Gemini Executive Synthesis

Broccoli (one-shot coding agent harness)

Technical Positioning

An open-source harness for taking coding tasks from Linear, running them in isolated cloud sandboxes, and opening PRs for human review. Positioned as an alternative to cloud coding agents, emphasizing independent execution and context management.

SaaS Insight & Market Implications

Broccoli addresses a critical operational inefficiency for development teams leveraging coding agents: managing concurrent tasks and context switching. By providing isolated cloud sandboxes for each task, it ensures independent execution, reducing local environment overhead and developer distraction. The integration with Linear for task management and GitHub for PRs streamlines the agent-driven development workflow. Its open-source nature positions it as a customizable, self-hosted alternative to proprietary cloud agents, appealing to organizations prioritizing control and specific integration needs. The reported 100% PR shipment from non-developers via Broccoli demonstrates tangible productivity gains and expands development capacity.

Proprietary Technical Taxonomy

Raw Developer Origin & Technical Request

Hacker News Apr 23, 2026

Show HN: Broccoli, one shot coding agent on the cloud

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: github.com/besimple-oss/broc... 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!

View Raw Source

Developer Debate & Comments

auszeph • Apr 22, 2026

Built similar for internal use at our work. Slack+JIRA though, not Linear. Otherwise GCP-native like this.I didn't want to be on the hook for supporting an open source version though, so never made it public. Good on you for putting it out there.A few differences I can quickly spot, fwiw...I went with Firestore over Postgres for the lower cost, and use Cloud Tasks for "free" deduping of webhooks. Each webhooks is validated, translated, and created as an instant Cloud Task. They get deduped by ID.We see a lot of value in a scheduler. So running a prompt on a schedule - good for things like status reports, or auto log reading/debug.I prefer to put my PEMs in to KMS instead of Secret Manager. You can still sign things but without having to expose the actual private key where it can be snooped on.I run the actual jobs on spot VMs using an image baked by Packer with all the tooling needed. You don't run in to time/resource limits running them as Cloud Run jobs?

xmonkee • Apr 22, 2026

One persistent issue I keep having is preview environments for this kind of stuff. I have the full setup, migrations, database seeding, etc. But having it run off a PR is still kind of a mess with spinning up 2 services, databases, redis etc. Do you guys run into this problem?

dennisy • Apr 22, 2026

Fair play for launching this, it looks like a neat project.However I feel it will be an uphill battle competing with OpenAI and Anthropic, I doubt your harness can be better since they see so much traffic through theirs.So this is for those who care about the harness running on their own infra? Not sure why anyone would since the LLM call means you are sending your code to the lab anyway.Sorry I don’t want to sound negative, I am just trying to understand the market for this.Good luck!

Almured • Apr 22, 2026

It's interesting that you’re using Linear tickets as the primary context source. From my experience so far, one of the biggest issues with coding agents is context drift. Ticket says one thing, but the codebase has changed since it was written. How did you solve? fresh RAG pass or use something like ctags to map the repo before it starts the implementation, or does it rely entirely on the LLM's provided context window?

ppeetteerr • Apr 22, 2026

How does this compare to using Claude Web with connectors to build the same feature?On a separate note, READMEs written by AI are unpleasant to read. It would be great if they were written by a human for humans.

sinansaka • Apr 22, 2026

nice work! I built a similar system at my previous company. It was built on top of github. agent was triggered by the created issue, run in actions, save state in PR as hidden markdown.It worked great but time to first token was slow and multi repo PRs took very long to create (30+ mins)Now im working on my standalone implementation for cloud native agents

orliesaurus • Apr 22, 2026

I use the Codex integration in Linear, can you tell me more about the differences please?

throwaway7783 • Apr 22, 2026

Cool! We have a similar setup,connected to JIRA, but it stops at analysis and approach to solution. I'm taking inspiration from this now to take it to the next level!

Jayakumark • Apr 22, 2026

Thanks for making it open source, Jira Support would be good

dbmikus • Apr 22, 2026

Like the detailed setup instructions in the readme!Also agree that teams should invest in their own harness (or maybe pedantically, build a system on top of harness likes Claude Code, Codex, Pi, or OpenCode)

Frequently Asked Questions

Market intelligence mapped to Broccoli (one-shot coding agent harness).

What problem does Broccoli (one-shot coding agent harness) solve?

Based on our AI analysis of the original developer request, its primary technical positioning is: An open-source harness for taking coding tasks from Linear, running them in isolated cloud sandboxes, and opening PRs for human review. Positioned as an alternative to cloud coding agents, emphasizing independent execution and context management.

How is the developer community reacting to Broccoli (one-shot coding agent harness)?

Yes, we have tracked 36 direct responses and active debates regarding this specific topic originating from Hacker News.

What architecture is tied to Broccoli (one-shot coding agent harness)?

Our proprietary extraction maps Broccoli (one-shot coding agent harness) to adjacent architectural concepts including open-source harness, coding tasks, Linear, isolated cloud sandboxes.

Are there startups building around Broccoli (one-shot coding agent harness)?

Yes, market intelligence reveals commercial overlap. A product named 'Grass' focuses directly on this: Gives your coding agent a dedicated VM that's ready 24/7

Engagement Signals

Upvotes

Comments

Cross-Market Term Frequency

Quantifies the cross-market adoption of foundational terms like coding agent and PRs by tracking occurrence frequency across active SaaS architectures and enterprise developer debates.