sift

Fast local search over your text and Markdown files, built for AI agents.

sift indexes folders of .md and .txt files, embeds them on your GPU, and runs a server that agents query over MCP. It offers three kinds of search: exact keyword matching, semantic search, and hybrid retrieval with reranking for RAG. Everything runs locally. No cloud services, no API keys.

Install

Requires Python 3.11 or newer. With uv:

uv tool install --torch-backend auto sift-rag   # installs the `sift` command

Or run it without installing: uvx --torch-backend auto sift-rag serve. With pip, in a virtual environment: pip install sift-rag.

On first use, sift downloads its two models from Hugging Face (about 1.5 GB).

GPU support

sift uses an NVIDIA GPU (CUDA) if there is one, else an Apple GPU, else the CPU, which works but embeds slowly.

• Linux, macOS: nothing to do. PyTorch from PyPI includes CUDA on Linux and uses the Apple GPU on macOS.
• Windows: PyTorch from PyPI has no CUDA support. uv's --torch-backend auto, used above, picks the CUDA build that matches your driver. With pip, install it afterwards: pip install --force-reinstall --no-deps torch --index-url https://download.pytorch.org/whl/cu128.

If an NVIDIA GPU sits unused, sift says so on start-up and prints the command that fixes it.

Usage

sift add ~/papers --name papers        # register a folder as a collection
sift index                             # scan files, chunk them, build the keyword index
sift embed                             # embed every chunk that has no vector yet
sift search '"reward shaping"'         # exact keyword search
sift vsearch "how do robots plan brush strokes"
sift query "mixing pigments to match a target colour"
sift get papers/2401.02225.md          # full document
sift get papers/2401.02225.md --lines 14-23   # only some lines, e.g. those of a search hit
sift status                            # collections and counts
sift rm papers                         # remove a collection from the index; its files stay on disk
sift serve                             # MCP server on http://127.0.0.1:8765/mcp

sift index and sift embed are incremental: run them again after files change, and only new or changed files are processed. Deleted files are removed. An interrupted sift embed continues where it stopped. A running server picks up new vectors on its own.

Search commands accept -k (number of results), -c (collection), --path (glob within the collection, e.g. "2024/*"), -f KEY=VALUE (front-matter filter, repeatable), --fields (front-matter fields to show with each hit, e.g. url,created, or * for all), --compact (no text) and --json.

search requires every term. If no chunk has them all and the query has no operators (AND, OR, NOT, NEAR), it returns the chunks that have any of them, those with more terms first.

Front matter

YAML front matter with flat key: value lines becomes filterable metadata; lists can be inline or one - item per line. A list field matches when it contains the value:

---
title: "Brush stroke planning"
categories: ["cs.RO", "cs.GR"]
year: 2024
tags:
  - painting
  - robots
---

sift query "stroke order" -f categories=cs.RO -f year=2024

Filters can also be ranges, with >, >=, < and <=. Dates compare at the precision given, so created<=2024 includes all of 2024 and created>2024 starts in 2025; a number compares with the number a date starts with:

sift search pigment -f "created>=2024-06" -f "created<2025"

The title field, or else the first heading outside code blocks, or else the file name, becomes the document title.

MCP

The search tools take query, k, collection, path, filters, fields and compact. Every result carries id (collection/path), title, lines, score and the chunk text, so agents can cite their sources. fields adds front-matter fields to each result, e.g. ["url", "created"], and compact: true leaves out the text, so an agent can survey many results without filling its context and then read the ones that matter. Filters take values or ranges, e.g. {"created": {">=": "2024-06", "<": "2025"}}. The server tells agents when they connect which collections there are and which front-matter fields each has.

Claude Code

With the server running (sift serve), register it once for all your projects:

claude mcp add --scope user --transport http sift http://127.0.0.1:8765/mcp

Keep --scope user. Without it, claude mcp add registers sift for the current folder only, and sessions started anywhere else don't see it, including those in the Claude desktop app's Code tab. Start a new session afterwards: running sessions don't pick up new servers. One server serves any number of agents, with the models loaded once.

After upgrading sift, restart sift serve and start a new Claude Code session: a running session can keep an outdated list of sift's tools and their parameters, even after reconnecting.

Or let every Claude Code session start a server of its own over stdio. Then each session loads the models into memory itself:

claude mcp add --scope user sift -- sift serve --stdio

A registration made without --scope user can be removed in the folder where it was made, with claude mcp remove sift --scope local.

Connectors in claude.ai and in the Chat tab of the Claude apps can't use sift: claude.ai reaches connectors from Anthropic's servers, which can't reach a server on your computer.

Configuration

None needed: sift picks the device, the GPU memory budget, the batch size and the number of worker processes itself. Three optional settings exist for special cases:

After changing the embedding model, run sift embed --reset. Models are downloaded from Hugging Face on first use.

How it works

• Indexing: worker processes read and parse files in parallel while the previous batch is written; small updates skip the process start-up. Files are compared by modification time and size, then by content hash, so unchanged files cost nothing. Files are read as UTF-8, or as UTF-16 when they start with its byte order mark (Windows PowerShell 5.1 writes those). Markdown is split into chunks of about 3,000 characters (about 750 tokens) on line boundaries, preferring headings, with a small overlap.
• Storage: one SQLite database in WAL mode holds documents, chunks, metadata, an FTS5 keyword index and the vectors (fp16).
• Embedding: PyTorch in fp16 on the GPU (NVIDIA, else Apple), in batches sorted by length to keep padding low. Each slab of 20,000 chunks is committed, so progress is never lost.
• GPU memory: sift shares the GPU with other programs. On NVIDIA GPUs it caps itself at the memory that is free when it starts, minus headroom (10% of the GPU, at least 1 GB), asking NVML as well as CUDA, since on Windows CUDA counts memory held by other programs as free. It then measures how much memory its longest text needs at growing batch sizes and uses the largest batch that fills 90% of that budget; if a batch still doesn't fit, it is halved. With less than 2 GB to spare, sift uses the CPU instead.
• Idle GPU: models and vectors wait in RAM and move to the GPU when a search needs them. After 5 minutes without GPU use, sift serve moves them back to RAM and hands the memory back; only CUDA's own context (about 0.3 GB) stays. The first search afterwards takes about a second longer; if other programs have taken the memory meanwhile, sift stays on the CPU rather than squeeze them. Keyword search never uses the GPU.
• search: SQLite FTS5 with BM25, titles weighted double. Input that isn't valid FTS5 syntax is treated as exact phrases.
• vsearch: exact nearest-neighbour search as one matrix multiply over all vectors on the GPU. No approximate index, so nothing to tune and no recall loss; a million 1024-dimensional vectors take about 2 GB of VRAM.
• query: the top 40 (or k, if larger) keyword and semantic candidates are merged by reciprocal rank fusion and reranked in one GPU batch.
• Server: sift serve loads models and vectors once and keeps them in memory.

Scope

In scope: plain text and Markdown files; Linux, macOS and Windows; NVIDIA GPUs (CUDA) and Apple GPUs (MPS), otherwise CPU; one user, any number of local agents.

Out of scope for now: PDF, Word and HTML parsing (convert to Markdown first); answer generation (sift retrieves, the agent writes); approximate nearest-neighbour indexes; live file watching; remote access and authentication.

Development

git clone https://github.com/tobiaswuerth/sift
cd sift
uv venv && uv pip install --torch-backend auto -e ".[dev]"   # or with pip: pip install -r requirements.txt -e ".[dev]"
pre-commit install      # lint, format and config checks on every commit
pytest --cov            # 100% line and branch coverage is required

The tests replace the embedding and reranking models with small deterministic fakes, so they need no GPU and no model downloads; everything else, including the MCP server, runs for real. See CONTRIBUTING.md for how changes and releases work.

License

MIT