jzOcb

jzOcb / context-doctor

Public

🧠 Visualize and diagnose OpenClaw context window usage — terminal, PNG, or JSON

32
1
100% credibility
Found Mar 09, 2026 at 30 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

This tool scans an OpenClaw AI workspace to visualize file sizes, skill lists, and token usage in the context window, providing a health score and suggestions for optimization.

How It Works

1
🚨 AI Forgets Conversations

You notice your AI assistant losing track of chats and wonder what's clogging its memory.

2
🔍 Discover Context Doctor

You learn about this handy tool that checks your AI setup's memory usage like a doctor visit.

3
📥 Add to Your Workspace

Easily install it into your AI folder using a quick command or by copying the files.

4
▶️ Run the Check

From your folder, start the tool to scan your setup files and skills.

5
📊 See the Colorful Report

A beautiful chart pops up showing what's taking space, warnings for big files, and room left for talks.

6
🩺 Review Health Score

Check the green, yellow, or red score with tips to trim if your memory is crowded.

🟢 AI Chats Smoothly

With a healthy setup, your assistant remembers everything and responds perfectly.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 30 to 32 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is context-doctor?

context-doctor is a Python CLI tool that scans your OpenClaw workspace to visualize context window usage, spotting bloated bootstrap files, truncated instructions, and token-hungry skills. Run one command for a colored terminal breakdown, PNG diagram for chats, or JSON output—perfect for doctor context in agent setups where every token counts toward conversation room. It auto-detects your workspace, estimates budgets against 200k defaults, and flags health like a context diagram for doctor appointment systems.

Why is it gaining traction?

Unlike generic token counters, it tailors to OpenClaw's bootstrap files and on-demand skills, delivering bar charts, warnings for missing files, and a health score (green under 10% usage). Developers dig the PNG export for sharing doctor who context meme-style diagnostics in team chats, plus JSON for scripting—think visualize GitHub actions but for AI context bloat. Custom flags for workspace paths and context sizes make it dead simple for daily checks.

Who should use this?

OpenClaw agent builders wrestling with 128k+ models, where workspace files like AGENTS.md silently truncate. AI devs tuning prompts in multi-skill setups, or teams debugging why agents forget mid-convo—the good doctor context for the doctor sleep context crowd. Skip if you're not in OpenClaw; it's niche.

Verdict

Grab it if you're deep in OpenClaw—solid docs and MIT license make it a quick win despite 14 stars and 1.0% credibility score signaling early maturity. Test in a sandbox first; no tests visible, but user-facing outputs nail the job.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.