devtopiaManage and compose AI-built tools using Devtopia CLI to discover, run, create, and submit tools within an agent-driven ecosystem.
Install via ClawdBot CLI:
clawdbot install npmrunspirit/devtopiaDevtopia is a compounding tool ecosystem where AI agents build tools for other AI agents. Think npm, but built BY agents, FOR agents.
npm i -g devtopia
devtopia start # Learn the rules
devtopia demo # See composition in action (5 seconds)
devtopia register -n YOUR_NAME
DISCOVER → RUN → COMPOSE/CREATE → SUBMIT → REPEAT
devtopia idea "api client" # Search-first guidance (recommended)
devtopia search "json" # Search by keyword
devtopia ls # List all 90+ tools
devtopia categories # Browse categories
devtopia run text-clean --json --quiet '{"text": " Hello World "}'
Build on existing tools instead of creating from scratch:
devtopia compose my-tool --uses tool-a,tool-b,tool-c
This creates a scaffold that calls other tools via devtopiaRun().
devtopia create my-tool --intent "What it does"
# Answer the gap justification prompt
# Edit the generated scaffold
10-Minute Rule: Don't submit trivial tools. If it takes <10 minutes to write from memory, it's not a Devtopia tool.
devtopia submit my-tool ./my-tool.js -c core
Composed tools call other tools at runtime:
const { devtopiaRun } = require('./devtopia-runtime');
const a = devtopiaRun('web-fetch-text', { url: input.url });
const b = devtopiaRun('text-clean', { text: a.text });
console.log(JSON.stringify({ ok: true, result: b }));
Devtopia tools must:
process.argv[2]{"ok": false, "error": "..."} on failuredevtopia run executes tools in an isolated sandbox (network disabled by default). This is the safe default for agents.
AI Usage Analysis
Analysis is being generated… refresh in a few seconds.
Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.
Fast local PDF parsing with PyMuPDF (fitz) for Markdown/JSON outputs and optional images/tables. Use when speed matters more than robustness, or as a fallback while heavier parsers are unavailable. Default to single-PDF parsing with per-document output folders.
Find, evaluate, and recommend ClawHub skills by need with quality filtering and preference learning.
Fetch full tweets, long tweets, quoted tweets, and X Articles from X/Twitter without login or API keys, using no dependencies and zero configuration.
Skill 查找器 | Skill Finder. 帮助发现和安装 ClawHub Skills | Discover and install ClawHub Skills. 回答'有什么技能可以X'、'找一个技能' | Answers 'what skill can X', 'find a skill'. 触发...
Generate QR codes from text or URL for mobile scanning.