Altimate Code – Open-Source Agentic Data Engineering Harness
Deterministic tooling layer stops AI from hallucinating SQL that references nonexistent tables.
Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers.
Self-hosted on your GCP, but AI coding agent orchestration is extremely crowded.
Engineering teams, DevOps engineers managing AI coding workflows
Aider · Cursor · Devin
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: Github
Repo: https://github.com/besimple-oss/broccoli
We 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!
Deterministic tooling layer stops AI from hallucinating SQL that references nonexistent tables.
Multi-stage pipeline with review gates before PR publication.
Parallel agent execution with 4.3x speedup and .nvmrc-style version pinning per project.
AI agents with local execution and cloud dashboards, but GitHub Copilot, Cursor, and Continue already own this space.
Remote coding agent—but unclear how it differs from Cursor, Continue, or existing AI coding platforms.
Yet another one-shot AI coder when Cursor and Codex already dominate this space.