Semble
Fast code search for agents with near-transformer accuracy
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hey HN! We've just open-sourced Semble, a fast and accurate code search library built for agents. We're also releasing potion-code-16M, a small code-specialized static embedding model that powers it.Most embedding-based code search methods are either too slow to index on demand or need GPU infrastructure, while grep-style retrieval methods often cannot find the relevant content. Semble combines the speed and quality benefits of both, so agents waste less time and fewer tokens exploring.Main features:- Fast: indexes a full codebase in ~250 ms and answers queries in ~1.5 ms, all on CPU (roughly ~200x faster indexing and ~10x faster queries than a code-specialized transformer).- Accurate: on par with code-specialized transformer models at a fraction of the size (see our benchmarks for more info).- MCP server: drop-in tool for Claude Code, Cursor, Codex, OpenCode, and any other MCP-compatible CLI/agent. Repos are cloned and indexed on demand.- Zero setup: runs on CPU with no API keys, GPU, or external services.Install as an MCP server for Claude Code:claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for install instructions for Codex, OpenCode, Cursor, and other agents.Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksHow it works: https://github.com/MinishLab/semble#how-it-worksModel: https://huggingface.co/minishlab/potion-code-16M
HN · launched Apr 26, 2026 · 7 upvotes (top 61%) · 0 views
Niche: semantic search and rag tools · 93 launches, 0 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Search & retrieval
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 93 launches in semantic search and rag tools →
Could you build this?
Partial The client library and local search index can be vibe-coded, but training a specialized 16M parameter static embedding model from scratch requires custom ML training data curation and modeling.
What it would actually take: A full version requires training a specialized static embedding model (like potion-code-16M) on billions of AST/code tokens using contrastive learning and distillation techniques. The serving stack uses a high-performance vector index (written in Rust or C++) optimized for CPU cache efficiency and sub-millisecond search across local codebases.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one : 740 launches clear the similarity bar, closest 8 shown.
Attention rank: #446 of 741 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 179 days after the earliest competitor.
- WarpGrep: A 20x faster subagent to grep for code · yc · 2025-11-28 · 17 upvotes · similarity 0.53
- CodeRLM · hn · 2026-02-11 · 81 upvotes · similarity 0.52
- Faster, cheaper Claude Code with local semantic code search via sqlite · hn · 2026-03-11 · 10 upvotes · similarity 0.51
- Mini-coder · hn · 2026-03-02 · 6 upvotes · similarity 0.49
- semq · github · 2026-10-05 · 11 upvotes · similarity 0.48
- jevgrep · github · 2026-09-20 · 66 upvotes · similarity 0.46
- 1Code · hn · 2026-01-15 · 75 upvotes · similarity 0.45
- CodeDiff · hn · 2026-09-29 · 7 upvotes · similarity 0.45
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.