signalHacker News Show HN2026-09-21
Show HN: Ambits - agentic grep/rg tool will history tracking
Ambits is an agentic grep/rg tool for coding AI agents that returns symbol definitions as structured JSON (by name or content hash) instead of whole files, and journals every symbol read so `restore-context` can hand history back after context compaction. Installed via `cargo install ambits`, it works with Claude Code, records read depth per symbol, and distinguishes "unread" from "nobody was watching" via a coverage object in `--json` output. Its `ambits rg` front-end mirrors ripgrep's flags and regex engine, annotating each match with its enclosing symbol and read depth while supporting `--no-symbol` for byte-identical ripgrep output.
- why now
- New agent tool launch: gain efficiency now.
- topic
- AI Tools & Agent Workflows
- source
- Hacker News Show HN
#Claude Code
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source