Skip to content
SPECIFICTION
Get listed

Precision File Search

pfs-ai.github.io

Free plan WindowsmacOSLinux
Visit pfs-ai.github.io
Spec score 7.6 #23 of 57 in Desktop Search Software

What it is

Precision File Search is a free desktop application for finding, classifying, and understanding local files on Windows, macOS, and Linux. It combines classic search with semantic search using a retrieval-augmented generation pipeline, and can answer natural-language questions with summarized responses. A trainable machine-learning model sorts scattered documents into categories users define. The maker says the application and AI models can operate locally, without cloud dependency, and that files, queries, and personal data are not sent to external servers. The project lists support for 18 languages, including English, Arabic, Chinese, French, German, Hindi, Japanese, and Spanish. An internet connection is needed on first run to download multilingual AI models; later runs can be offline. PFS supports OpenAI-compatible inference URLs, including online providers and local engines such as Ollama and LM Studio. The README lists 8 GB of RAM for the core platform and a dedicated GPU, with at least 4 GB of VRAM for smaller models, for local LLM use. The project is licensed under MPL-2.0.

Spec sheet

What it does
Precision File Search is a desktop application for searching, classifying, and understanding local files.Read 3 Oct 2026 · pfs-ai.github.io
Intended users
The project README names researchers, students, developers, legal and business professionals, writers, and people organizing large local document collections as intended users.Read 3 Oct 2026 · github.com
Security
The maker lists path-traversal prevention, XSS sanitization, and prompt-injection hardening as security measures.Read 3 Oct 2026 · pfs-ai.github.io
Privacy
The maker says PFS never uploads files or search queries and that personal data is not sent to external servers.Read 3 Oct 2026 · pfs-ai.github.io
License
The project README states that PFS is licensed under the Mozilla Public License 2.0 (MPL-2.0).Read 3 Oct 2026 · github.com
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.Read 3 Oct 2026 · github.com
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.Read 3 Oct 2026 · github.com
Business services
The README offers organizations custom feature development, enterprise integrations, priority support and maintenance, on-premise deployment consulting, and AI/RAG consulting.Read 3 Oct 2026 · github.com
Classification
Its trainable machine-learning model can classify scattered documents into user-tailored categories.Read 3 Oct 2026 · pfs-ai.github.io
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.Read 3 Oct 2026 · github.com
Languages
The site lists support for 18 languages, including English, Arabic, Chinese, French, German, Hindi, Japanese, and Spanish.Read 3 Oct 2026 · pfs-ai.github.io
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.Read 3 Oct 2026 · pfs-ai.github.io
Maintainer
The README says PFS was developed by Aran Kazemi and describes him as an IBM Certified AI Engineer.Read 3 Oct 2026 · github.com
Search modes
It combines high-speed classic search, semantic search using a RAG pipeline, and natural-language questions with summarized answers.Read 3 Oct 2026 · pfs-ai.github.io
Windows download
The project README directs users to download a Windows installer with an .exe extension.Read 3 Oct 2026 · github.com

Plans and prices

Free and open-source Free No paid tiers or usage limits stated on the opened pages Read 3 Oct 2026 · pfs-ai.github.io

Every Precision File Search plan and price →

Strong points and limits

Strong points

  • Available for Windows, macOS, and Linux
  • Searches classically and semantically, with summarized answers
  • Trainable model sorts files into tailored categories
  • Maker says files and queries stay off external servers

Limits

  • First run needs internet to download AI models
  • Local LLM use calls for a dedicated GPU
  • Core platform lists at least 8 GB of RAM

Who it suits

PFS suits researchers, students, developers, legal and business professionals, writers, and others organizing large local document collections. It is a fit for users seeking local file search and classification across Windows, macOS, or Linux.

Verdict

PFS combines local search, document classification, and question answering in one desktop app. Note the first-run download and hardware requirements, particularly if you plan to use local LLMs.

Where Specifiction places it

Alternatives to Precision File SearchAll alternatives →