codegraph has 19K GitHub stars. GitNexus has 40K. Aider has 20K. We benchmarked 7 systems on 302 tasks across 17 codebases, 8 languages. knowing is 3.79x more precise than codegraph, 6.00x vs GitNexus, 6.35x vs Gortex, 22.0x vs grep. 13 self-adapting mechanisms that compound over time.
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.
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.
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.
We built a reproducible experiment measuring how many tokens AI coding agents consume when navigating code with grep vs LSP. On HashiCorp Consul (319K lines), LSP uses 34x fewer tokens. On a TypeScript rename across 24 files: 1,441x fewer bytes. The experiment covers 4 codebases, 3 languages, 13 tasks covering 7 agent workflows.
MCP servers are the tools AI agents rely on. We tested 55 of them with mcp-assert, found 20 bugs across 9 servers, and submitted fix PRs. Grafana and Ant Group merged ours. Three days after launch, Ant Group’s visualization team asked us to integrate mcp-assert into their CI. The most common failure: servers throw unhandled exceptions instead of returning isError, leaving agents unable to recover.
I needed AI agents to reliably rename symbols, find references, and check diagnostics without silent failures. The existing MCP-LSP tools were stateless, feature-poor, and untested. So I built agent-lsp: a persistent runtime with 50 tools, 20 provider-agnostic skills, speculative execution, and an audit trail for every AI-driven edit.
Agents accumulate autonomous behaviors over time - ‘always do X before Y’, ‘if you see Z then do W’. These instructions eat context budget, drift across invocations, and can’t be observed or tested. How to recognize when an autonomous behavior is a skill waiting to be extracted, and the layered model that makes the boundary clear.
Claude Code agents write code fast. Too fast to catch quality issues in real-time. Here’s how to build validation directly into agent workflows using hooks and team coordination - micro validation after every file write, macro validation before completion, and independent review from validator agents.
The Scaffold Agent doesn’t add capability. It restores a review gate that was cosmetically present but structurally absent. The worktree isolation trip wire catches failures that were invisible until merge time. Neither fixes a bug in the traditional sense. Both fix trust.
Scout-and-wave v0.1.0 worked. Then we ran it on documentation agents, measured the overhead honestly, and learned that raw agent count is a bad proxy for when parallelism is worth it. This post covers the audit-fix-audit loop, the dogfooding experiment that confirmed SAW was 88% slower than sequential for that job, SAW Quick mode for small disjoint work, and the bootstrap problem for new projects.
The scout refused to write the IMPL doc. Forty-five percent of agents arrived at work already done. The skill file grew to 400 lines with no separation of concerns. Each failure drove a specific fix — and each fix is traceable to an exact incident in an exact run. This is the scout prompt’s bug tracker.
Naive parallel agents step on each other. The scout-and-wave pattern solves this by front-loading dependency mapping: one throwaway agent identifies seams and builds a living coordination artifact before any implementation begins. Development then proceeds in waves, each consuming and updating the artifact for the next.
Most developers cargo-cult their SSH config from Stack Overflow. This is the setup I actually run: three GitHub identities on one machine, persistent control sockets, conditional git configs that auto-select the right key, and pinned known_hosts. No third-party tools.
Most CLI tools ship with no visual identity beyond a help screen. Here’s how I used AI image generation to create Shelby, a consistent mascot with a locked-down spec, and built a complete brand system - poses, screencasts, color palette, terminal theme - for shelfctl in 4 days.
Why copyleft licenses ‘infect’ derivative works, how GPL differs from permissive licenses, and when viral licensing protects community contributions from proprietary capture
Why Apache 2.0 matters for patent-heavy projects, how it differs from MIT, and when explicit patent grants protect your users and contributors
Why MIT became the most popular open-source license, when to choose it over GPL/Apache/BSD, and a decision framework for selecting the right license for your project
Part 2: A comprehensive reference covering every glob pattern from basic wildcards to advanced features like brace expansion and extended globs. Learn the rules that apply everywhere.
Glob patterns are everywhere - .gitignore, shell wildcards, build configs - yet most developers learn them by accident through copy-paste. Here’s why glob deserves explicit teaching.