Semble
Hacker ApprovedRanked 3 of 15 code search tools by recommenders
Developers recommend Semble for fast local code search that needs fewer tokens and queries than grep. Critics question how the token savings are measured.
Developers recommend Semble for fast local code search that needs fewer tokens and queries than grep. Critics question how the token savings are measured.
27 people gave an opinion
- recommend it
- 20
- criticize it
- 7
- approval share
- 74%
Recommended in 4 of 13 months
- November 2025: recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 20 people recommend itNeeds 10 or more, met.
- 2.9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 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
Fast indexing and quick results
“it blow away my kludged solution particularly given that it doesn't have a lengthy indexing process”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “Semble indexes for like 3 seconds and prints out the actual code that runs the model on the CPU.”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “Semble is fast enough that it's not going to be behind.”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” - Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
- Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
- Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
Fewer queries and better context efficiency
“you need fewer semble queries to achieve the same outcome, compared to grep+readfile calls”
Comment from 17 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “fewer correction cycles are more valuable than tokens themselves”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “Clearly a win for Semble for context efficiency”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” - Comment from 19 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
Working well in everyday use
“we do believe that Semble makes agents better based on our own experience of using it for the past months while in development”
Comment from 19 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “The results are much better. Even better than my own setup, but, vary a lot.”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “So far our experience is good with Semble”
Comment from 19 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” - Comment from 17 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
Finds results grep misses
“This seems to work better for the "how does auth work" style of queries”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “Semble surfaced things grep missed”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep”
What people warn about
Each mark is one comment
Token savings baseline questioned
“So are we supposed to believe that grep is so wasteful that models are reading 98% useless garbage every time they call it?”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “The savings are calculated against the assumption that agents read the matched files in their entirety.”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “grep doesn't need tokens, so what is 98% fewer than zero?”
Comment from 17 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” Setup friction and MCP hangs
“codex-cli hangs when calling this through the MCP. The semble process even sticks around as a zombie”
Comment from 18 May 2026 in “Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep” “require some arcane instructions to coerce Claude Code into compliance”
Comment from 14 Jun 2026 in “Don't trust large context windows”
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 |
| SembleThis page | 20 | 7 | 74% | 4 | — | Approved |
| Graft (Claude Code hooks) | 13 | 4 | 76% | 4 | — | Approved |
| Lat.md | 11 | 3 | 79% | 3 | — | — |
What people said
30 of the 35 comments that mention it, newest first. Each links to the original comment.
“except for Semble and Serena”
“require some arcane instructions to coerce Claude Code into compliance”
“The efficiency gains are compelling”
“So far our experience is good with Semble”
“we do believe that Semble makes agents better based on our own experience of using it for the past months while in development”
“it blow away my kludged solution particularly given that it doesn't have a lengthy indexing process”
“The library is extremely fast.”
“I feel this should be a mode on ripgrep. a disk search-lib in python? really?”
“fewer correction cycles are more valuable than tokens themselves”
“semble indexing (if any) took no noticeable time”
“This looks like the latter pushed harder than I've seen before.”
“codex-cli hangs when calling this through the MCP. The semble process even sticks around as a zombie”
“Semble is fast enough that it's not going to be behind.”
“So are we supposed to believe that grep is so wasteful that models are reading 98% useless garbage every time they call it?”
“My first contact instinct is that this will result in a net negative 'deployable intelligence' over long horizon runs”
“Semble surfaced things grep missed”
“The tool itself is fully local though, so there's no real security risks there”
“The savings are calculated against the assumption that agents read the matched files in their entirety.”
“The results are much better. Even better than my own setup, but, vary a lot.”
“Semble only does 1 thing: very quick code search, that's it.”
“This is really useful and very much like the experiments we want to be doing in the near future”
“it surfaced the right files pretty quickly”
“This seems to work better for the "how does auth work" style of queries”
“Clearly a win for Semble for context efficiency”
“Semble indexes for like 3 seconds and prints out the actual code that runs the model on the CPU.”
“unlike grep it's probabilistic search on search terms”
“it's been working pretty well so far”
“you need fewer semble queries to achieve the same outcome, compared to grep+readfile calls”
“grep doesn't need tokens, so what is 98% fewer than zero?”
“for an alpha it has quite a bit of potential”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.