# git grep Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/git-grep
> Markdown URL: https://aitinkerers.org/technologies/git-grep.md
> Technology record last updated: 2026-05-29T17:19:09Z
> Generated: 2026-09-23T01:46:31Z

A lightning-fast command-line utility built directly into Git to search tracked files, the index, and historical commit trees for matching patterns.

When you need to find a specific string or regex pattern across your codebase, skip the slow filesystem searches and rely on git grep. Because it targets only files tracked by Git (or specific commits and branches), it bypasses node_modules and other untracked noise automatically. You can pinpoint patterns with flags like -n for line numbers, -p to show the containing function, or target historical snapshots by passing a commit hash (such as git grep 'TODO' HEAD~5). It is a highly optimized, native alternative to standard grep that respects your repository structure out of the box.

- Official technology site: https://git-scm.com/docs/git-grep
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [What Is Your Coding Agent Actually Searching?](https://columbus.aitinkerers.org/talks/rsvp_t4IMPq7lJnc)

I built SearchBench, a harness for running controlled evaluation rounds over coding-agent search behavior. A SearchBench round takes real bug-localization tasks, gives an agent access to a repository, and checks whether it found the files that were actually changed in the human fix. The harness compares an incumbent search strategy against one or more challengers, then writes a static evidence bundle with exact-hit, hop-distance, token-usage, failure, and report artifacts. For the demo, I’ll run a small live ablation round over three cases. I’ll reuse cached Bash/native-search results as the incumbent, then run a few IC challenger policies in parallel. The question is: when IC succeeds or fails, was the important factor anchor quality or graph lookahead? I’ll show the actual workflow: preflight cost prediction, run planning, parallel execution, actual spend, cost-prediction error, generated bundle artifacts, and a short report explaining what changed. One thing I want to show explicitly is how much information the harness can derive from a small, bounded run: exact hits, hop distance, token usage, failure modes, and the next optimization target.

- Event context: AI Tinkerers - Columbus June Meetup — 2026-06-01 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_t4IMPq7lJnc

## Related Technologies

- [bash](https://aitinkerers.org/technologies/bash) ([Markdown](https://aitinkerers.org/technologies/bash.md)) — 12 public demos
- [Code](https://aitinkerers.org/technologies/code) ([Markdown](https://aitinkerers.org/technologies/code.md)) — 9 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [Harness](https://aitinkerers.org/technologies/harness) ([Markdown](https://aitinkerers.org/technologies/harness.md)) — 2 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [rg](https://aitinkerers.org/technologies/rg) ([Markdown](https://aitinkerers.org/technologies/rg.md)) — 1 public demo
- [tree-sitter](https://aitinkerers.org/technologies/tree-sitter) ([Markdown](https://aitinkerers.org/technologies/tree-sitter.md)) — 8 public demos