#coding agents
8 stories
4DCodeBench tests coding agents' motion reconstruction
Coding agents struggle to rebuild motion from video, 4DCodeBench reveals.
RuntimeWire · 1m
Ted Haley Releases Pensieve for Coding Agents
Ted Haley launches Pensieve, a local search tool for coding agents.
RuntimeWire · 1m
How to build better coding agents
Researchers break down the components that make AI coding agents work, revealing what actually matters for performance.
arXiv · 1m
Skillsync: portable AI context across coding agents
Move your AI coding sessions between different agents without losing context or starting over.
Skillsync · 1m · 6 views
Cloudflare's AI security auditor skill
Open-source tool that turns coding agents into systematic security auditors with verified findings and machine-readable reports.
GitHub · 1m
OpenSpec: Build the right thing, right
A lightweight framework that keeps teams and AI agents aligned on what to build and how to build it.
OpenSpec · 1m
SWE-2: near-frontier coding at a quarter the price
Cognition's new coding model scores within a point of Fable 5.1 while costing 64% less, and the trick is how they penalized cost during RL.
Cognition · 3m · 7 views
How AI Coding Agents Choose Their Tools
A study of 16,893 sessions reveals how Claude Code, Codex, and Cursor evaluate and choose developer tools.
Armature · 2m