Scale coding agents across your team — without losing control

Kodel is the management layer over Claude Code, OpenCode, and your agents. Describe workflows as code, run them through guardrails, and see every step — not a black box, a governed engineering process.

See how it works

Pre-launch · SaaS-first · Enterprise self-hosted available

Pipeline guardrails

Agent → check → human gate. The server owns the graph — agents can't skip a step or fake an outcome.

Pipeline observability

See where every task is, which checks passed, who approved — pipeline-level visibility, not terminal logs.

The problem

Coding agents are powerful — but a black box for engineering leaders

Your team hired coding agents for speed. The process stayed ad-hoc — and predictability dropped below expectations.

No traceability

Unclear what was done, by whom, and through what process — prompt in, diff out.

No guarantee checks ran

Can't verify that tests, lint, or human review actually happened before merge.

Everyone invents their own workflow

Each developer has a different prompt and level of control — no team standard.

Nothing to audit or replay

No audit trail, no reproducibility — you can't debug a failure or repeat a success.

When you need it

Five moments when teams start looking for a solution

If a third of your team already uses coding agents regularly and at least one of these happened in the last three months — you're in the right place.

01

Incident

The agent faked a result, tests failed, or nobody can explain what happened on a task.

02

Scale

A third of the team uses agents, but the process is still "how Ivan does it" — not a standard.

03

Pressure from above

CEO, board, or compliance asks: "How is AI-assisted development governed in your engineering org?"

04

Onboarding

A new engineer can't repeat a colleague's successful agent run — knowledge lives in DMs, not in process.

05 · Enterprise

Audit

You need to prove that AI-assisted changes go through a controlled, documented process — not trust in a chat log.

Built for leaders

Made for engineering leaders

Your developers already use coding agents. Kodel helps you turn ad-hoc prompts into a repeatable, auditable engineering workflow — without slowing the team down.

CTO / VP Engineering

Scale AI without losing governance

Not another agent — an operational model for AI-assisted development you can audit, standardize, and embed in engineering culture.

  • SaaS onboarding in minutes; Enterprise self-hosted when data must stay in-house
  • One pipeline standard across teams — versioned in git
  • Server-owned status and audit trail for every AI workflow
Tech Lead

One pipeline per task type — not chaos in Slack

Replace "everyone has their own prompt" with runbooks your squad can apply on day one. See where tasks block and where human review is required.

  • Ready-made runbooks for bugfix, feature, refactor, and more
  • Full trace: agent steps, checks, human gates — per task
  • Observability console for bottlenecks and recurring check failures
Platform / DevOps

Deploy and operate the control layer

Config-as-code pipelines, MCP integration, and observability hooks — SaaS by default, self-hosted when data must stay in your perimeter.

  • YAML workflows applied with kodelctl apply
  • Enterprise: Docker Compose on your infrastructure
  • Images from ghcr.io/kodelai/* — secrets stay yours

CTO? Subscribe and run one pipeline end-to-end — get an audit trail on a real task without deploying infrastructure.

Platform

Not another agent — infrastructure on top of agents

Claude Code and OpenCode stay the executors. Kodel defines the process, enforces gates, and holds the source of truth for every task.

Pipeline as code

CONFIG-AS-CODE

Projects, workflows, skills, and pipelines in YAML — applied with kodelctl apply. A DAG of agent, check, and human nodes your whole team shares.

  • Agent steps with skills

    Instructions injected per step — intent fixed in code, not reinvented per developer.

  • Check nodes

    Automated commands and tests with explicit pass/fail — the server records the result.

  • Human gates

    Approval points where the process must stop for a person — enforced, not optional.

Server-owned observability

VISIBILITY

The server owns the graph, gates, and final status. Agents report one step at a time via MCP — you see the full path, not just the final diff.

  • Task position in the pipeline

    Where the task is now, which steps completed, what blocks progress.

  • Check and gate history

    Which automated checks ran, who approved at human gates — audit-ready by design.

  • Team-level console

    Bottlenecks, time on human gates, recurring failures — Datadog for coding agents.

The shift

From ad-hoc prompts to a governed workflow

Without Kodel
With Kodel
Everyone on their own
One pipeline in git
Prompt → result
Step → check → gate → step
No audit trail
Server-owned status
"Works for Ivan"
Reproducible for the whole team

CI/CD gave observability for deploys. Kodel does the same for the era of coding agents — not a replacement for your agents, a control layer above them.

How it works

Agent → check → human gate

Every task follows a pipeline you define. The agent executes one step; the server decides when it's done.

tier-0 / local — agent on the developer's machine  ·  tier-1 — server-managed dev-box

01

Define

Describe your project, tracker, and workflow in YAML. Pick a runbook template or write your own pipeline — version it in git.

02

Execute

Your coding agent connects via MCP, runs one step at a time, and reports back. It cannot skip ahead or claim success without passing gates.

03

Observe

Every node is an observable event — skills in YAML, check exit codes, gate status on the server. Full trace per task and per team.

04

Govern

Human gates where review is mandatory. Tracker Bridge keeps Jira or Linear in sync — one ticket, one traceable AI workflow.

Sign up for SaaS and run your first pipeline end-to-end — no infrastructure to deploy.

Tech Lead? Describe one real team workflow in YAML in 30 minutes and compare it to how your squad works today.

See pipeline as code
What's in the platform

Built for day-one value

Core capabilities shipping in the first release — productized workflows on top of the Kodel pipeline engine.

Runbooks

Ready-made YAML pipelines for bugfix, feature, refactor, dependency updates, and incident fix. Your team's playbook — applicable in a day, not invented from scratch.

Observability Console

Dashboard for CTOs and Tech Leads: tasks by pipeline stage, time on human gates, recurring check failures, and who approved what — team-wide, not per terminal.

Agent CI

CI/CD checks the artifact after merge. Agent CI controls the process before the PR — lint, tests, security scan, and review gates enforced on every AI task.

Review Gate

AI does the first pass against your checklist; human gates guarantee the final word on sensitive paths. Review by process, not by trust in a chat log.

Tracker Bridge

Jira, Linear, or GitHub Issues → Kodel pipeline. Ticket status reflects pipeline stage — one ticket, one traceable workflow, no shadow process.

Secure Dev Box

Tier-1 server-managed sandbox: agents and checks run in isolation. AI-assisted development inside a perimeter that passes security review.

Compliance Trail

Every step, human gate, and check in an immutable audit log tied to the task and approver. AI in development with a provable process — not trust in a chat.

Platform preview

Pipeline observability for the whole team

Illustrative view of the Observability Console — task flow, gates, and tracker sync in one place.

kodel / observability — acme-platform
Pipeline board
Human gates
Check failures
Tracker sync
TASKS_IN_FLIGHT 12
AWAITING_REVIEW 3
CHECK_PASS_RATE 94%
[14:02:11] WEB-4821 → human gate senior-review · waiting on @alex
[14:01:03] check tests passed · ticket-4821 bugfix runbook
[13:58:44] agent step implement completed · synced to Linear
Security & deployment

SaaS-first. Enterprise when you need it.

Start on managed cloud in minutes. Move to self-hosted or Secure Dev Box when compliance requires it.

Managed SaaS

Default deployment — fast onboarding, no infrastructure to operate. Enterprise-grade security for most teams out of the box.

Enterprise self-hosted

docker compose up in your infrastructure — images from ghcr.io/kodelai/*. Data, secrets, and audit trails stay in your perimeter. Start with kodel-compose.

SSO, RBAC & audit

Role-based access for pipelines, dashboards, and configuration. Every step, gate, and approval logged — server-owned, not agent-reported.

Agent-agnostic. Works with Claude Code, OpenCode, and other MCP-compatible coding agents — your tools, Kodel's process.

Packages

Start where your team is

Pre-launch pricing is tailored to team size. Subscribe for details when pilots open — tiers below reflect product scope, not final pricing.

Now onboarding

Founding pilot teams

Hands-on setup, direct access to the team, and influence on the roadmap. SaaS pilots open first; Enterprise self-hosted available for qualified teams.

Starter
SaaS

Fast entry for squads adopting coding agents with guardrails.

  • Runbooks — ready-made pipelines
  • Review Gate — AI first pass + human approval
  • Pipeline as code + MCP integration
  • Core task observability
Enterprise
Custom

Self-hosted deployment for regulated and security-first organizations.

  • Everything in Team
  • Self-hosted in your infrastructure
  • Secure Dev Box (tier-1 sandbox)
  • Compliance Trail — immutable audit export
  • Security & architecture review
Explore self-hosted
FAQ

Common questions

Quick answers before you subscribe — we'll share more detail as features ship.

How is Kodel different from using Cursor or Claude directly?

Cursor and Claude Code help developers write code. Kodel is the control layer above them — it defines the pipeline (agent → check → human gate), enforces guardrails, and gives leaders observability across the whole team. Your agents stay; the process becomes repeatable.

We already have CI/CD — why do we need Agent CI?

CI checks the code after merge. Kodel orchestrates the process while the agent works — before and during the task — with gates and human approval. Agent CI ensures no AI task closes without the checks your team requires.

Is Kodel SaaS or self-hosted?

SaaS is the default — sign up and run pipelines without deploying infrastructure. Enterprise customers can run Kodel self-hosted with Docker Compose and ghcr.io/kodelai/* images when data must not leave the perimeter. See kodel-compose to evaluate locally.

Will developers resist another tool?

The coding agent stays the same — Claude Code, OpenCode, or whatever your team already uses. Kodel only defines the process once in YAML so nobody reinvents it per task. Less coordination in Slack, not another IDE.

Another SaaS with our source code?

For most teams, managed SaaS with enterprise-grade security is enough. If code and audit trails cannot leave your perimeter, Enterprise self-hosted runs entirely in your infrastructure — you hold the secrets and the data.

Isn't AI governance too early for us?

The earlier you standardize, the less tech debt you accumulate from ad-hoc agent usage. Teams that wait usually fix process chaos after the first incident or board question — not before.

What do pilot teams get?

Direct onboarding with the founders, influence on roadmap priorities, and early access to Runbooks, Observability Console, and Agent CI. Typical pilots start with one runbook (e.g. bugfix) and expand from there.

How long until we see value?

On SaaS, most teams target a first pipeline run within the first days. Apply a runbook template, connect your agent via MCP, and trace a real task end-to-end.

What happens after I subscribe?

You'll get occasional product news: what we shipped, SaaS and pilot openings, and early access invites. No spam — unsubscribe anytime.

From prompt chaos to a governed engineering workflow.

Kodel is in active development. Pick the next step that matches your role.

CTO / VP Engineering

Prove governance on a real task

Subscribe for SaaS early access, run one pipeline end-to-end, and get an audit trail — no infrastructure to deploy.

Tech Lead

Model your team's workflow

Describe one real bugfix or feature flow in YAML and compare it to how your squad works today — runbooks included.

See how it works
Enterprise / compliance

Evaluate in your perimeter

Try self-hosted via kodel-compose and a local pipeline example — data and audit trail stay inside your infrastructure.

Explore kodel-compose
◉ SaaS & pilot openings ◉ Product & roadmap updates ◉ Unsubscribe anytime