Try Benzi
A coding harness/agent beating Claude Code itself on Sonnet. Benzi - Compiler-backed AI coding agent. It compiles your codebase into a resolved map of calls, data flow, control flow and class hierarchy, then reads, edits and verifies code using it. 82.6% on SWE-bench Verified at 1.85 cents per task. Been working on something that should've been made a long time ago imo.

Reactions (1)
Similar products
by description similarity
AI powered cli coding agent that monitors your dev/test server and fixes errors and adds features
Claude-replay
github.comA video-like player for Claude Code sessions
Autonomous game development with Claude Code and Codex
MyCoder
github.coman open source Claude-Code alternative
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.