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…
Semble – Code search for agents that uses 98% fewer tokens than grep launched on May 17, 2026 with 445 votes, #24 of 20,538 launches that month and more than 99% of that year's launches.
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
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read - MinishLab/semble
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…
Does a similar job
all alternatives →
Web Search Agents by NimbleAug 2026 · nimbleway.com · ▲371Self-learning agents automate web research + retrieval
Sourcebot, an open-source Sourcegraph alternative2024 · github.com · ▲259Hi HN, We’re Brendan and Michael, the creators of Sourcebot (https://github.com/sourcebot-dev/sourcebot). Sourcebot is an open-source code search tool that allows you to quickly search across many large codebases. Check out our demo video here: https://youtu.be/mrIFYSB_1F4, or try it for yourself on our demo site here: https://demo.sourcebot.dev While at prior roles, we’ve both felt the pain of searching across hundreds of multi-million line codebases. Using local tools like grep were ill-suited since you often only had a handful of codebases…
CodeRLM – Tree-sitter-backed code indexing for LLM agentsFeb 2026 · github.com · ▲81I've been building a tool that changes how LLM coding agents explore codebases, and I wanted to share it along with some early observations. Typically claude code globs directories, greps for patterns, and reads files with minimal guidance. It works in kind of the same way you'd learn to navigate a city by walking every street. You'll eventually build a mental map, but claude never does - at least not any that persists across different contexts. The Recursive Language Models paper from Zhang, Kraska, and Khattab at MIT CSAIL introduced a cleaner framing. Instead of cramming everything into…
Mantic.sh – A structural code search engine for AI agentsJan 2026 · github.com · ▲81Author here! Some context: I published this 48 hours ago and it was auto-listed on MCPMarket (the MCP tools directory). Got 700+ organic downloads with zero marketing—developers were actively searching for exactly this solution. The "Git Accelerator" optimization story: Initially used a file walker that took 6.6s on Chromium. Profiling showed 90% was filesystem I/O. The fix: git ls-files returns 480k paths in ~200ms. Added smart heuristics for untracked files (only scan dirs <50k files), bringing total to 0.46s. Why this matters: Agents can't wait 10 seconds for search. Sub-500ms makes…
- CACodebased, an AI Search Engine for Code2024 · codebased.sh · ▲17
Codebased combines Tree Sitter for code awareness (find functions, data structures, constants, etc. not just lines of code), full-text search using SQLite, and semantic search using OpenAI embeddings + FAISS. Despite being implemented in Python, supporting semantic search, making multiple API calls for embedding and re-ranking, it is faster than ripgrep for runng searches against the Linux kernel (takes ~1 second vs. ~2 seconds, obviously depends on system, temperature, time of day, tidal forces, etc.) Up next: - A Perplexity-like agent for interpreting results, making multiple follow-up…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
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
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com