makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It offers a compelling local alternative to Microsoft's Windows Recall, prioritizing privacy by keeping all data on-device and using open-source components like sqlite-vec and sentence-transformers for efficient vector search.
Who it is for
- Privacy-conscious Windows users
- Developers building local-first productivity tools
- Power users wanting semantic screen history search
- Researchers evaluating local RAG pipelines
Use cases
- Quickly retrieving past on-screen information via natural language queries
- Debugging or recalling steps in a workflow without manual note-taking
- Building a private, searchable memory of computer activity over time
- Exploring local retrieval-augmented generation (RAG) implementations
Strengths
- 100% local operation with no data leakage to cloud
- Fast sub-50ms KNN semantic search via sqlite-vec
- Deduplication using perceptual hashing to save storage
- Integrates with local LLM server (LM Studio) for conversational Q&A
Considerations
- Windows-only (requires WinRT OCR and ctypes hooks)
- Early prototype with APIs and schemas subject to change
- Depends on external LM Studio server and a local LLM model (e.g., Qwen 2.5-7B), which may require significant RAM
README quick start
Installation & Setup
Description
An early prototype alternative to Microsoft/Windows Recall, built to run 100% locally with zero cloud communication. Captures screen snapshots, extracts text via WinRT OCR, and indexes embeddings into SQLite. Query your history conversationally via your local LLM (LM Studio). Under active development.
Related repositories
Similar projects matched by category, topics, and programming language.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
l0ng-ai
Featured
tty7
tty7 is a fast, GPU-accelerated terminal workbench with persistent sessions, built-in input tools, SSH support, and coding agent awareness.