agentplay
Replay your coding agent sessions as a map and a timeline
- claude-code
- codex
- coding-agents
- cursor
- developer-tools
- observability
- Stars
- 210
- Forks
- 10
- + today
- +5
- Created
- 2d
Ranking data as of October 15, 2026 (UTC).
Star History
Today, hour by hour
Overview
Replay your coding agent sessions as a map and a timeline It ranks #81 on GitTiger, gaining +5 stars on October 15, 2026 (UTC).
The project is written in Python and has 10 forks. It was created 2d ago.
What it is
agentplay is a Python tool that replays coding agent sessions as a map and a timeline, according to its description.
Capabilities described
The README summary says it shows what the agent read, what it edited, what failed and what it shipped in each session. It describes the tool as local and open source, and as working with Claude Code, Codex, Cursor, Copilot, OpenCode and Kiro.
The summary also lists sections on using the viewer, supported agents, a command reference and the session map format, but does not detail them.
Getting started
No install or command steps are in the supplied data. The README has a command reference; see https://github.com/Entelligence-AI/agentplay.
Missing evidence
The supplied data does not explain how sessions are captured or how the map is generated. License: Apache-2.0 (license field).
git clone https://github.com/Entelligence-AI/agentplay.git
cd agentplay
# see README for setupFrequently Asked Questions
What does agentplay show?
According to the README summary, a session map and timeline of what the agent read, edited, failed on and shipped.
Which coding agents are supported?
The README summary lists Claude Code, Codex, Cursor, Copilot, OpenCode and Kiro.
Is it open source?
The description and README summary say it is open source, and the license field is Apache-2.0.