---
title: "bernstein"
description: "The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte"
canonical: https://agentpluginsdirectory.com/plugins/bernstein
last-updated: 2026-09-25
---

# bernstein
The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.
- Slug: bernstein
- Publisher: chernistry
- Repository: https://github.com/sipyourdrink-ltd/bernstein
- Manifest: plugin.json
- Version: 3.20.0
- License: Apache-2.0
- Category (editorial): agent-tooling
- Skills: 1 (bernstein-run)
- MCP servers: 1 (bernstein)
- Stars: 1271
- Repository created: 2026-03-22
- Repository last pushed: 2026-09-25
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/bernstein
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What bernstein does, in the publisher's words

> "To achieve great things, two things are needed: a plan and not quite enough time.": attributed to Leonard Bernstein

> Status: beta. Solo-maintained, under active development. The version number counts releases, not maturity, minor versions may change interfaces. Pin the version for anything you depend on; regressions get fixed fast, file them.

Bernstein is the open-source governance layer for AI agents. It runs on policy as code: you write the policy, who may do what, what needs approval, what must be recorded, and Bernstein enforces it and produces the verifiable record. A deterministic scheduler, no model in the coordination loop, runs agents in parallel, gates what they produce, and records every step, so a run can be verified after the fact, offline, from the artifacts alone.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/sipyourdrink-ltd/bernstein/HEAD/README.md

## Skills

- bernstein-run: Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a fini…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- bernstein: transport: stdio; command: bernstein mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.