Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Semble

Code search for agents that uses 98% fewer tokens than grep

Details

External ID
47997629
Source
HN
Company
—
Product
Semble
Website domain
github.com
Launched
May 3, 2026
Cohort
—
Upvotes
8
Upvotes percentile
0.4894991922455573
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.So we built Semble. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!

Enrichment

Theme
Claude integrations and coding agents
Vertical
Horizontal
Function
Search & retrieval
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
code search for ai agents
Manually corrected
False

Could you build this?

Partial Building a simple AST or symbol indexer is accessible, but building a production-grade code search tool that reduces token usage by 98% compared to grep across huge codebases requires sophisticated code graph indexing, chunking, and ranking algorithms.

What it would actually take: A production tool needs a high-performance parser (such as tree-sitter bindings in Rust), symbol resolution algorithms, and efficient lexical/hybrid vector indexing. It must parse language constructs (functions, classes, references) and output compact, semantically dense summaries specifically formatted for LLM context windows. Deep systems engineering and compiler/parsing domain knowledge are required.

Discussion

No comments on this launch.

Competitors

Other products that read as similar to this one — 268 launches clear the similarity bar, closest 8 shown.

Attention rank: #152 of 269 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 178 days after the earliest competitor.

Other launches for this product