AICodeOps.dev Reviews and Details

AI CodeOps is a browser-based platform where AI agents plan, build, review, test and ship code, and nothing merges until quality gates and a person approve it.

How a change moves through it

• Plan: an architect agent reads your repository and settles the approach before code is written.
• Build: a builder agent writes the change as a diff you can review.
• Review: an AI review reads the actual diff and records findings by severity. Open high or critical findings block the merge.
• Test: your own test suite runs against the change in a sandbox. Results only count for the exact version they ran on.
• Secure: a security auditor reviews sensitive changes, policies guard protected paths, and SBOMs are recorded per project.
• Deploy: approved changes deploy through a gate, with deployment and rollback records and DORA metrics.

Quality gates. A pull request opens only when tests pass on that exact version, no high or critical findings are open, and a person approves. The person who started a session can't approve it alone when someone else in the workspace can. CI can ask the same gate for a verdict through an API, so merges made directly on GitHub or GitLab are covered too.

Evidence packs. Every change gets an Ed25519-signed record of the task, models, findings, tests, approvals and policy decisions, which anyone can verify offline.

Also included: 20+ specialised agents, spend caps per workspace and workflow, roles and an audit log, and integrations with GitHub, GitLab, Bitbucket, Gitea and Forgejo, including self-hosted servers. Your code, prompts and outputs aren't used to train AI models.

Free during the open beta, and free forever for non-commercial open-source projects (apply here). Enterprise adds SSO and self-hosting on your own Kubernetes.