Semble indexes codebases, cuts agent token use 98%

Summary

Agents waste tokens reading full files to find code; Semble returns only matched chunks, reducing context window pressure and latency on every retrieval step. Replaces manual grep exploration with semantic search agents can call directly.

Why it matters

Agents waste tokens reading full files to find code; Semble returns only matched chunks, reducing context window pressure and latency on every retrieval step. Replaces manual grep exploration with semantic search agents can call directly.

Sources

1. 1.returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read
2. 2.indexes an average repo in ~250 ms and answers queries in ~1.5 ms, all on CPU
3. 3.NDCG@10 of 0.854 on our benchmarks, on par with code-specialized transformer models
4. 4.Everything runs on CPU with no API keys, GPU, or external services
5. 5.~200x faster indexing and ~10x faster queries than a code-specialized transformer