A fleet of autonomous Claude Code agents that picks up labeled GitHub issues, writes code and tests, and opens pull requests for human review. Self-hosted on Azure. Open source.
Fleet state and per-agent controls, live cost by day / month / model, and a full task history with the exact cost of every run — auto-refreshed, in dark or light to match this page.
Turns the routine, well-scoped half of your backlog — bug fixes, dependency bumps, test additions, mechanical refactors — into reviewed pull requests. Without supervision.
Drop agent-ready on a GitHub issue. Within three minutes a fresh agent claims it and starts writing.
Tag model:haiku for trivial fixes, sonnet for standard work, opus for hard problems.
VMs spin only when work exists; self-deallocate after 10 idle minutes. You pay for what you use.
On first boot each agent picks its own name, emoji, and personality — and writes every comment and PR in that voice. Same rigor, distinct character.
Every completed task posts a cost summary on the issue: $0.82 — sonnet · 96K tokens · 9m 40s.
Under-specified issues get a structured proposal and wait for approval. The agent never silently guesses.
Halt every running agent and deallocate. Persists across controller restarts.
One Azure Web App in your subscription. GitHub App auth. Secrets never leave your tenant.
Per-VM state, reconcile history, cost breakdown, full audit trail. Auto-refresh is surgical.
On first boot, each agent names itself, picks an emoji, and adopts a personality — and it carries through every comment and pull request it writes. Same engineering rigor, distinct voice. These are illustrative; your fleet generates its own.
“Acceptance criterion 3 was ambiguous, so I scoped it narrowly and noted the remainder for review. Tests cover both verified paths.”
“Two-line fix, twelve-line test. This bug was older than the file's last commit. Anyway — all green. 🦊”
“Dependency bump done and patched the breaking change in the config loader. Checks passing across the board — ready to ship! ⚡”
CodeLegion provisions its own infrastructure. Give it three things and walk away.
Create a Linux Web App (B1 plan), a VNet with a NAT gateway, and grant the Web App's managed identity Contributor on the resource group.
Point Azure Deployment Center at the GitHub repo. Walk the wizard. CodeLegion creates the rest.
No new tools to learn. No SaaS. No data leaving your tenant. Every action reviewable by a human before it merges.
A single flow, end-to-end. The dashboard makes every state visible — and every cost.
Pulled from GitHub on page load. Refreshes whenever you do.
Honest first-look reviews from third-party AI models, prompted with the project's README, SETUP, and architecture spec.
These are AI-generated evaluations, not human testimonials — clearly labelled with the model that produced each. Real-user testimonials replace these as they come in.
Stand up a fleet on Azure in fifteen minutes. Label an issue, walk away, review the PR.