Semble – Code search for agents that uses 98% fewer tokens than grep
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…
In plain words
Semble is an open-source code search tool designed for AI agents working with large codebases. It combines static embeddings and BM25 search to find relevant code snippets while using 98% fewer tokens than traditional grep-based approaches. The tool runs on CPU, requires no API keys, and works across 19 programming languages, addressing the problem of inefficient code retrieval when AI agents can't locate information directly.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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!
Does the same job
all alternatives →- SCSemble – Code search for agents that uses 98% fewer tokens than grepMay 2026 · github.com · ▲8
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…
- SFSemble – Fast code search for agents with near-transformer accuracyApr 2026 · github.com · ▲7
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…
AgentmemoryMay 2026 · agent-memory.dev · ▲322Persistent memory for Claude Code, Codex & coding agents
- INI nerfed our coding agents on purposeJun 2026 · ▲27
Tl;dr: I trained a classifier to route to the least expensive model and reasoning depth to complete the request. Coupling that with additional automated token efficiency techniques has yielded 3x usage for the same spend. For anyone interested in trying it themselves: https://nerfguard.com Various teammates and I switched over to Codex from Claude Code recently. We still bounce between the tools, but Codex’s speed and steerability coupled with performance gains were hard to ignore. One of the downsides was that the per token pricing kicked in way sooner. This is happening across…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com