabase.com/tools/multica