# cosmtrek/mindwalk

A visualization tool that replays coding-agent sessions on a 3D map of your codebase.

Repository: https://github.com/cosmtrek/mindwalk
Canonical: https://ross.abutalabs.com/products/mindwalk
Language: Go
License: MIT
License Family: permissive
Last push: 2026-08-10T02:06:47+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 96, longevity 3
- inputs: {"age_days": 55, "days_push": 24, "days_rel": 26, "gap_med": 3.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1287, forks 111 (observed 2026-08-28T04:04:14.978303+00:00)

## What it is
mindwalk is a Go CLI tool that replays coding-agent sessions (Claude Code, Codex, pi) as glowing activity on a 3D map of your codebase. It runs fully locally, serving a browser UI that visualizes which files the agent searched, read, and edited during a session.

## Use cases
- visualize how a coding agent explored my repo during a session
- replay Claude Code session logs on a 3D codebase map
- understand which files an AI agent touched and edited
- review agent session footprints against intended task scope
- export a repository citymap JSON for analysis
- evaluate a coding-agent session quality with an LLM judge

## When to choose
- you use Claude Code, Codex, or pi and want insight into agent behavior
- you need to audit or review what an AI agent did across your codebase
- you prefer a fully local tool with no data sent anywhere

## When to avoid
- you don't use coding-agent tools or have no session logs
- you need a general-purpose code visualization tool independent of agent sessions

## Facets
- artifact type: cli-tool
- maturity: active
- function: data-visualization, developer-tools, cli
- domain: developer-tools, artificial-intelligence, data-visualization
- platform: windows, cli, browser
- tags: coding-agents, session-replay, 3d-visualization, claude-code, codex, codebase-map, local-first, ai-agents, linux, macos

## Member repositories
- cosmtrek/mindwalk (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.978303+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:55:51.371256+00:00, confidence not recorded.
  - readme: https://github.com/cosmtrek/mindwalk (fetched 2026-08-28T04:04:14.978303+00:00, sha b58402d77fdc)
- Data as of 2026-08-30T08:39:29.467469+00:00.