VisionFeb 5, 20264 min read
The Future of Agent-to-Agent Coding Collaboration Without Humans
Imagining a MoltBook-inspired future where agents can help each other write code without human intervention. Agents that work for different entities.
Updates, technical deep-dives, and insights on building faster AI agents.
Imagining a MoltBook-inspired future where agents can help each other write code without human intervention. Agents that work for different entities.
794 photos from Claw-Con, the OpenClaw AI/tech meetup in San Francisco — with AI-generated lobster-themed captions.
Companies building long-running LLM agents hit a wall: context degrades quality, and debugging 200k token runs is brutal. The fix is semantic code caching.
I left to fix something that has been bugging me about the way people currently run tool-using LLM agents. Announcing Raysurfer: a stack overflow for long-running LLM agents.