Precision File Search
pfs-ai.github.io
- Free plan
- Windows
- macOS
- Linux
What Precision File Search is
Precision File Search is a free desktop application for searching, classifying and understanding files stored locally. It combines fast classic search with semantic search using a retrieval-augmented generation pipeline, and it can answer natural-language questions with summarized responses. A trainable machine-learning model can sort scattered documents into categories users define. The maker says the app and its AI models can run on the local machine without cloud dependency; it also says files, queries and personal data are not sent to external servers. PFS is available for Windows, macOS and Linux, and the project lists support for 18 languages. An internet connection is needed on first run to download multilingual AI models; later use can be offline. The project supports OpenAI-compatible inference URLs, including online providers and local engines such as Ollama and LM Studio. The README says the core platform runs on modern consumer hardware with at least 8 GB of RAM; local LLM use calls for a dedicated GPU, with at least 4 GB VRAM for smaller models. It is licensed under MPL-2.0.
Who it suits
PFS is intended for people managing local document collections, including researchers, students, developers, legal and business professionals, and writers. It suits users who want file search and classification on Windows, macOS or Linux.
Good to know, and what to watch
- Combines classic search, semantic search and natural-language questions.
- Trainable model sorts files into user-defined categories.
- Maker says files and queries stay off external servers.
- Supports 18 languages.
- First-run model download requires an internet connection.
- Local LLM use needs a dedicated GPU.
- The README lists at least 4 GB VRAM for smaller local models.
Plans
Every plan and priceFree and open-source
Free plan
The verdict
Precision File Search combines several ways to find and organize local documents, with offline use after the initial model download. Its local LLM option has a dedicated-GPU requirement.
What the maker publishes
- AI integrations
- The README says PFS supports OpenAI-compatible inference URLs, including online providers such as OpenAI and Together.ai and local engines such as Ollama and LM Studio. source
- AI model setup
- The release page says an internet connection is needed on first run to download multilingual AI models, after which subsequent runs can be fully offline. source
- Business services
- The README offers organizations custom feature development, enterprise integrations, priority support and maintenance, on-premise deployment consulting, and AI/RAG consulting. source
- Classification
- Its trainable machine-learning model can classify scattered documents into user-tailored categories. source
- Hardware requirements
- The README says the core platform runs on most modern consumer hardware with at least 8 GB of RAM; local LLM use is listed as needing a dedicated GPU, with at least 4 GB VRAM for smaller models. source
- Intended users
- The project README names researchers, students, developers, legal and business professionals, writers, and people organizing large local document collections as intended users. source
- Languages
- The site lists support for 18 languages, including English, Arabic, Chinese, French, German, Hindi, Japanese, and Spanish. source
- License
- The project README states that PFS is licensed under the Mozilla Public License 2.0 (MPL-2.0). source
- Local operation
- The maker says the application and AI models can run entirely on the local machine, and that it works offline without cloud dependency. source
- Maintainer
- The README says PFS was developed by Aran Kazemi and describes him as an IBM Certified AI Engineer. source
- Privacy
- The maker says PFS never uploads files or search queries and that personal data is not sent to external servers. source
- Search modes
- It combines high-speed classic search, semantic search using a RAG pipeline, and natural-language questions with summarized answers. source
- Security
- The maker lists path-traversal prevention, XSS sanitization, and prompt-injection hardening as security measures. source
- What it does
- Precision File Search is a desktop application for searching, classifying, and understanding local files. source
- Windows download
- The project README directs users to download a Windows installer with an .exe extension. source
Checked against the maker's pages on 3 Oct 2026.