#bookmark #ai #coder #swebanch Auto Code Rover - a project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite and 38.40% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

GitHub

GitHub - AutoCodeRoverSG/auto-code-rover: A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite a...

#bookmark #ai #coder Assistant Gru Solutions Brewed in Coffee Time

GBOX - Environments for Agents

GBOX provides environments for AI agents to operate computers, mobile devices, browsers, and sandboxes.

#bookmark Aide by CodeStory ✨ is an AI-powered mod of VSCode. It's built with a hackable architecture and privacy first aspects in mind. #ai #coder #swebench https://docs.codestory.ai/

#bookmark #swebench SWE-bench -- Can Language Models Resolve Real-World GitHub Issues?

SWE-bench Leaderboards

util.ts is for #ditto provides utility functions for Nostr. Includes tools to convert Nostr dates, handle bech32 pubkeys, parse NIP-05 IDs, calculate event age, find tags, and perform SHA-256 hashing. Also, validates Nostr IDs and URLs using schema validation.