Broccoli, one shot coding agent on the cloud
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN — we built Broccoli, an open-source harness for taking coding tasks from Linear, running them in isolated cloud sandboxes, and opening PRs for a human to review.We’re a small team, and our main company supplies voice data. But we kept running into the same problem with coding agents. We’d have a feature request, a refactor, a bug, and some internal tooling work all happening at once, and managing that through local agent sessions meant a lot of context switching, worktree juggling, and laptops left open just so tasks could keep running.So we built Broccoli. Each task gets its own cloud sandbox to be executed end to end independently. Broccoli checks out the repo, uses the context in the ticket, works through an implementation, runs tests and review loops, and opens a PR for someone on the team to inspect.Over the last four weeks, 100% of the PRs from non-developers are shipped via Broccoli, which is a safer and more efficient route. For developers on the team, this share is around 60%. More complicated features require more back and forth design with Codex / Claude Code and get shipped manually using the same set of skills locally.Our implementation uses:1. Webhook deployment: GCP 2. Sandbox: GCP or Blaxel 3. Project management: Linear 4. Code hosting & CI/CD: GithubRepo: https://github.com/besimple-oss/broccoliWe believe that if you should invest in your own coding harness if coding is an essential part of your business. That’s why we decided to open-source it as an alternative to all the cloud coding agents out there. Would love to hear your feedback on this!
HN · launched Apr 22, 2026 · 82 upvotes (top 12%) · 0 views
Niche: ai coding agents · 475 launches, 23 in the last 7 days ▼ -28% · Explore this niche →
Category and tags
- Horizontal
- Agent / copilot
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 475 launches in ai coding agents →
Could you build this?
Yes This is a developer workflow harness that listens to Linear webhooks, spins up an isolated sandbox via existing container/sandbox APIs, runs an LLM agent prompt, and calls the GitHub API to submit a pull request.
Discussion
20 comments analyzed.
Competitors mentioned: Cursor Cloud Agent, productbuilding-orchestration (GitHub), testeranto
Concerns raised: One-shot approach unreliable for complex PRs requiring back-and-forth, Preview environments difficult to set up for backend changes, Time/resource limits on Cloud Run for long-running jobs, Complexity of reactive feedback loop from multiple sources, OSS support burden
Feature requests: Multi-vendor compute support (spot VMs, Blaxel), Scheduler for running prompts on schedule, Preview environment support for backend/infrastructure changes, Instance type and timeout configuration, KMS-based key management instead of Secret Manager
Competitors
Other products that read as similar to this one : 142 launches clear the similarity bar, closest 8 shown.
Attention rank: #20 of 143 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 168 days after the earliest competitor.
- Shikigami, run AI coding agents in parallel, each in a Git worktree · hn · 2026-07-19 · 7 upvotes · similarity 0.44
- Murmell · hn · 2026-08-30 · 8 upvotes · similarity 0.44
- Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud · hn · 2026-06-04 · 105 upvotes · similarity 0.42
- Hoplite · ph · 2026-08-14 · 154 upvotes · similarity 0.42
- ChatML · hn · 2026-03-09 · 6 upvotes · similarity 0.41
- Amika · hn · 2026-09-15 · 7 upvotes · similarity 0.39
- Jalebi · ph · 2026-09-15 · 5 upvotes · similarity 0.39
- Open-source certificate from GitHub activity · hn · 2026-01-18 · 43 upvotes · similarity 0.39
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.