Agentplay: Local Replay and Visualisation for Coding Agent Sessions

RepositoryEntelligence-AI/agentplayTool

Agentplay is an open-source Python tool that parses transcripts from coding agents like Claude Code, Cursor, and Codex to replay their actions as an interactive map and timeline locally.

Key points

  1. Parses local transcript logs found in directories such as ~/.claude, ~/.codex, or ~/.cursor.
  2. Builds a timeline and radial map showing touched files, executed commands, context window limits, and MCP server calls.
  3. Operates fully locally without requiring accounts or API keys; session data stays on the machine.
  4. Requires Python 3.11+ with zero runtime dependencies beyond the standard library for the CLI.
  5. Supports Claude Code, Codex, Cursor, Copilot, OpenCode, and Kiro.

Why it matters

Coding agents frequently operate as black boxes, generating verbose session logs that developers rarely inspect. Agentplay provides necessary observability into file edits, tool failures, and retry loops directly on the local machine.

Analysis

Agentplay tackles observability in agentic development workflows by turning unstructured transcript logs into an intelligible timeline and dependency map. It allows software engineers to inspect which context files an agent evaluated before editing, detect repeated command failures, and observe subagent interactions. Technically, the project stands out by relying solely on the Python standard library for its CLI, paired with a local web-based viewer. With around 240 GitHub stars and an Apache-2.0 license, it represents an early-stage yet highly practical utility for teams relying heavily on terminal- and IDE-based coding assistants.

Found in

Summary generated by AI (Gemini 3.8 Flash, 18 October 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:tt-a1i/archify

    Archify: Interactive Architecture and System Diagrams for AI Coding Agents

    Archify is an open-source Node.js rendering and validation engine designed as a skill for coding agents like Cursor, Claude Code, Codex CLI, and OpenCode. Agents produce a typed JSON Intermediate Representation (IR), which Archify deterministically compiles into self-contained, interactive HTML, SVG, and media exports.

    45.5kstarsJavaScript

    AI & LLMs· Tool

  • Repository:anthropics/claude-code

    Claude Code: Terminal-Based Agentic Coding Tool

    Claude Code by Anthropic is an agentic coding tool that operates in the terminal. It understands codebases, executes routine development tasks, explains complex code, and handles Git workflows using natural language commands.

    144.1kstarsPython

    AI & LLMs· Tool

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Repository:rohitg00/agentmemory

    agentmemory: Persistent Memory for AI Coding Agents

    agentmemory is an open-source TypeScript solution providing persistent memory for coding agents and MCP clients. Powered by the iii engine, it builds on Andrej Karpathy's LLM Wiki pattern by introducing confidence scoring, lifecycle management, knowledge graphs, and hybrid search.

    28kstarsTypeScript

    AI & LLMs· Tool

  • Repository:anomalyco/opencode

    OpenCode: Open-Source AI Coding Agent

    OpenCode is an open-source AI coding agent available via a terminal interface and a standalone desktop application. Built with TypeScript, the project provides a free alternative to proprietary AI programming assistants.

    204.4kstarsTypeScript

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.