back to top
HomeSoftwareKanBots: Open-Source AI Kanban Board for Claude Code & Codex Agents

KanBots: Open-Source AI Kanban Board for Claude Code & Codex Agents

- Advertisement -

File Info

FileDetails
NameKanbots
Versionv1.0.1
TypeAI Kanban Board / Multi-Agent Development Platform
DeveloperKanbots
LicenseMIT License (Open Source)
PlatformsWindows • macOS • Linux
Formats.exe • .dmg • .AppImage
Size110MB (may vary by OS)
Github Repositorygithub/kanbots

Description

Kanbots is a local-first AI kanban board designed for developers who want AI agents to work on multiple tasks in parallel instead of one conversation at a time.

You open a repository, drop it into Kanbots, and instantly get a visual board where every card can become its own autonomous AI task. Claude Code or Codex agents run inside isolated git worktrees, allowing multiple coding sessions to happen simultaneously without interfering with each other.

It treats AI agents more like active team members than chat assistants.

Agents can split tasks into subtasks, review their own work, iterate in autopilot cycles, run QA loops, and continue refining changes until tests pass or a budget limit is reached. The board updates live as agents work, showing logs, decisions, costs, branches, and progress in real time.

Kanbots stays heavily focused on local ownership. Everything lives inside the .kanbots/ directory within your project, database, configs, worktrees, attachments, and runtime state.

Use Cases

  • AI powered software development workflows
  • Parallel Claude Code or Codex task execution
  • Autonomous feature implementation
  • AI-assisted QA and testing loops
  • GitHub issue automation
  • Local AI project management
  • Multi-agent coding environments
  • AI backlog management
  • AI code review workflows
  • Self-evolving development pipelines

Screenshots

Features of Kanbots

FeatureDescription
Parallel AI AgentsRun multiple AI coding agents simultaneously
Git Worktree IsolationEvery agent gets its own isolated branch and worktree
Autopilot ModeAI agents iterate automatically until tasks converge
Multi-Persona WorkflowsProduct author, engineer, reviewer, tester personas
Live Agent ThreadsStream tool calls, logs, prompts, and decisions in real time
Drag-and-Drop Kanban BoardManage tasks visually across workflow stages
Claude Code SupportNative integration with Claude Code CLI
Codex SupportWorks with Codex execution workflows
GitHub ModeSync board state with GitHub Issues
Local-First StorageSQLite database stored locally
Sentry ImportPull Sentry issues directly onto the board
MCP ServerExpose Kanbots through Model Context Protocol
Branch PreviewLaunch and preview agent worktree environments
Promote to Commit / PRConvert agent work into commits or draft PRs
Decision PromptsHuman approval workflow during agent runs
Zero TelemetryNo tracking or remote analytics
You May Like: Goose: Open Source Local AI Coding Agent for Developers

Supported Agent Providers

CategorySupported Providers
AI Agent CLIsClaude Code • Codex
Git IntegrationsGit • GitHub
MCP SupportCursor • Claude Desktop • MCP-compatible tools
Error TrackingSentry

System Requirements

ComponentRequirement
Operating SystemWindows • macOS • Linux
Node.jsVersion 20+
Package Managerpnpm 10+
Required ToolsGit
AI CLIClaude Code and/or Codex installed

How to Install Kanbots?

Windows

  1. Download the .exe installer
  2. Open the installer
  3. Launch Kanbots
  4. Select a Git repository workspace

macOS

  1. Download the .dmg file
  2. Drag Kanbots into Applications
  3. Launch the app
  4. Choose your repository folder

Linux

  1. Download the .AppImage
  2. Make it executable
  3. Launch Kanbots
  4. Open a repository workspace

Download KanBots Open-Source AI Kanban Board

More Than Just an AI Coding Tool

Kanbots is closer to an AI development operating system than a simple coding assistant.

It combines autonomous agents, kanban workflows, git isolation, QA automation, and local project orchestration into a single desktop environment built around parallel execution.

For developers experimenting with AI-assisted engineering workflows, autonomous coding agents, or multi-agent software pipelines, Kanbots is one of the more interesting open-source projects currently emerging in the AI development tooling space.

LEAVE A REPLY

Please enter your comment!
Please enter your name here

YOU MAY ALSO LIKE
Osaurus Open-Source macOS AI App for Running Local LLMs Offline

Osaurus: Open-Source macOS AI App for Running Local LLMs Offline

0
Osaurus is a macOS-native AI harness designed around an idea "Your AI should belong to you." Instead of locking users into a single AI provider or cloud platform, Osaurus acts as a local control layer that sits between your AI models, tools, memory, and workflows. You can switch between local models running directly on Apple Silicon or connect cloud providers like OpenAI and Anthropic whenever you need extra power.
openhuman app

OpenHuman: Open-Source Personal AI Assistant With Memory, Voice & Integrations

0
OpenHuman is trying to make personal AI assistants feel less like developer tools and more like something you can actually live with every day. You install it, connect apps like Gmail, Notion, GitHub, Slack, or Calendar, and it starts building a private memory system from your data on your own machine. It feels closer to installing a desktop app and getting started in a few minutes. It also comes with a lot built in already including voice support, web search, coding tools, local AI through Ollama, and a memory system that stores everything as Markdown inside an Obsidian compatible vault. The agent keeps syncing connected apps every 20 minutes, so it slowly builds context around your work. The project is still in early beta, so there are rough edges, but the direction is interesting. Especially if you've been looking for an AI assistant that feels personal.
omlx Run Local AI Models on Your Mac With a Native Menu Bar App

oMLX: Run Local AI Models on Your Mac With a Native Menu Bar App

0
oMLX is one of the cleanest ways to run local AI models on a Mac. You install the app, download models, and manage everything from a native macOS menu bar app and web dashboard. It can keep frequently used context in memory, move older cache data to SSD automatically, run multiple models together, and work with tools like Claude Code, OpenCode, Codex, and OpenClaw. The admin dashboard is surprisingly useful too. You can download models, benchmark them, manage memory usage, and even run vision or OCR models from the same interface. If you already own an Apple Silicon Mac, this feels much closer to a proper local AI workspace than most open source inference tools right now. oMLX keeps model context cached across RAM and SSD storage, so repeated prompts and long coding sessions feel faster over time.

Don’t miss any Tech Story

Subscribe To Firethering NewsLetter

You Can Unsubscribe Anytime! Read more in our privacy policy