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.

Semble is our solution for this. 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 services

Install in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" semble

Or check our README for other installation instructions, benchmarks, and methodology:

Semble: https://github.com/MinishLab/semble

Benchmarks: https://github.com/MinishLab/semble/tree/main/benchmarks

Model: https://huggingface.co/minishlab/potion-code-16M

Let us know if you have any feedback or questions!

I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead).

For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.

Better than grep obviously, but how does this compare to existing LSPs?

Shouldn’t it be a part of the harness at least for local codebase? I wonder how many harnesses are doing that already.

Semantic code search seems like a useful tool for a human too. Not just for agents.

How does this compare with colgrep?

https://github.com/lightonai/next-plaid/tree/main/colgrep

I also like the index feature form https://maki.sh Source code has a lot of structure, using a real parser instead of grepping and reading files can potentially save a lot of tokens

Would this replace something like codebase-memory-mcp[1] or improve when both is being used?

[1] - https://github.com/DeusData/codebase-memory-mcp

This looks great! I built a tool in the same space- and I found that the biggest challenge was often to get the agent to prefer to use the tool over bash tools. What’s your experience with that?

How does it compare to context-mode or serina that are both well established now?

Congratulations on the release!

Could you add fff to the benchmarks?

Very useful thanks for sharing!

Does this work well for non-coding documents as well? Say api docs or AI memory files?

Is the benchmark measuring one-shot retrieval accuracy, or Coding agent response accuracy?

grep doesn't need tokens, so what is 98% fewer than zero?

very curious to give it a spin but why write a cli in python? would surely be faster and more portable with go or rust?