Weekend project: point moss-cli at your own notes.
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ
Bring vectors from any embedding model. No account, nothing leaves your machine.
Things people search with a local index:
โ notes
โ product docs
โ support macros
โ research papers
pip install moss-cli. Bring your own embeddings, no account.
Private by default, in plain words: with no account, moss-cli keeps one index on your device, and it opens only for the user and device that created it.
pip install moss-cli
Start on your laptop. Move to the cloud when you want to.
๐บ๐ผ๐๐ ๐น๐ผ๐ด๐ถ๐ป
๐บ๐ผ๐๐ ๐ถ๐ป๐ฑ๐ฒ๐ ๐ฝ๐๐๐ต ๐ป๐ผ๐๐ฒ๐ --๐๐ฎ๐ถ๐
Your local index goes up to your project with its embeddings. Until then, no account needed.
Already have vectors? Add an "embedding" field to each doc, JSON or CSV, and index in one command.
๐บ๐ผ๐๐ ๐ถ๐ป๐ฑ๐ฒ๐ ๐ฐ๐ฟ๐ฒ๐ฎ๐๐ฒ ๐ป๐ผ๐๐ฒ๐ -๐ณ ๐ฑ๐ผ๐ฐ๐.๐ท๐๐ผ๐ป
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ. No account for bring-your-own-embeddings.
Hybrid search by default.
--alpha 0.8 out of the box. Slide to 0 for pure keyword, 1 for pure semantic. Tune it per query, on your own machine.
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ
Works where you work.
macOS on Apple silicon. Linux on x86 and Arm. Windows. Python 3.10 or newer.
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ
No account needed when you bring your own embeddings.
Searching private notes shouldn't mean uploading them.
With no account, moss-cli keeps one index on your device. Nothing from it leaves: no documents, no queries, no vectors.
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ
Bring your own embeddings. No sign-up required.
Semantic search on your laptop. No account.
๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น ๐บ๐ผ๐๐-๐ฐ๐น๐ถ
Bring vectors from the embedding model you already use, build a local index, and query it from your terminal. Your documents and queries stay on your machine.
Want Moss embedding models? That's when you sign up.
Want to ensure grounded responses with every LLM call automatically? Then check out Moss Inference and join the private beta today!
How to get into the Moss Inference private beta:
โ Request access for Moss Inference private beta for free, or contact Moss about paid plans after requesting access.
โ Share your personal invite link with others, each use to join the waitlist moves you higher up on the waitlist.
โ You'll earn credits if you're able to hit a certain amount of referrals.
โ In the meantime, you can also create a free Moss account and try Moss retrieval today!
Learn more and join the wait list: https://t.co/ZxOcyL6lHg
Thereโs a difference between OpenMOSS and Moss, and we wanted to clear up some of the confusion. Despite the similar names, theyโre two distinct projects with different teams, products, and goals.
We put together a quick breakdown of OpenMOSS vs. Moss, what each is building, and what you should know if you come across either.
Check it out: https://t.co/U8chLW0ZEL
60M+ conversational minutes have taught us a lot about what it takes to run AI in production.
One thing is clear: every millisecond matters when you're building agents that need to respond in real time.
Moss Inference brings optimized LLM inference closer to retrieval, running both on the same host with a target of sub-200ms inference latency.
We're inviting teams building real-time and long-horizon agents to try it.
Get private beta access โ https://t.co/fhzzxSZrVa
Last year I built at Cal Hacks. This year I came back to judge the @usemoss track.
Loved seeing Voice AI applied to air traffic control and emergency response, and how proactively teams asked for feedback.
Thanks to @srimalireddi and the @CalHacks team!