[Resource]: Bernstein — parallel AI agent orchestrator

[chernistry]

Display Name

Bernstein

Category

Tooling

Sub-Category

Tooling: Orchestrators

Primary Link

https://github.com/chernistry/bernstein

Author Name

Alex Chernysh

Author Link

https://github.com/chernistry

License

Apache-2.0

Other License

No response

Description

Deterministic orchestrator that parallelizes Claude Code agents with test-driven verification, spending zero LLM tokens on coordination.

Validate Claims

Install with pipx install bernstein (requires Python 3.12+ and Claude Code). In any git repo, run:

bernstein -g "Add a hello world function with a test"

You will see multiple Claude Code agents spawn in parallel, each assigned a subtask. The orchestrator's janitor verifies tests pass before committing. The terminal dashboard shows agent assignments, live progress, and test results in real time - zero LLM tokens spent on coordination. Compare wall-clock time vs running agents sequentially to observe the parallelism benefit.

Specific Task(s)

Run bernstein with a coding goal and observe parallel agents spawned

Specific Prompt(s)

bernstein -g "Add a hello world function with a test"

Additional Comments

No response

Recommendation Checklist

• I have checked that this resource hasn't already been submitted
• It has been over one week since the first public commit to the repo I am recommending
• All provided links are working and publicly accessible
• I do NOT have any other open issues in this repository
• I am primarily composed of human-y stuff and not electrical circuits

[hesreallyhim]

A cooldown period is currently in effect for your account. Submitting during an active cooldown extends the restriction.

Please wait at least 14 days before opening any more submissions.

Please review the CONTRIBUTING guidelines and pinned issues before your next submission.