vibehacker
News
GitHub / Benzi ·

Benzi: compiler-backed coding agent hits 78.2% on SWE-bench Verified for $37

Benzi parses your repo with tree-sitter into a resolved map of symbols, call edges, data flow, and inheritance, then has the model query it through ~36 structured tools instead of reading raw files; it ships as a VS Code extension, a pip install benzi package, and an MCP server. Its authors report 391/500 on SWE-bench Verified with DeepSeek v4-flash at pass@1 for $37.33 total, a self-run result that includes a review pass, not just the index.

More news

View all

Darktrace MCP Server now generally available

Announced Nov 13, the server lets AI assistants query security alerts, pull Cyber AI Analyst findings, and run triage actions across licensed Darktrace products. A read only mode hides tools that change data…

Darktrace

Spotted something we missed? Start a thread.