The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
Latest release v3.23.0 · 24 Oct 2026
3 files for GitHub Copilot, Codex, OpenCode and Claude Code: bernstein copilot-instructions.md, bernstein AGENTS.md, bernstein CLAUDE.md — 3,236 tokens loaded in every session.
.github/copilot-instructions.md A 740 tok AGENTS.md A 1,251 tok CLAUDE.md A 1,245 tok These files are sipyourdrink-ltd/bernstein's own configuration — they tell GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.