TOOL · REPLAY
Open infrastructure for reproducible AI-agent execution.
Replay is a local-first execution recorder and state engine for AI-agent runs. Its deterministic core works without AI and is designed to make technical execution inspectable, restorable, branchable and comparable.
EXPERIMENTAL · CURRENT IMPLEMENTATION
CURRENT
What is implemented today.
- — Generic execution recording with command, process and workspace capture.
- — Verification of recorded state.
- — Verified restore into a staged tree.
- — Branch creation from historical state with explicit live-rerun consent.
- — Controlled rerun workflows.
- — Deterministic multi-dimensional replay diff.
DESIGN LAW
The architecture separates evidence from interpretation.
The deterministic core is complete without AI.
The Generic Recorder remains mandatory; adapters may enrich but never gate recording.
Watcher events are triggers for reconciliation, not authoritative truth.
Final checkpoints plus reconciled file events and Merkle state are the technical source of truth.
Playback and re-execution are separate concepts: playback reads stored evidence, rerun executes code.
REPRODUCIBILITY LADDER
Reproducibility is a ladder, not a binary claim.
R0
Inspectable
R1
Restorable
R2
Re-executable
R3
Controlled external I/O
R4
Containerized / fully captured
R0–R4 is the architecture contract for describing achieved reproducibility. The page does not claim every level is fully implemented for every session today.
ARCHITECTURE
State and storage architecture.
01
CLI / API layer
02
Session + event services
03
Generic recorder + adapters
04
Event bus + state engine
05
SQLite metadata and indexes
06
Content-addressed state storage
07
Optional read-only intelligence layer
FINDINGS
Engineering findings.
- — Reliable restore needs its own state model rather than relying only on terminal logs.
- — Content-addressed storage and recursive state trees make state identity explicit and deduplicable.
- — A filesystem watcher cannot be the source of truth by itself; reconciliation and checkpoints are required.
- — Recorded playback should never silently execute code or access the network.
- — Adapters are additive so reproducibility does not depend on one IDE or agent vendor.
PLANNED / ARCHITECTURE TARGET
Architecture targets that must not be confused with current implementation.
- — Portable .rplay export/import package
- — Complete external-I/O cassette ecosystem
- — Full local UI
- — Optional local intelligence sidecar
- — Broader adapter coverage and hardening
USAGE
Current CLI surface.
rappid replay record -- <command>
rappid replay verify <session>
rappid replay restore <session>
rappid replay branch <session>
rappid replay rerun <session>
rappid replay diff <left> <right>AUDIENCE
Who it is for.
Developers and researchers debugging autonomous agents, comparing execution paths, reproducing failures, testing agent changes and preserving inspectable local evidence of what a run changed.
Reviewed architecture and source