OpenRecall records your screen at regular intervals and makes that history searchable with local AI. It's a free, open-source alternative to Microsoft's Windows Recall and Rewind.ai for people who want to find something they previously saw on their computer. It runs on Windows, macOS and Linux, with a browser interface served from your own machine.
You can search captured content or scroll through earlier screenshots to revisit past activity. Local OCR extracts text from the captures, and semantic search helps you find relevant information in the recorded history. This gives you a way to look back across screen activity rather than relying on a particular app's history.
Processing stays on your device. OpenRecall works offline without a cloud service, and it stores both screenshots and its database locally. You control where that archive lives, including the option to keep it on an encrypted volume or removable disk. That encryption depends on the storage you choose, rather than an automatic encryption feature within the app.
Unlike Windows Recall, OpenRecall doesn't require Copilot+ certified hardware. It supports a broad range of computers across its three desktop platforms. It can capture multiple monitors or limit recording to the primary display.
The project uses Python and carries the GNU Affero General Public License v3.0 (AGPL-3.0), so its source code is available for inspection and modification under that license.
Claim this page and we'll verify you by hand. OpenRecall gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find OpenRecall?Promote it
Something wrong or outdated on this page?
18.3KUpdated 24 hours agoMIT
macOS · Windows · Linux · Docker · Web#Human approval#Hybrid search#llama.cpp backend
DocsGPT is an MIT-licensed, open-source platform for teams that want AI search, assistants and agents over their own documents. It can run on your servers with local models, including fully air-gapped deployments where documents and questions stay inside your network. Answers include the source title and page number so readers can check the evidence.
77KUpdated 3 months agoAGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multi-user access#RAG
982Updated 1 year ago
macOS · Windows · Linux · Docker#Home Assistant integration#Image-to-image#Multimodal input
68.2KUpdated 1 day agoMIT
macOS · Windows · Linux#MCP#Works offline
796Updated 2 weeks agoMIT
macOS · Windows · Linux#llama.cpp backend#LM Studio integration#Multilingual
9.1KUpdated 21 hours agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#MCP#Multi-user access
AppFlowy is a self-hosted Notion alternative for teams that want project management, shared documents, and AI in an environment they control. Its self-hosted enterprise offering can run on premises, in your own cloud, or in an air-gapped environment. Self-hosted LLMs and embedding models let you keep AI processing and workspace data inside your infrastructure, with no vendor access to your instance.
CodeProject.AI Server gives developers a shared API for AI tasks that run on their own hardware. It's a self-hosted service for adding image analysis, text processing and generation to applications. Processing stays on the machine running the server, without cloud calls or sending data outside your device or network.
Docling is an MIT-licensed, open source document parser for developers turning files into structured content for search and AI applications. It runs locally on macOS, Linux, and Windows, including in air-gapped environments. Its PDF processing identifies page layout and reading order, extracts tables, code, and formulas, and classifies images.
Interpreter reads Japanese text from game windows and displays English translations over your screen. It's built for people playing Japanese retro games, with MeikiOCR tuned for game text and pixel fonts. The default OCR and Sugoi V4 translation models run locally, so text stays on your computer and no internet connection is needed after setup. It's open source under the MIT license, with support for Windows, macOS and Linux.
Local Deep Research is a self-hosted AI research assistant for people who need cited answers drawn from academic papers, the web and their own documents. It can produce a quick summary or pursue a complex question through repeated searches, then assemble a structured report. It's open source under MIT.