Skip to content
ENDE
 Try it free

Your AI teammate.
Just talk to it.
Proof it works.

Tell kanman what you need, in the app, in Slack or in Microsoft Teams. It drafts the stories, ships them through Claude Code or Codex under your rules, proves every change against your acceptance criteria and tells you how it went. Hosted in the EU or on your own servers.
Start the 14-day trial Team plan, no card needed See how it works
A requirement from finance for the Sandbox Team is typed into the general conversation. kanman offers to continue in the team's chat, the conversation moves there beside the team's board, and kanman drafts three stories with acceptance criteria, which are approved and written to the tracker. The first story is moved to Ready on the board and kanman starts planning. kanman asks to approve the plan, the plan is approved in the conversation, and the run passes every check on a clean checkout. The pull request is merged, the story moves to Done with its criteria, tests and cost, and the weekly report sums up the week.

The gap

Everyone on your team has an AI coding tool. Nobody has an AI teammate.

Copilot and Claude Code licenses make each developer faster. They don't decide what gets built, what the agent may touch, or whether the result works.

  • Nobody owns intake.

    Someone still has to turn requests into work an agent can finish. Vague tickets in, vague code out.

  • Nobody sets the rules.

    Nobody decided what the agent may touch, spend or merge. So either it can't do much, or it can do too much.

  • Nobody proves the result.

    'Tests pass' is not 'it works'. Somebody has to check, and right now that somebody is your best reviewer.

How it works

From a conversation to a reviewed pull request

You talk, kanman does the rest in five stages. Your tracker, your CI and your review rules stay where they are.

  1. 1. Tell kanman

    Describe the work in the app, in Slack or in Microsoft Teams. kanman asks what is unclear and drafts stories with acceptance criteria and a way to demonstrate each one.

  2. 2. Rules

    Your policy decides what kanman may touch, spend and merge. Big calls come to you with a recommendation.

  3. 3. Work

    Claude Code or Codex does the coding in a sandbox. kanman picks the model by complexity, so trivial fixes stay cheap.

  4. 4. Proof

    Before anything reaches review, an acceptance spec runs against a fresh environment. No spec, no Ready. No green run, no review.

  5. 5. Hear back

    kanman tells you the pull request is ready, with the evidence attached. Your people review and merge, or your policy does.

Walk through a full example

kanman tells you

It tells you what happened. It asks only when it needs you.

No dashboard to check, no status to chase. kanman writes to you in the app, in Slack or in Microsoft Teams, in one voice and in a few sentences.

  • Updates when something happened

    A run finished, a failure it handled, a convention it learned. Each update links to the run or the evidence pack. When nothing happened, it stays quiet.

  • Decisions where you read them

    When your policy says a call needs you, kanman asks one question with its recommendation and the options. You answer right there, in the app or in your channel.

  • A weekly report you can forward

    Stories merged, rework and time to review, with the reason behind each change. Ask a follow-up in the same conversation.

Talks to you in

  • The kanman app
  • Slack
  • Microsoft Teams
The team's chat with kanman beside its board: updates about runs with their stage and cost, the evidence of a finished run and a decision with kanman's recommendation and its options

Proof

Agents say "done". kanman shows you.

Every pull request comes with an evidence pack. You review the change knowing it already does what the story asked for.

  • The spec was written before the code.

    kanman writes the acceptance spec at intake. It has to fail before the story counts as Ready.

  • The agent cannot edit it.

    The coding agent has no write access to the spec. A changed spec fails the gate.

  • It ran on a clean checkout.

    Not on the agent's machine. A fresh environment, the pull request's commit, nothing cached.

Evidence pack of a finished run: 3 of 3 acceptance criteria passed, the acceptance spec passed in a clean environment, 14 tests and CI passed, cost and duration

See it on your own repo.

The Team plan is free for 14 days, no card needed. You keep the evidence either way.

Start the 14-day trial

Control

You decide how much it decides.

Presets from Trial to Autonomous. Budgets with hard stops. Every decision in an audit log you can export.

Team settings, Autonomy: the trust dial from Trial to Hardening on Balanced, and the steps from intake to live with who decides at each
kanman asks in the conversation: approve the plan for a story? With kanman's recommendation and the options Approve plan, Request changes and Reject

  • Authority levels

    Per repo and path. What kanman may change alone, what needs a review, what it never touches.

  • Budgets with hard stops

    Per run, per day and per month. When a budget runs out, kanman stops and asks. Incident work is never blocked.

  • An audit log you can export

    Who decided what, on whose approval, at what cost. Ready for the next audit.

Team memory

It gets better at your codebase every week. You can see what it learned.

Review comments that repeat become team conventions. You can read, edit and retire every one.

Lineage you can follow
Every convention links back to the review comments it came from.
You stay the editor
Pin a rule, reword it or retire it. kanman follows the current list.
A team's conventions: the rule learned from three review findings, with its areas and the actions Pin, Edit and Retire

Fits your stack

Your tracker stays. Your CI stays. Your review rules stay.

kanman joins the tools your team already runs. Nothing to migrate.

  • GitHub: Issues, pull requests, checks
  • GitLab: Cloud and self-managed
  • Jira: Your boards, your column names
  • Claude Code: Headless, in a sandbox
  • Codex: Headless, in a sandbox
  • Slack: Questions, requests and decisions in your channels
  • Microsoft Teams: Channels, group chats and direct messages
  • Confluence, Notion, SharePoint: Answers from your docs and Git wikis, with sources
  • Your CI: GitHub Actions, GitLab CI and the rest
  • Self-hosted runner: Coding runs inside your network
  • kanman board: No tracker yet? Stories live on the team's own board
  • MCP: Use kanman from Claude Code or Codex

Pricing

Priced per AI team. Not per seat.

Start free on your own machine. Try the Team plan for 14 days, no card needed.

Local

The kanman board and the kanman MCP in your own Claude Code or Codex. Your machine does the work.

€0per AI team
  • The kanman board for your team's stories, decisions and history
  • The kanman MCP for Claude Code or Codex on your machine
  • Cloud runs, runners and the outcome gate start with Starter
Start free

Starter

kanman works your stories under your rules and proves every change.

€99per AI team / month

Billed monthly, no minimum term. Cancel to the end of any billing month.

  • Cloud sandboxes in Frankfurt or your own runner, including runner-only mode
  • One tracker - GitHub Issues, Jira or GitLab
  • Outcome gate with acceptance specs and evidence packs
  • Decisions and audit log
  • 2 runs in parallel
Start the 14-day trial

14 days free

Team

kanman as a full teammate, in your channels and on call.

€249per AI team / month

Billed monthly, no minimum term. Cancel to the end of any billing month.

  • Everything in Starter
  • Context connectors for your docs, wikis, Confluence, Notion and SharePoint
  • Maintenance scans and on-call
  • Slack and Microsoft Teams
  • 5 runs in parallel
  • Up to 15 people per team. Larger team? Talk to us.
Start the 14-day trial

Enterprise

For several teams and stricter requirements. Contracted for the number of teams you need.

from €1,000per month
  • SSO and SCIM
  • Long audit log retention
  • Custom DPA and SLA
  • Optional self-hosted control plane
  • Up to 20 runs in parallel
Talk to us

14 days of the Team plan, free

Every new team gets the Team plan for 14 days, without a card. When the trial ends, cloud runs pause until you pick a plan. Your board and the Local plan keep working.

Start the 14-day trial

Guided onboarding

Want us to set kanman up with your team? Guided onboarding is available on request, with any paid plan, priced for your setup.

Ask about onboarding

Model usage runs on your own keys (Anthropic, OpenAI, Azure OpenAI or Amazon Bedrock), or is passed through at provider cost plus 15%. No per-seat pricing.

Prices are net. No VAT is added, as kanman is a small business under section 19 UStG.

FAQ

Questions engineering leads ask us

Short answers. Each one links to the long version.

Something missing? Email [email protected]
How is this different from assigning issues to Copilot, Claude or Codex in GitHub or Linear?
Those tools hand an issue to an agent and give you a pull request back. kanman adds what sits around the agent. It turns requirements into stories with acceptance criteria, follows the policy you set, and proves each change against those criteria on a clean checkout before anyone reviews it. The coding itself still runs on Claude Code or Codex. Read the docs (opens in a new tab)
What does working with kanman look like day to day?
You talk to it. Describe the work in the app, in Slack or in Microsoft Teams, and kanman drafts the stories, works them under your team's rules and proves the result. It tells you when something is ready, asks when a decision needs you and sends a weekly report. The board, runs and evidence packs open from the conversation when you want the details. Read the docs (opens in a new tab)
Do we have to leave Jira or GitHub?
No. kanman works in your tracker, whether that is GitHub Issues, Jira or GitLab. Stories, status changes and pull requests show up where your team already looks. No tracker yet? A team can keep its stories on its own kanman board and connect a tracker later. Read the docs (opens in a new tab)
Which models and agents does it use? Can we use our own contracts?
The coding runs through Claude Code or Codex. You can bring your own keys for Anthropic, OpenAI, Azure OpenAI or AWS Bedrock, or your company's OpenAI-compatible AI gateway, or let kanman pass usage through at cost plus 15%. kanman picks the model by complexity, so small fixes stay cheap. Read the docs (opens in a new tab)
Where is our code processed and stored? What do model providers see?
kanman runs in the EU. Coding happens in sandboxes in Frankfurt, and every run gets a fresh sandbox that is thrown away afterwards. Model providers see the prompts and code context a run needs, under your own contract if you bring your keys. With the self-hosted runner, code execution stays in your network. Read the docs (opens in a new tab)
Can it merge to main on its own?
Only if your policy says so. By default a person reviews and merges. You can allow automatic merges for small changes: every gate green and the diff under a line limit you set. While main is red, kanman holds them. Read the docs (opens in a new tab)
What happens when it gets stuck?
It stops and asks. You get a decision with its recommendation and the options, in the app, in Slack or in Microsoft Teams. A failed gate gets one rework attempt. After that it comes back to you instead of looping. Read the docs (opens in a new tab)
Can kanman be on call for the services we run?
Yes, if you want it to. Connect uptime checks, your alerting tool (Alertmanager, Grafana, Datadog, PagerDuty, Opsgenie, Sentry, CloudWatch and others) and your logs. When something degrades, kanman opens an incident in your Slack or Teams channel, looks at recent merges, deploys and error traces, and posts what it finds. For a bug in the code it starts a fix that has to reproduce the error first, or proposes a revert. Changes to production outside the code always go to a person. Observe only is one switch away. Read the docs (opens in a new tab)
Does kanman take part in our Slack or Microsoft Teams conversations?
Only where you add it. It answers questions about the team's work with links and sources, and turns requests into story drafts that a lead approves before anything reaches the board. By default it speaks only when mentioned. Per channel you can let it speak up, with a daily cap, quiet hours and a stop button on every unprompted reply. Read the docs (opens in a new tab)
Can it answer from our docs, repos, wikis, Confluence, Notion or SharePoint?
Yes, once a team switches it on. Add uploads, web pages, repository docs, issues, GitHub or GitLab wikis, Confluence spaces, Notion pages or SharePoint sites (library files and site pages), and kanman names its sources in every answer. Where the source can tell, it only uses what the person asking may see there, such as Confluence page permissions or repository access; SharePoint sources are shared with the whole team. If nothing fits, it says so. Read the docs (opens in a new tab)
What does it cost to run, and how do budgets work?
Every plan is a flat price per AI team, never per seat, listed in the pricing section. Local is free, Starter and Team are billed monthly, Enterprise is contracted for the number of teams you need. Model usage comes on top, on your own keys or at provider cost plus 15%. You set budgets per run, per day and per month with hard stops. Incident work is never blocked by a budget. Read the docs (opens in a new tab)
Our repo has no acceptance tests. Can we still start?
Yes. The Trial preset works without specs and says so plainly in every evidence pack. In the first week kanman opens one pull request that adds an acceptance manifest. From then on every story gets a spec. Read the docs (opens in a new tab)
Can we self-host?
Yes. The self-hosted runner comes with every paid plan from Starter and does all code execution inside your network, with your model contracts. Switch on "Run everything on our runners" and model calls, reviews and every repository action stay there too; kanman's cloud keeps the board, the decisions and the audit log. With Enterprise, kanman's control plane can run on your own servers as well. Read the docs (opens in a new tab)
Can we try it before we pay?
Yes. Every new team gets the Team plan free for 14 days, no card needed. When the trial ends, cloud runs pause until you pick a plan; your board and the free Local plan keep working. If you would like us to set kanman up with your team, guided onboarding is available on request. Guided onboarding

Blog

From the blog

All posts
ai

Issue to PR Is a Commodity. Here's What Isn't.

GitHub, Linear, Jira and OpenAI all turn issues into pull requests now. The loop is free. What your team still doesn't have is the operating model around it: who writes the work, who sets the rules, and who proves the result.

Marco Kerwitz

Founder of kanman.ai

ai

Don't Trust an Agent That Says Done

Coding agents grade their own homework. kanman doesn't let them: an acceptance spec is written before the code, must fail before work starts, can't be edited by the agent, and has to pass on a clean checkout before anyone is asked to review.

Marco Kerwitz

Founder of kanman.ai

ai

Agents Need a Policy, Not a Better Prompt

"Please don't touch the billing module" in a system prompt is not a rule. It's a wish. kanman replaces wishes with a policy: authority levels, presets, budgets with hard stops, decisions that come with a recommendation, and an audit log you can export.

Marco Kerwitz

Founder of kanman.ai