Optimized, auditable execution for Codex and Claude Code: bounded repository context, verified patches, and reproducible paired benchmarks.
git open-source security typescript mcp sandbox developer-tools codex ai-agents anthropic llm-tools context-management coding-agents agentic-ai model-context-protocol claude-code context-engineering repository-context auditable-ai patch-verification
-
Updated
Aug 10, 2026 - TypeScript