←
Moss (YC F25)163 posts
Moss (YC F25) avatar✓

Moss (YC F25) ✓

@usemoss

The retrieval layer for production AI. Sub-10ms search for voice agents, copilots, and real-time AI.

◷ Joined February 2025▧ 71 Photos and videos
Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 14

𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 That's the post.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 14

Weekend project: point moss-cli at your own notes. 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 Bring vectors from any embedding model. No account, nothing leaves your machine.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 13

Things people search with a local index: → notes → product docs → support macros → research papers pip install moss-cli. Bring your own embeddings, no account.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 13

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

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 12

3/3 Query it on your machine. moss query notes "billing" --embedding q.json That's it. Your documents and queries stay on your device.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 12

2/3 Build an index from a JSON file where each doc has its text and vector. moss index create notes -f docs.json

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 12

1/3 moss-cli in 60 seconds. pip install moss-cli No account if you bring your own embeddings.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 12

Start on your laptop. Move to the cloud when you want to. 𝗺𝗼𝘀𝘀 𝗹𝗼𝗴𝗶𝗻 𝗺𝗼𝘀𝘀 𝗶𝗻𝗱𝗲𝘅 𝗽𝘂𝘀𝗵 𝗻𝗼𝘁𝗲𝘀 --𝘄𝗮𝗶𝘁 Your local index goes up to your project with its embeddings. Until then, no account needed.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 11

Already have vectors? Add an "embedding" field to each doc, JSON or CSV, and index in one command. 𝗺𝗼𝘀𝘀 𝗶𝗻𝗱𝗲𝘅 𝗰𝗿𝗲𝗮𝘁𝗲 𝗻𝗼𝘁𝗲𝘀 -𝗳 𝗱𝗼𝗰𝘀.𝗷𝘀𝗼𝗻 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶. No account for bring-your-own-embeddings.

Post attachment
Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 11

Filter on metadata without leaving your laptop. moss query notes "shoes" --filter '{"field": "category", "condition": {"$eq": "footwear"}}' 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 10

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. 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶

Post attachment
Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 9

Works where you work. macOS on Apple silicon. Linux on x86 and Arm. Windows. Python 3.10 or newer. 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 No account needed when you bring your own embeddings.

Post attachment
Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 9

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. 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 Bring your own embeddings. No sign-up required.

Moss (YC F25) avatar
Moss (YC F25)@usemoss·Nov 9

Semantic search on your laptop. No account. 𝗽𝗶𝗽 𝗶𝗻𝘀𝘁𝗮𝗹𝗹 𝗺𝗼𝘀𝘀-𝗰𝗹𝗶 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.

Post attachment