Kadmo
Sovereign agentic engineering platform: Kadmo runs Claude Code, Codex and your other AI coding agents with roles, playbooks and gates, on your infrastructure.
What is Kadmo?
Kadmo is a sovereign agentic engineering platform that runs AI coding agents such as Claude Code and Codex as a team, with defined roles, playbooks and gates. It works inside the tools a team already uses — task boards like Jira or Linear and repositories on GitHub or GitLab — on the customer's own cloud, models and gateway. Each agent runs on its own machine with scoped credentials, and every step writes what it did and why back into the ticket.
Key features
- Roles instead of one generalist
- Engineers, a product manager, a reviewer and a QA agent each do only their own job, and a frontend agent is better at frontend work than a generalist.
- Playbooks with gates
- Work advances step by step through a playbook, and nothing moves on before its gate passes.
- Runs inside your tools
- Agents work in your task board, your repository and your cloud, and nobody installs anything.
- Agents ready out of the box
- Software Engineer, Product Manager, QA Engineer, Documentation, Skill Discovery and Website Builder ship ready, with Security listed as coming soon.
- Self-learning skills
- What one run learns is written down so every following run loads it.
- Sandboxed by role
- Each agent gets its own machine and scoped credentials, with outbound traffic allowlisted per agent.
- Governance controls
- Roles with scoped tools, approval policies, spend ceilings in euros per account and workspace, data residency policies, replayable run transcripts and SAML/SCIM sign-in, included in Business and Enterprise.
How to use Kadmo
- Connect the tools you already use — Jira or Linear for tickets, GitHub or GitLab for code.
- Set the rules once: roles, playbooks, gates, approval policies and budgets.
- Drop a ticket onto the board, or hand a goal to the product manager agent to split into tickets sized for one agent each.
- Let the fleet work: agents pick up the ticket on their own machines and branches, following the playbook, and open a pull request.
- Review the result in the ticket. Gates return work for rework when a reviewer requests changes, and every step leaves a comment explaining what it did and why.
Use cases
- Engineering teams already using AI coding assistants that want more throughput while keeping review and quality.
- Teams that must keep code inside their own perimeter, on their own cloud, models and gateway.
- Teams with a backlog of well-scoped work such as bug fixes, dependency upgrades and test backfill.
- Teams that need documentation, release checks and regression passes to keep up with shipped code.
- Product managers who want a goal turned into an epic and then into tickets each sized for a single agent.
Pricing
The official website does not list prices for Kadmo on the pages reviewed; it links to a plan comparison page, and the governance features are described as included in the Business and Enterprise plans. Model usage runs on your own accounts at your own rates, and every run reports its real token spend in the ticket. Check the official pricing page for current plans and prices.
FAQ
Is Kadmo free?
The official website does not state a free plan or a free trial on the pages reviewed. Pricing is not listed there, so check the official pricing page for current plans.
Where do Kadmo's agents run, and does code leave the company perimeter?
Kadmo runs the agents on your cloud. Every agent has its own machine and its own scoped credentials, outbound traffic is allowlisted per agent, and model calls go through your own gateway, so the code stays inside your perimeter.
Which AI coding agents and models does Kadmo support?
Claude Code and Codex today, on models from Anthropic, OpenAI and Google, either direct, through Amazon Bedrock, or behind your own gateway. There is no lock-in: when a better model ships, you switch.
What does Kadmo need to get started?
A repository, a task board and one item from your backlog. Kadmo works inside Jira or Linear and GitHub or GitLab, so there is nothing to replace or migrate, and the fleet is set up with you and live within days.
How much does a ticket cost with Kadmo?
Every run reports its real token spend in the ticket, in one place, so a shipped ticket has a price. The models run on your own accounts at your own rates, and budgets with spend ceilings can be set per account and per workspace in euros.
How is Kadmo different from a single AI coding assistant?
Kadmo runs a fleet of specialist agents — engineers, a product manager, a reviewer and a QA agent — rather than one assistant taking a whole ticket alone. Each agent keeps a small context window, works on its own machine, and a gate at every handoff decides whether the work moves on.
Kadmo
Sovereign agentic engineering platform: Kadmo runs Claude Code, Codex and your other AI coding agents with roles, playbooks and gates, on your infrastructure.
Amazon CloudFront
Amazon S3
Amazon Web Services
HTTP/3Free AI anime and manga generator. Turn text into anime episodes, manga, comics, webtoons and comic shorts in any art style — no drawing or animation skills needed.
Translate image text across 70+ languages with our advanced AI Image Translator to help you better expand your products globally to various countries
Advertised Here
Reach thousands of visitors daily. Get your spot now!
Tools similar to Kadmo
Managed hosting for Claude Code and Codex. Persistent cloud environments, browser terminal, SSH access. Your AI coding agent runs 24/7. Free trial included.
Browse and download open-source agent skills for Claude Code, OpenAI Codex, and ChatGPT. Curated collection of SKILL.md files from GitHub. Find productivity skills, code generation prompts, MCP tools, and AI agent templates. The best Claude skills marketplace with 50,000+ skills.
Always free, no set up. Claude Code or Codex runs 100+ browser automation tasks at the same time for you, 3.45x faster than agent-browser.
Coordinate coding agents from intent through validated code while preserving durable task, session, review, and evaluation evidence.
Bring Claude Code, Codex or Pi to Slack and Lark. openTag is a free, open source AI coworker that runs on your machine with your own plan or API key.
Designed to accelerate the velocity of modern engineering teams.
Bring your own code, and run CPU, GPU, and data-intensive compute at scale. The serverless platform for AI and data teams.
Build, deploy and monitor on-premise GenAI applications to solve specific business needs, reducing costs, driving revenue and boosting competitiveness - all in one platform