TechCrunch rounds up AI agents that live in your text messages

Offrun runs coding-agent CLIs locally on Apple Silicon Macs, giving each agent its own git worktree so parallel agents never touch the same files. It uses your existing agent logins, moving a chat to another account when one hits its limit.

A developer spent the past week building a strategy combat game described as "fantasy airship FTL," with crew dungeon runs, cargo quests, and mage crew members. It is playable for free.

A llama.cpp expert-streaming setup on Windows hits ~11.5 tok/s with the UD-IQ3_XXS quant of Qwen3.8-Flash-Next 177B, up from roughly 7 tok/s on the inherited setup. Hardware is an RTX 5070 with 12GB VRAM plus 32GB DDR4 RAM.

A LocalLLaMA user built a dedicated RAG/search node for Qwen3.8 27B using a cheap AliExpress mini PC that arrived with fraudulent hardware instead of the promised Intel N150 with DDR4/DDR5 support.

A patent attorney with 20 years of experience and 300+ filed industrial-automation patents argues robotics startups lose when they delay IP filings, citing Boston Dynamics' 2022 suit against Ghost Robotics over fall-recovery "core technology." Swarm robotics raises an unresolved question: whether the behavior of a swarm can be patented, or only the machines producing it.