A teammate that never sleeps. It studies your patterns, writes the code, runs the tests, and fixes failures, ending with a PR ready for approval.
What You Get
Agents handle the repetitive tickets that pile up - bug fixes, dependency updates, documentation
Ship improvements and fixes in hours, not weeks
Your engineering team can focus on high-impact features instead of maintenance
Assign tasks to the best coding agent
- Choose from Claude Code, OpenCode, and Codex.
- Run multiple agents in parallel and compare their outputs.
- Run the same agent n times to increase success rate.
Agents verify changes in isolated dev environments
- Agents spin up sandboxes to build, test, and iterate on changes, making PRs trustworthy.
- No setup needed, the agent figures out the best infrastructure for the task.
- Access the sandbox infrastructure logs and ports, securely.
Integrates with your tools
- Mention @twill from GitHub, Linear, or Slack.
- Works where your team already collaborates, with no context switching. Set up once, for all your teammates.
- SSH to the sandbox to debug or test, with your favorite IDE (Cursor, VSCode, etc).
Use Cases
Human-Originated
Mention @twill on a GitHub or Linear issue. An agent reproduces, fixes, and opens a PR, often before your morning standup.
Add a new API endpoint, update a form, or refactor a component. Assign it, review the PR, merge.
Upgrade packages, fix breaking changes, and run the test suite, all without context-switching your team.
Trigger-Originated
Connect Sentry or your alerting tool. When errors spike, an agent investigates, identifies the root cause, and proposes a fix.
Trigger agents on every PR to generate missing tests, covering edge cases humans tend to skip.
Keep READMEs, API docs, and inline comments accurate. Agents update docs when code changes.
Schedule automatic scans for vulnerabilities. Agents apply security patches, run database migrations, and verify nothing breaks.
