Broccoli: Open-source harness for running AI coding agents from Linear tickets in cloud sandboxes
What Broccoli does
Broccoli turns Linear tickets into shipped PRs by running AI coding agents in isolated cloud sandboxes. Each task gets its own sandbox where it checks out the repo, uses ticket context, implements solutions, runs tests and review loops, then opens a pull request for team review.
Architecture and deployment
The implementation uses:
- Webhook deployment: GCP
- Sandbox: GCP or Blaxel
- Project management: Linear
- Code hosting & CI/CD: GitHub
It's deployed to your own GCP project against your Postgres database with no third-party control plane. The deployment is production-grade using Cloud Run + Secret Manager + webhook deduplication + durable job state.
Key features
- Linear ticket → reviewable PR workflow
- Your infrastructure, keys, and data stay within your tenancy
- AI code review on every PR using Claude and Codex
- Customizable prompt templates that you can fork, tune, and version
- Deploys in ~30 minutes with one bootstrap script and one config file
Deployment prerequisites
To deploy, you need:
- GCP project with billing attached and
gcloudlogged in - GitHub App with specific permissions (Contents, Pull requests, Issues = read/write; Metadata = read-only; subscribed to Pull request review event)
- Linear bot user (dedicated, not personal account) with API key
- OpenAI and Anthropic API keys with billing enabled
- Linear webhook pointing at
${Service URL}/webhooks/linearusing auto-generatedbroccoli-oss-linear-webhook-secret
Usage results
In the last four weeks, 100% of PRs from non-developers were shipped via Broccoli. For developers on the team, this share is around 60%, with more complicated features requiring manual back-and-forth design with Codex/Claude Code.
📖 Read the full source: HN AI Agents
👀 See Also
PocketTeam: A Claude Code Pipeline with Hook-Based Safety and Learning Agents
PocketTeam is a Claude Code pipeline that implements 9 safety layers at the tool-call level to block dangerous operations like writes to .env or rm -rf commands. The system includes an Observer agent that analyzes completed tasks and writes structured learnings to improve future agent performance.
Claude Auto-Continue: Chrome extension automates tool-use limit interruptions
A developer built a free Chrome extension that automatically clicks 'Continue' when Claude hits its tool-use limit after roughly 20 tool calls, eliminating manual interruptions during agentic workflows. The extension includes optional token minimization and works across all tabs and windows.
Lucas Gerads demonstrates MCP servers for oscilloscope and SPICE simulator integration with Claude Code
Lucas Gerads built MCP servers for his LeCroy oscilloscope and SPICE simulator, enabling Claude Code to validate SPICE circuits and models, handle embedded programming, and automate data analysis tasks like time axis normalization and data alignment.
Claude IDE Bridge: MCP Tool for Remote Editor Access
Claude IDE Bridge is an open-source tool that provides Claude AI with remote control access to code editors via MCP (Model Context Protocol). It exposes editor knowledge like live type information and debugger state as callable tools.