tilth
Shares rank 7 of 15 code search tools by recommenders
Recommended as a simple, daemon-free code navigation tool for AI agents that cuts token use by about 40% in benchmarks. Main caveat: agents may do worse with niche tools.
Recommended as a simple, daemon-free code navigation tool for AI agents that cuts token use by about 40% in benchmarks. Main caveat: agents may do worse with niche tools.
10 people gave an opinion
- recommend it
- 9
- criticize it
- 1
- approval share
- 90%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Cuts token use and cost
“my agent has been able to use them very effectively and I've seen context usage drop considerably”
Comment from 19 May 2026 in “Ask HN: Is there a good code intelligence MCP server yet?” “now agents find things faster and with ~40% less token use (benchmarked)”
Comment from 4 Apr 2026 in “We replaced RAG with a virtual filesystem for our AI documentation assistant” “benchmarked to reduce cost per correct answer by ~40%”
Comment from 18 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK” - Comment from 9 Mar 2026 in “Ask HN: What Are You Working On? (March 2026)”
- Comment from 6 Mar 2026 in “Claude Code told me what tools it needs to work faster”
Faster, more accurate answers
“in the benchmarks, I'm seeing very positive results with Haiku, getting quicker and more correct answers”
Comment from 10 Mar 2026 in “Show HN: Tilth v0.5.0 –> ~40% cheaper AI code navigation (160 runs, 3 models)” “That's already better than RTK because you measure task accuracy AND savings!”
Comment from 19 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK” Preferred over alternative tools
“That's already better than RTK because you measure task accuracy AND savings!”
Comment from 19 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK” “Very cool. I'll probably switch away from AFT to this.”
Comment from 19 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK” “On the surface, I like your approach a bit better.”
Comment from 19 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK”
Other code search tools people recommend
The four most recommended other code search tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| ripgrep | 122 | 18 | 87% | 12 | — | Approved |
| ast-grep | 21 | 3 | 88% | 9 | — | Approved |
| Semble | 20 | 7 | 74% | 4 | — | Approved |
| Graft (Claude Code hooks) | 13 | 4 | 76% | 4 | — | Approved |
| tilthThis page | 9 | 1 | 90% | 6 | — | — |
What people said
15 of the 16 comments that mention it, newest first. Each links to the original comment.
“Not as precise as LSP but simple (no daemon), human readable, and in many cases works without configuration.”
“That's already better than RTK because you measure task accuracy AND savings!”
“Very cool. I'll probably switch away from AFT to this.”
“On the surface, I like your approach a bit better.”
“benchmarked to reduce cost per correct answer by ~40%”
“Oh that is a nice approach whish more benchmarks did cost per successful”
“my agent has been able to use them very effectively and I've seen context usage drop considerably”
“This seems really good...going to test it :)”
“now agents find things faster and with ~40% less token use (benchmarked)”
“in the benchmarks, I'm seeing very positive results with Haiku, getting quicker and more correct answers”
“Reduces LLM token use and cost by ~40% (benchmarked)”
“saves you 30% token use (benchmarked)”
“Agents tend to perform worse with niche tools”
“You might find it useful for markdown as well, especially if you add support for section-based addressing”
“I implemented this hash (read and edit) approach in tilth if you want to test it out.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.