Replay Python Packages

kitaru

Agent traces you can run, not just read.

flyto-core

AI said it finished. Flyto2 shows the proof.

jevnav

Page truth for browser agents — and decisions that replay, test and audit. Jev picks the element, risky actions are gated, every run replays offline in CI.

argus-agents

Catch silent failures in AI agents before your users do

gem-dota

Python replay parser for Dota 2

chp-core

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

kitaru-pydantic-ai

Agent traces you can run, not just read.

novafabric

Open-source replay and evidence infrastructure for AI agents. Capture runs as portable Run Capsules for replay, diff, lineage, provenance, and audit.

chp-host

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

replay-trajectory-classification

State space models for decoding hippocampal trajectories and determining their type using sorted or clusterless data

chp-adapter-audit

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

agentmesh-ai

Open-source observability, traceability, replay, and cost intelligence platform for multi-agent AI systems

kitaru-langfuse-importer

Agent traces you can run, not just read.

replay-identification

A semi-latent state-space model that combines movement, LFP, and ensemble spiking information to identify periods of replay and decode its content in real time. Long Tao et al., unpublished.

terx

Browser-agent memory that turns repeated workflows into deterministic replays.

kitaru-logfire-importer

Agent traces you can run, not just read.

kitaru-openai-agents

Agent traces you can run, not just read.

kitaru-claude-agent-sdk

Agent traces you can run, not just read.

kitaru-evaluator

Agent traces you can run, not just read.

kitaru-langgraph

Agent traces you can run, not just read.

substrate-kernel

A Python runtime that coordinates models and anything else you want through a single append-only log. Replay, diff, and trace every run.

aevum-mcp

Open-source AI agent governance kernel — cryptographic audit trails, consent-checked data access, and verifiable decision records.

aevum-core

Open-source AI agent governance kernel — cryptographic audit trails, consent-checked data access, and verifiable decision records.

kitaru-post-import-insights

Agent traces you can run, not just read.