Skip to content

DEV Community

Marcell Havlik

Building TODO for AI — a TODO list where the items get done by AI agents. Benchmarks, agent architecture, and what actually ships.

Budapest, Hungary Joined on Sep 22, 2026 https://todofor.ai

Sep 22

Claude Code for non-coders and non-coding tasks: what works, what doesn't, and what to run for the rest

#claudecode #aiagents #productivity #comparison

4 min read

Sep 22

How an AI agent works in your logged-in browser: extension vs CDP relay vs cloud browser

#browseragent #chromeextension #aiagents #security

5 min read

Sep 22

Our task categorizer routed 46% of tasks. A $0.04/MTok decision model routes 97%.

#benchmarks #categorization #embeddings #llm

3 min read

Sep 22

94.7% on LoCoMo — and why most of the gap between published memory numbers isn't the memory

#memory #benchmarks #agents #llm

9 min read

Sep 22

voiceloop: the fastest voice agent loop in the browser is now open source

#voice #agents #benchmarks #opensource

5 min read

loading...