Audit-grade multi-agent orchestration for CLI coding agents with HMAC-chained audit logs and deterministic scheduling.
bernstein is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add sipyourdrink-ltd/bernsteinRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
Bernstein is a tool that runs multiple AI coding agents (like Claude Code or Codex) in parallel to solve a single task. It keeps a secure, tamper-proof log of every action, making it easy for compliance teams to review. Think of it as a conductor that ensures all AI agents work together reliably and transparently.
Bernstein is a deterministic Python scheduler that orchestrates a crew of CLI coding agents (Claude Code, Codex, Gemini CLI, and 40+ more) against a single goal using parallel git worktrees. It features an HMAC-SHA256 audit chain per RFC 2104, providing tamper-evident records for every scheduling decision. The system includes bearer-token task server authentication, signed agent cards using detached JWS with Ed25519 keys, and per-artefact lineage tracking that links every file write back to its producer, inputs, prompt SHA, model, and cost. The scheduler is fully deterministic—no LLM in the coordination loop—ensuring replayable, predictable task graphs. Bernstein is designed for environments requiring auditability, compliance, and transparency, such as regulated industries or enterprise deployments.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
552 GitHub stars indicate community interest.
22 open issues signal maintenance load.
Apache-2.0 license detected.
Running multiple AI coding agents in parallel to solve complex software tasks faster
Generating tamper-proof audit logs for compliance in regulated industries
Reproducing task execution plans for debugging or verification
Integrating with CI/CD pipelines to automate code generation with full lineage tracking
Requires access to multiple third-party AI services; data may be sent to external APIs
HMAC keys must be managed securely to maintain audit integrity
Bearer tokens and JWT secrets need proper rotation and storage
552
Stars
46
Forks
22
Issues
Apache-2.0
License
Vercel's official collection of packaged instructions and scripts that extend AI coding agent capabilities.
Official Supabase agent skills to help AI agents work accurately with Supabase products.
A best-practices skill for Terraform and OpenTofu AI agents, enabling testing, module structuring, CI/CD, and production infrastructure code.
Audit-grade multi-agent orchestration for CLI coding agents with HMAC-chained audit logs and deterministic scheduling.
DevOps engineers needing auditable automation, Compliance officers reviewing AI-assisted code changes, AI researchers experimenting with multi-agent coordination
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Requires access to multiple third-party AI services; data may be sent to external APIs HMAC keys must be managed securely to maintain audit integrity
Similar or complementary options to evaluate include agent-skills, supabase-agent-skills, terraform-skill.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 4/5.