GitKraken Desktop
GitLens for IDEs 
GitKraken MCP
GitKraken CLI
GitKraken Insights
Git Integration for Jira
Dev Team Automations
AI & Security Controls
Supercharge Your Dev Team 
Secure Your Dev Team 
Run more agents. Merge more code.
Kepler is GitKraken’s agentic development environment (ADE). It gives you full clarity and control to run parallel agents at scale: plan work, write code, and review what ships, all from one surface.
Start from where work already lives
Planning work means starting from what you already have: issues in your tracker, pull requests in your queue. Kepler connects those entry points to your agents so you go from “here is what needs doing” to “agents are on it” in one step, without rebuilding context or setting up sessions by hand.
Launch agents from your backlog
Select one or more issues and Kepler handles the setup and starts your agents. The work starts from the same place it always did. Agents just do more of it.
Start from a PR
Pick a pull request and Kepler spins up an agent to handle the review feedback, draft a fix, or start a follow-on change. You choose what to hand off and the agent gets to work.
One task, multiple repos
A database migration, an API change, and a front-end update can live inside a single Task. Kepler keeps them connected through shared context, so you see the full picture instead of three disconnected branches.
Every agent, in one view
When you are running agents across multiple repos, clarity is the thing that breaks first. Different terminals, no shared view, no signal about what is done and what is stuck. Kepler’s Kanban view puts every session on one board so you always know where the work stands.
Track every Task from Exploration to Done
Kepler’s Kanban columns match how agent work actually moves: Exploration, In Development, In Review, and Done. Each card shows the branch, the Task it belongs to, the repo, and the last thing the agent did. You see the whole pipeline at a glance.
Filter by what matters right now
Sessions are organized by status: Needs Attention, Active, Idle, Errored, and Inactive. Filter to just the sessions that need a decision and ignore the ones that are running fine. You focus where the work needs you.
See what each agent changed
An agent finishing a session is not the same as work that is ready to ship. You still need to see what it actually did. Kepler shows the diff and working changes for each branch alongside the task that created it, so you can review what changed in the same place you manage the work.
Review the diff in context
Open a worktree from your Task list and Kepler surfaces the files the agent changed. Click any file to see the diff. The changes sit right next to the task and session that produced them, no window switching required.
Stage files and commit without leaving Kepler
Once you have reviewed the changes, you can stage files and write your commit message in the same view. The work stays in one place from the moment the agent starts to the moment you commit.
Get a direct line to every Agent
The Console gives you a window into each agent session while it is running. You can read what the agent did and redirect it without leaving Kepler. When you are running several sessions at once, you can open them side by side and compare what each one produced.
A session for every agent, open when you need it
Each agent session has its own console panel showing the agent’s output, the changes it made, and a message input for new direction.
Multiple sessions, side by side
Open several session consoles at once and compare what each agent did across repos. When agents are working on related tasks, seeing their output together makes it faster to spot gaps or decide what to review first.
Course-correct before it compounds
Agents move fast. That speed is useful when pointed at the right thing. The Console gives you enough visibility to redirect early, so a wrong call does not turn into a large cleanup.
Works with your stack
Kepler does not replace what you are already using. Your existing setup stays. Kepler connects your agents, your Git provider, and your issue tracker and gives you one surface on top.
Works with Claude Code, Codex, and Open Code
Kepler works with the agents you are already running. Connect your existing setup and Kepler becomes the surface around it. You do not switch agents to use Kepler. You just get a better place to direct them.
Start from the tools you already use
Connect your issue tracker and your work starts from your existing backlog. Connect your Git provider and Kepler picks up your repos, branches, and PRs. No new workflow to learn from scratch.
This product is just amazing! It is exactly what i need as lead AI engineer.
David Bonan, Lead AI Engineer
Kepler is an amazing AI orchestration tool because it works with the AI CLI workflows I already use rather than locking me into a single model or ecosystem. It gives me a consistent flow for managing agents across different eco systems, in a simple familiar way, allowing me to focus on what matters rather than wrangling different agent CLIs.
Kevin Bost, Senior Software Architect
Unification of approach is what I’ve been doing for the past 30 years. I have been moving through things just trying to make it more simpler, more easier, more work. You’ve just done another one for me with Kepler. Thank you so much.
Jon Humphrey , Senior Front-End Engineer
Start from where work already lives
Planning work means starting from what you already have: issues in your tracker, pull requests in your queue. Kepler connects those entry points to your agents so you go from “here is what needs doing” to “agents are on it” in one step, without rebuilding context or setting up sessions by hand.
Launch agents from your backlog
Select one or more issues and Kepler handles the setup and starts your agents. The work starts from the same place it always did. Agents just do more of it.
Start from a PR
Pick a pull request and Kepler spins up an agent to handle the review feedback, draft a fix, or start a follow-on change. You choose what to hand off and the agent gets to work.
One task, multiple repos
A database migration, an API change, and a front-end update can live inside a single Task. Kepler keeps them connected through shared context, so you see the full picture instead of three disconnected branches.
Every agent, in one view
When you are running agents across multiple repos, clarity is the thing that breaks first. Different terminals, no shared view, no signal about what is done and what is stuck. Kepler’s Kanban view puts every session on one board so you always know where the work stands.
Track every Task from Exploration to Done
Kepler's Kanban columns match how agent work actually moves: Exploration, In Development, In Review, and Done. Each card shows the branch, the Task it belongs to, the repo, and the last thing the agent did. You see the whole pipeline at a glance.
Filter by what matters right now
Sessions are organized by status: Needs Attention, Active, Idle, Errored, and Inactive. Filter to just the sessions that need a decision and ignore the ones that are running fine. You focus where the work needs you.
See what each agent changed
An agent finishing a session is not the same as work that is ready to ship. You still need to see what it actually did. Kepler shows the diff and working changes for each branch alongside the task that created it, so you can review what changed in the same place you manage the work.
Review the diff in context
Open a worktree from your Task list and Kepler surfaces the files the agent changed. Click any file to see the diff. The changes sit right next to the task and session that produced them, no window switching required.
Stage files and commit without leaving Kepler
Once you have reviewed the changes, you can stage files and write your commit message in the same view. The work stays in one place from the moment the agent starts to the moment you commit.
Get a direct line to every Agent
The Console gives you a window into each agent session while it is running. You can read what the agent did and redirect it without leaving Kepler. Type a follow-up, paste a screenshot, or speak your instructions.
A session for every agent, open when you need it
Each agent session has its own console panel showing the agent's output, the changes it made, and an input for new direction. You can type, attach an image, or speak into your mic.
Multiple sessions, side by side
Open several session consoles at once and compare what each agent did across repos. When agents are working on related tasks, seeing their output together makes it faster to spot gaps or decide what to review first.
Course-correct before it compounds
Agents move fast. That speed is useful when pointed at the right thing. The Console gives you enough visibility to redirect early, so a wrong call does not turn into a large cleanup.
Works with your stack
Kepler does not replace what you are already using. Your existing setup stays. Kepler connects your agents, your Git provider, and your issue tracker and gives you one surface on top.
Works with Claude Code, Codex, and Open Code
Kepler works with the agents you are already running. Connect your existing setup and Kepler becomes the surface around it. You do not switch agents to use Kepler. You just get a better place to direct them.
Start from the tools you already use
Connect your issue tracker and your work starts from your existing backlog. Connect your Git provider and Kepler picks up your repos, branches, and PRs. No new workflow to learn from scratch.
integrate with your existing stack
Kepler works with the agents you are already running, your Git provider, and your issue tracker. Connect your existing setup and Kepler becomes the surface around it.
GitKraken Plans & Pricing
Kepler ADE is currently free for all users during a limited preview period. Try it now or buy a GitKraken plan to secure your long-term access.
Full Clarity. Full Control. for free
Connect your existing agents, start a Task from your backlog or PR queue, and see what it looks like to run agents at scale without losing track of anything. Free to try.
Kepler Faqs
Kepler is GitKraken’s agentic development environment (ADE), which means it helps you kickoff coding agent sessions across multiple repos.
It gives developers full clarity and control to scale their use of parallel agents, across planning work, writing code, and reviewing what ships. You start from your existing backlog or PR queue, run agents across multiple repos, and see every session from one surface.
An ADE (Agentic Development Environment) is the workspace built for a developer whose primary job is no longer writing code but directing AI agents that write it. Where an IDE was built for one developer typing code, an ADE is built for one developer running multiple agents in parallel. Kepler is GitKraken’s ADE.
GitKraken Desktop is built for one developer, one agent, one repo at a time. Kepler is built for developers scaling parallel agents across multiple repos simultaneously. If you are already using GitKraken Desktop and managing several agents, Kepler is the next step. GitKraken Desktop remains the right tool for focused, single-repo work.
Kepler is agent-agnostic, and it currently integrates with v
Connect the agent you are already using and Kepler manages the sessions, visibility, and review around it. See the [integrations page] for the current list of supported agents.
A Task is the container that holds your work across repos. You start one from an issue in your tracker (like Jira, Linear, Trello, GitHub Issues, or GitLab Issues) or a PR in your queue. Kepler creates the worktrees, launches your agents, and keeps everything connected through shared context. A Task can span any number of repos.
Yes. Kepler connects to your issue tracker so you can select issues and have agents start on them directly. Connect to Jira, Linear, Trello, GitHub Issues, or GitLab Issues. You can also pick a pull request and have an agent handle the follow-on work. The entry points are the same ones you already use.
Yes. Kepler works with GitHub Enterprise and GitLab Self-Managed. Connecting to a self-hosted service requires a Personal Access Token with the appropriate permissions. See the Integrations documentation for setup instructions.
Add to Chrome
Add to Firefox
Add to Microsoft Edge