Knowing
We Benchmarked the Most Popular Code Search Tools. We Beat All of Them.
codegraph has 19K GitHub stars. Aider has 20K. We benchmarked 7 systems on 117 tasks across 7 codebases (3.5M LOC to 14K LOC). knowing is 1.36x more precise than codegraph, 2.45x vs GitNexus, 2.92x vs Gortex, 14.2x vs grep. Queries Kubernetes in 2ms (codegraph: ~1s), eliminates 99.9% of grep noise on ambiguous queries.
Your AI Agent's Code Search Hits 2% of the Time. We Benchmarked It.
Rigorous benchmark of AI agent code retrieval: 107 tasks, 5 repos, 5 languages, 4 competitors. grep precision: 2%. GitNexus: 7.6%. knowing: 23% (11.5x better, p<0.0001). Plus: 193x faster indexing, 28x less RAM, 48x more token-efficient than Repomix. The first statistically validated comparison of code intelligence tools for AI agents.
The Code Intelligence Landscape: Context, Memory, and Proofs
AI coding agents have a context problem. The tools solving it fall into four categories: context packers, code graphs, memory systems, and runtime observability. Each solves one piece. None versions the intelligence. None proves anything. None learns without poisoning itself over time. This article explores the landscape and argues that content-addressed code graphs with cryptographic proofs are the missing foundation.
What Git Did for Files, Applied to Code Relationships
Git proved that content-addressing file contents gives you integrity, history, efficient equality, and distributed collaboration for free. The same architecture applied to code relationships gives you something new: versioned intelligence that you can diff, cache, prove, and trust over time.