agent-kanban
agent-kanban is an open-source orchestration platform that provides an agent-first kanban board for managing AI coding assistants. It implements a leader-worker model where a central coordinator assigns tasks to multiple AI agents running in parallel, enabling teams to scale their development efforts across multiple runtimes. The system supports multiple AI backends including Claude Code, Codex, and Gemini CLI, allowing users to leverage different models based on task requirements. The platform features cryptographic agent identity, meaning each AI worker is assigned a unique, verifiable identity that signs commits and actions, ensuring accountability and auditability in code changes. A built-in real-time WebSocket relay (backed by Cloudflare Durable Objects) provides live updates on agent progress, tool use, and conversation history directly to the kanban dashboard. Agents can work simultaneously on independent tasks, and the board visually tracks their states through columns like Backlog, In Progress, and Done. agent-kanban is deployed as a self-hosted service typically on Cloudflare Workers, offering a serverless architecture that scales with demand. It includes a web-based admin panel for user and agent management, and integrates with popular Git hosting services to trigger agent workflows on events like pull requests. The project is actively maintained and aims to simplify the coordination of multiple AI coding agents in complex software projects.
- Category
- AI Agents
- Pricing
- Open Source
Problem solved
Development teams using AI coding assistants often struggle to coordinate multiple agents working on different tasks simultaneously, leading to conflicts, duplicate work, and loss of accountability. agent-kanban solves this by providing a centralized kanban board that distributes tasks to AI agents with unique cryptographic identities, enabling parallel execution, real-time monitoring, and verifiable agent contributions, thereby increasing development velocity and trust in AI-generated code.
Use cases
- Coordinating a fleet of AI agents to implement multiple features or bug fixes concurrently in a monorepo.
- Running automated refactoring or code modernization tasks across a large codebase by distributing work to specialized agents.
- Creating a CI/CD pipeline that triggers an AI agent on pull requests to review code, run tests, and suggest fixes.
- Managing a kanban board where human developers and AI agents collaborate, with agents autonomously picking up and completing tasks.
- Auditing AI agent contributions through cryptographic signatures for compliance or team oversight.
- Experimenting with different AI runtimes (Claude Code, Codex, Gemini CLI) on the same project to compare performance and cost.
Audience
- Developers
- ML Engineers
- Data Scientists
Pros
- Enables parallel execution of AI agents, significantly speeding up large development tasks.
- Leader-worker model simplifies agent coordination and task distribution.
- Cryptographic agent identity provides verifiable commit attribution and enhances security.
- Real-time WebSocket relay offers live progress visibility and interactive history.
- Multi-runtime support allows selecting the best AI model for each task.
Cons
- Requires operational knowledge to self-host and manage multiple AI runtimes.
- Documentation may be limited, making initial setup and customization challenging.
- Single point of failure if the orchestration layer goes down (though serverless architecture mitigates this).
Official website: https://github.com/saltbo/agent-kanban
Canonical LambdaBase page: https://www.lambdabase.com/tools/agent-kanban