Deterministic Replay Python Packages

bernstein

The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

belay-harness

The agent harness: sandbox any agent, verify each step by replaying it against real state, and keep a deterministic trace.

openadapt

Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.

kigumi

Load-bearing joinery for LLM content pipelines: context injection, validated repair loops, deterministic replay, DAG orchestration.

metriplane

Open-source physical observability for robotics workcells: deterministic replay, verifiable incident evidence, and generated regression tests.

oasg

Local-first, model-agnostic workflow optimizer for long-running AI agents: observable JSONL ledgers, deterministic reducers, no-meta gates, and receipt-backed self-improvement without LLM judges or model-weight updates.

salvor

An event-sourced runtime for AI agents that survives kill -9, written in Rust.

audit-closed-ai-scientist

Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.

durabl

Durable execution for AI agent workflows in Python. Crash mid-run and resume exactly where you left off. SQLite, no services.