Anvil CoderLog in

Forge something mighty.

From ticket to pull request with AI agents

Anvil Coder implements software tasks in your repository. AI agents break tickets into small steps and create traceable commits. You define the project rules and review the result before merging. In the hosted service, the output is a draft pull request.

Join the waitlistRequest a demo

Access currently opens through a waitlist. Subscription prices are not final. Platform usage and external model costs are separate.

Anvil Coder's anvil symbol

Follow the work in your cockpit

See which steps are complete, running or pending. Open the resulting pull request in your code host to review the changes.

Anvil Coder run overview showing completed, running and pending work steps (German interface, example data)
Product screenshot with example data, German interface. A completed work step does not by itself mean that build and tests passed.

Evidence from a reference run

A reference run produced three commits with a Laravel bug fix and regression test. The sandbox could not execute the test because the PHP toolchain was missing; functional review remained outstanding.

Aug 31, 2026 (one run, ~24 minutes)

Read the run, artifacts and verification limits

Which tools can you connect?

Model availability depends on the service configuration. Your project stack is defined separately in a stack profile.

Model connections

  • Anthropic
  • OpenAI
  • Groq
  • Gemini
  • Mistral
  • Ollama

Built with

  • Java
  • Spring Boot
  • Angular
  • Astro
  • PostgreSQL
  • NATS
  • Kubernetes
  • Flux CD

Integrations and operations

  • GitHub
  • YouTrack
  • Keycloak
  • nginx
  • Prometheus
  • Grafana
Project compatibility is not the same as the platform stack
AreaScope and prerequisites
Project stackJava and Spring Boot are the most established path. Other profiles require the corresponding build and test toolchain. Stack requirements
Issue trackersInternal issue board, YouTrack, GitHub Issues, Jira Cloud, GitLab Issues, Bitbucket. The connection and trigger must be configured.
Git hostingGitHub, GitLab, Bitbucket. Access permissions and output settings depend on the integration.
Platform componentsThe “Built with” list describes Anvil Coder itself, not a guarantee that every customer project can be built or tested.
Explore integrations and requirements

Connect your existing repository and use the internal issue board or an external tracker. A stack profile describes your language, framework and check commands. Java and Spring Boot are the most established path; other stacks depend on the available toolchain.Check the requirements for your stack.

How it worksFollow a ticket through planning, implementation, checks and review.IntegrationsConnect your tracker, code host and model provider.SecurityUnderstand data location, access controls and model-provider transfers.

What does Anvil Coder cost?

One Team subscription per organisation, with up to ten seats at the base price and 75% of the base as runtime credit. Current amounts are placeholders. Usage beyond the credit is chargeable; BYOK model costs are paid separately.

Understand subscription and usage costs

What should you know before starting?

Does Anvil Coder merge automatically?
In the hosted service, the result arrives as a draft pull request and a human merges it. Intermediate approvals are configured per project; without a configured supervision level, the run proceeds without intermediate approval.Details: Review and supervision
What if the result is no good?
There are two places for that, one inside the run and one after it. Inside, a consistency pass over the whole stands at the end. If it measures a regression, it sends the affected work steps into capped repair rounds. If it cannot measure, it lets the run through like the VERIFY gate and records an error on the gate — nothing was checked then. The measurement itself is available in the hosted service and is switched on per project; an additional build-and-test pass over the full state is optional and switched on there. Afterwards the draft pull request sits in your review tool: a comment on it becomes the requirement of an incremental follow-up run — an optional channel, switched on in the hosted service.The flow as a whole: How it works: phases and slices · Integrations: the feedback channel on the pull request
Does it run in Switzerland?
Yes, the hosted service runs on the Infomaniak Public Cloud in Switzerland. Source code in model requests is sent to the configured model provider. Results can also leave Switzerland if your repository or tracker is hosted abroad. Swiss hosting does not mean all data stays in Switzerland.Where the data lives: Security: where the data lives
How do I keep control?
How much supervision you keep is a per-project setting: from every action needs a release to only the consequential ones — but without a set level, the order runs through; the release levels are a per-project feature, not a default. What holds either way: in the hosted service the result arrives as a draft pull request, and a human merges it to the main branch.Why that is the real question: For product teams: hand over the execution, keep the decision

All questions and answers

For the methodology behind the workflow, see Spec-Driven Development · GitHub Spec Kit (external methodology reference).

Content reviewed by Halvic Labs GmbH on .