| What it does | Sovereign agentic engineering platform that runs AI coding agents with roles, playbooks and gates on your infrastructure
| An AI panel debates your goal; a referee rules on re-checkable evidence
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Trial: Free for 15 days with €5 credit on Kadmo's LLM provider. Business: Flat monthly rate per workspace, unlimited seats, 100K runs per month, up to 100 agents on your cloud. Enterprise: Custom pricing with flexible terms, support for more than 100 agents by agreement. Model pricing: Claude Haiku
| Free: $1.00 starting credit once. Credit plans from $10 top-up with no expiration. Your own key: 5% infrastructure fee after the first $5.00 of usage.
|
|---|
| Key features | - Multiple specialized agent roles (Engineer, Product Manager, QA, Security, Documentation, Skill Discovery, Website Builder)
- Playbook-based workflows with gates at every handoff
- Integration with existing tools (Jira, Linear, GitHub, GitLab, Slack, Notion, Teams)
- Code execution on customer's own cloud infrastructure (AWS, Google Cloud, Hetzner)
- Support for multiple AI models (Claude, GPT, Gemini, Codex) with no vendor lock-in
- GDPR-compliant with data residency enforcement
- Full transcript and audit logs for every agent run, replayable anytime
- Governance controls including role-based access, approval policies, and spend budgets
- Transparent token cost reporting per ticket
| - Panel of up to six AI models from different vendors
- Referee rules on re-checkable evidence only
- Searches academic databases: arXiv, OpenAlex, Crossref, Europe PMC
- Executes Python code to verify claims
- Customizable acceptance standards
- Matches pause and resume without losing work
- Shared ledger prevents re-derivation
- Spending limit per match
|
|---|
| What makes it different | - Agents run on your infrastructure with no code leaving your perimeter, maintaining full data sovereignty and GDPR compliance
- No vendor lock-in with support for any AI model; switch models as better ones ship
- Integrates seamlessly into existing tools and workflows without requiring installations or migrations
- Live in days with transparent cost accounting per run in real tokens
| - Referee decides on evidence, not argument quality
- Panel from different vendors fails in different directions
- Stuck is a targeted question, not model thrashing
- Cost grows with ledger, not round count
- Published matches become research record
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 14 ▲ +1 (up) since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 11 | 0 |
|---|
| Citation Flow (Majestic) | 25 | 13 |
|---|
| Referring domains (Majestic) | 6 | 31 |
|---|
Kadmo
Referee.chat