monkeSearch
monkesearch.github.io
- Free plan
- Windows
- macOS
- Linux
7.6 Club score Visit monkesearch.github.io
What the maker publishes
- Agent use
- The maker says the LLM-based implementation can serve as a natural-language file-discovery bridge for AI agents and orchestration systems. source
- Benchmark
- The maker's benchmark page says its query-parsing evaluation covers 80 queries across file type, temporal awareness, combined queries, and noise resistance. source
- Current platform status
- The repository describes the main branch as currently macOS-only and says cross-platform support is in the vectordb branch. source
- Data handling
- The maker says nothing leaves the machine; the Spotlight approach is read-only and uses Spotlight's access controls. source
- Integrations
- The main/dev approach uses macOS Spotlight and is described as a natural-language filesystem bridge for AI pipelines and agents. source
- License
- The repository lists the project under the Apache-2.0 license. source
- License and support
- The project is open source under the Apache-2.0 license, and its site asks users to support it by starring the repository. source
- Limitations
- The repository lists Spotlight-indexed files only, metadata-only search, possible small-model misunderstandings, and simple temporal expressions as limitations. source
- Limitations
- The repository says the main implementation searches Spotlight-indexed files, searches metadata rather than file contents, and supports only simple time expressions. source
- Local processing
- The maker says both approaches work fully offline and that nothing leaves the machine. source
- Local processing
- The project says both its LLM and vector database approaches run fully offline. source
- macOS approach
- The main/dev approach uses a local LLM to turn queries into macOS Spotlight search arguments. source
- macOS approach
- The main/dev branch uses a local LLM to turn queries into macOS Spotlight search arguments. source
- macOS integration
- The main/dev branch uses Spotlight’s existing index and the NSMetadataQuery API for file discovery. source
- Performance tradeoff
- On macOS, the maker says disabling LEANN recompute makes searches faster at the cost of disk space; recompute is enabled by default. source
- Platform architecture
- The maker describes vectordb support for macOS, Windows, and Linux; the repository says the main branch is currently macOS-only. source
- Product
- monkeSearch is an open-source, offline-first desktop tool for searching local files with natural-language queries. source
- Purpose
- monkeSearch is an offline-first desktop tool for searching local files with natural language. source
- Requirements
- The main branch requires macOS, Python 3.8 or later, llama-server, and a GGUF model; the stated default model is about 700 MB. source
- Requirements
- The repository lists macOS, Python 3.8+, llama-server from llama.cpp, and a GGUF model as requirements. source
- Search inputs
- The maker describes queries as combining file type, temporal context, and other keywords. source
- Search queries
- Queries can combine file type, temporal context, and other keywords. source
- Security
- The maker describes the Spotlight-based approach as read-only and scoped through Spotlight’s access controls. source
- Support
- The project page asks users who find the open-source project useful to star its GitHub repository. source
Checked against the maker's pages on 11 Oct 2026.