Anygrep

Anygrep is a command-line search tool that finds notes, PDFs and images by meaning locally.

Anygrep is a command-line tool designed to search through notes, text files, PDFs, and images based on meaning rather than exact text. It operates locally on the CPU by running the EmbeddingGemma 2 model and maintaining a local index. Users can run searches directly from the terminal, and the tool handles indexing new files automatically or via background processes. It supports various formats including markdown, text files, HTML, PDFs, and image formats like JPG and PNG. The software is intended for developers and power users who need semantic search capabilities across their local files without external cloud dependencies. Additionally, it can be integrated and used directly from Python projects.

Anygrep at a glance

Best for: Software engineer, Researcher
Runs on: Linux, macOS, Windows, CLI, API, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI search engine
Website: github.com/kuroko1t/anygrep

Key features

Search files by meaning from the terminal
Index text files, PDFs, and images locally
Support exact string matching alongside semantic search
Hide weak matches and deduplicate near-identical files
Index new files in the background during work
Use as a library directly from Python scripts

Use it for

Search personal notes and documents by conceptual meaning
Find specific images and PDFs using text queries
Query local documentation from the command line

Alternatives to Anygrep

Sgrep — Runs locally without accounts or hosted indexes using small CPU models.
AnySearch MCP — It delivers high accuracy, fast latency, and structured outputs for AI agents.
Orama — Runs in browsers, servers, and edge networks with zero dependencies.
DigUp — It searches local files by content and meaning without sending data to the cloud.
zvec-grep — Unifies ripgrep, BM25, and vector search behind one local-first interface.
Instant — Finds files using semantic descriptions without sending any data to the cloud.
PixelRAG — Preserves visual structure like tables and charts that text parsers miss.
Gsearch — Runs a real browser over MCP to fetch genuine Google results with zero API keys.
Jina — It provides reliable reader and search APIs optimized for LLMs and RAG systems.
Hister — Protects privacy with a self-hosted search index for your pages and files.
AnyCrawl — Provides clean, structured, and LLM-ready data from any website.
BGE Embeddings — Provides specialized models for high-performance information retrieval.

All Anygrep alternatives