Repository agnostic
Connect any GitHub repository through a least-privilege GitHub App installation.
Autonomous software delivery
ForgeLoop is the control plane around coding agents: it delegates bounded work, runs it on your infrastructure, repairs failures, proves acceptance criteria, and delivers the reviewed commit.
The delivery loop
Connect any GitHub repository through a least-privilege GitHub App installation.
Plan, implement, integrate, verify, repair, independently review, and deliver one exact commit.
Every gate produces checksummed evidence, criterion coverage, provider telemetry, and an audit trail.
Source code, shell commands, containers, and browser tests stay on enrolled infrastructure you control.
Designed for real repositories
Signed GitHub webhooks, short-lived installation credentials, tenant-scoped membership, task leases, isolated worktrees, policy-selected verification, immutable evidence, bounded retries, and guarded expected-SHA delivery.
From setup to deliberate execution
GitHub sign-in identifies you. GitHub App installation grants repository access. Intake policy decides which issues become eligible for work.
Follow the workflow →Save provider keys locally, verify prerequisites, and explicitly start processing. Setup checks do not call a model; work execution can incur charges.
Explore runner setup →Inspect the diff, acceptance coverage, gate results, and commit identity. Keep human approval on until your evidence supports a narrower auto-merge policy.
Explore the controls →Before your first run
Yes. Connect authorized GitHub repositories with their own stacks and verification policies. ForgeLoop runs work on your enrolled infrastructure.
Yes, configure a supported provider on your runner. Provider usage is separate from GitHub authentication. Actual coding work can incur provider charges.
No. Browser pairing, saving settings, local key checks, and heartbeat checks do not invoke a model. Start runner can claim eligible work; it is not a dry run.
Not yet. Windows, macOS, and Linux installers are available as unsigned previews through GitHub Releases. Publisher signing and remaining live validation have separate release gates.
Field notes
Runner operations
Use a practical restart recovery checklist for self-hosted AI coding runners: verify durable state, credentials, heartbeats, leases, and safe task resumption.
Read field noteGitHub workflows
Build an issue-to-PR workflow with explicit intake rules, bounded tasks, verification evidence, and a deliberate approval point.
Read field noteArchitecture
Understand the difference between an AI coding agent and the orchestration, policy, evidence, and recovery system around it.
Read field noteVerification
Write observable acceptance criteria for AI coding tasks, including failure paths, permissions, test evidence, and explicit scope boundaries.
Read field note