bernstein
Orchestrate multiple CLI coding agents with deterministic scheduling and verifiable audit records.
Orchestrate multiple CLI coding agents with deterministic scheduling and verifiable audit records.
The Python orchestrator decomposes a coding goal, runs agents such as Claude Code, Codex, and Gemini CLI in isolated Git worktrees, and gates merges with tests, linting, and type checks. Scheduling decisions are deterministic, while HMAC-chained logs, signed records, and artifact lineage support offline verification and air-gapped operation. It targets multi-agent engineering and compliance-sensitive work, not simple pair programming or general research.
Resource types
Use cases
Orchestrate multi-agent automation with role-based teams and event-driven flows.
Configure and run custom multi-agent workflows without writing orchestration code.
Platforms
Runtime
Protocols & integrations
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Coordinate AI coding agents with persistent git-backed work tracking
Build enterprise AI workflows, RAG systems, agents, and model operations in one platform.