// code agents · on-premises

Your backlog closes itself.
On your server.

From a natural-language requirement to an approved merge request: an AI analyst turns your goals into tickets, agents write the code, and every change goes through peer-review cycles — with human control where it matters. Everything runs on your infrastructure: your code never leaves.

sprint-42 · acme/api
Backlog4
TK-311Paginate the invoices list
TK-314Migrate auth to refresh tokens
TK-317CSV export for reports
In progress2
TK-305Fix: webhook timeouts
agent coding
TK-309Per-key API rate limiting
review · round 2
Done7
TK-298Index for customer search
PR #482 merged
TK-301Validate negative amounts
PR #485 merged

// how it works

From requirement to mergeable PR, hands-free

This isn't autocomplete or a chatbot: it's a team of agents that runs your board end to end, under the same rules you'd expect from a developer.

01

From requirement to backlog

Describe the goal in natural language. The analyst turns it into epics, tickets and milestones on your GitHub repositories — connected from the UI, with no manual token handling.

02

Planning with human control

Your team prioritizes and assigns tickets to workers, sprint-planning style. Each worker operates in its own isolated git workspace, and as many run in parallel as your team can manage.

03

Peer review until merge

Every change goes through automated review rounds until it comes out clean. The PR arrives with context, numbered by round, for your final approval — nothing gets merged without human sign-off.

// what it feels like

Like a remote team, not a bot with commit access

mkanban follows the natural conventions of software engineering: backlog, planning, priority-based assignment and peer-review cycles. No agent does whatever it wants — there are AI and human controls at every stage.

analyst

Analyst

Turns natural-language requirements into well-defined epics, tickets and milestones, ready to assign.

human

Your team

Keeps control: prioritizes the backlog, assigns tickets to each worker and gives the final approval on every merge.

workers

Seniors and juniors

Each worker can run a different model — stronger models for complex tasks, lightweight ones for simple work — and its own GitHub identity. LLM costs optimize themselves and history stays traceable.

review

Peer review

Every change goes through automated review rounds before reaching a human — the same cross-checks you'd demand from a real team.

// what's included

A board that works, not one that just organizes

Everything around the development cycle is built in — no fragile integrations.

Hardened review loop

Automated review rounds with a configurable limit. Infrastructure failures don't burn rounds: retries with backoff and model fallback.

Epics and milestones

The analyst turns goals into GitHub epics, tickets and milestones — a single source of truth for what's done.

Embedded editor

File explorer, search, diffs and direct editing in the browser. Review and fix without leaving the board.

Fleet control

The state of every workspace and branch in one panel: what's running, what failed, what's waiting for review. Prometheus metrics included.

OTA updates with rollback

Unattended daily updates: automatic backup, healthcheck, and rollback only if something doesn't come up healthy.

Own GitHub identity

Each worker can operate with its own GitHub account: every commit, PR and review comment is attributed to whoever made it. Full traceability in the history, like any other member of the team.

// true on-premises

Your code never passes through anyone else's cloud

mkanban installs on your server — a VPS, an EC2 instance inside your VPC, or a physical server in your own datacenter. Repositories, database and credentials live in your volumes.

  • stays Source code, branches and agent workspaces
  • stays Database, configuration and credentials
  • stays Full history of every agent session
  • leaves Only the agents' model calls (your own API key), operational telemetry —metrics and technical logs, never code— and a licensing heartbeat

// pricing

You pay a percentage of what you save. Nothing else.

No seat licenses, no flat fees: mkanban charges 10% of the savings it generates, calculated on the tickets it actually closed during the month. A month with no output is a month with no invoice.

savings  = tickets closed × 4 h × USD 30
invoice  = savings × 10%
  • Hours per ticket and hourly cost are fixed, deliberately conservative parameters of the model: 4 h and USD 30, the same for every customer. If your real numbers are higher, your real savings are bigger — and the invoice doesn't change.
  • Closed tickets come from your own instance's report — the number you see on the board is the number that gets billed.
  • Billed in arrears: first the savings, then the invoice.

Run your numbers

Your estimated real monthly savings USD 9,600
mkanban invoice USD 960

Calculated with the fixed parameters (4 h × USD 30 × 10%): equal to 10% of your real savings.

Equivalent to the output of 2 full-time developers.

On-premises

mkanban runs on your server. You pay only 10% of the month's savings — no minimums, no fixed costs.

Managed by mkanban

We operate your dedicated instance. Same 10% of the savings, with a monthly minimum that covers the infrastructure.

// faq

What every security team asks

Does my code leave my infrastructure?

No. Repositories are cloned and worked on inside your server. The only outbound connections are the agents' calls to the AI model (with your API key, straight to the provider), GitHub, and a licensing heartbeat that reports usage counters — never code or content.

What do I need to install it?

An x86_64 Linux server with Docker and HTTPS egress to four domains (we provide the exact list for your network team). Nothing else: everything ships in a single container.

How does it update?

Automatically, every night: the updater downloads the new version from the stable channel, backs up your data, brings it up and verifies health. If anything is off, it rolls back to the previous version automatically and notifies.

How is the invoice calculated?

In arrears: tickets closed during the month × 4 h × USD 30 × 10%. Hours per ticket and hourly cost are fixed, deliberately conservative parameters of the model: if your real numbers are higher, your real savings are bigger and the invoice stays the same. Closed tickets come from your own instance's report. No black boxes: the number you see on the board is the number that gets billed.

How many tickets would your team close
with 5 more developers?

Book a 30-minute demo on your own backlog. Even if you decide not to move forward, you'll walk away with a diagnostic of your development process.

Book a demo