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.

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.

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.

Moss Inference beta is live. Join the waitlist here: moss.dev/product/infere…

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:
→ Request access for Moss Inference private beta for free, or contact Moss about paid plans after requesting access.
→ Share your personal invite link with others, each use to join the waitlist moves you higher up on the waitlist.
→ You'll earn credits if you're able to hit a certain amount of referrals.
→ In the meantime, you can also create a free Moss account and try Moss retrieval today!

Learn more and join the wait list: moss.dev/product/infere…

There’s a difference between OpenMOSS and Moss, and we wanted to clear up some of the confusion. Despite the similar names, they’re two distinct projects with different teams, products, and goals.

We put together a quick breakdown of OpenMOSS vs. Moss, what each is building, and you come across either.

Check it out: moss.dev/blog/openmoss-…

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 ith 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 → moss.dev/product/infere…

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!

Where you run AI matters.

Running everything in the cloud isn't always the best option. Latency, cost, and privacy all come into play, especially when you're building AI products for real users.

We break down the trade-offs between running AI in the cloud, at the edge, on devices, and in the browser, and what to consider when choosing the right setup.

moss.dev/blog/run-ai-wh…

went to the largest collegiate hackathon in the world (Cal Hacks 13) and won a record-breaking 6 prizes

my awesome team: @brendangiang, David Wu, and @IImzihao!!

thank you to @AnthropicAI, @Microsoft, @CalHacks, @usemoss, @apify, and @convex for the recognition :)

An AI agent can have the right context and still feel slow.

Retrieval gets the information to your agent. Inference determines how quickly it can start responding.

With Moss Inference, we're bringing optimized LLM inference and retrieval together on the same host, targeting ency.

We're opening the private beta to teams pushing the limits of real-time AI.

Request access → moss.dev/product/infere…

AI infrastructure costs go beyond your cloud bill.

Every service adds latency, complexity, and another thing to maintain.

We break down the hidden costs of AI infrastructure and what to consider when building for production.

moss.dev/blog/the-hidde…

We’ve brought retrieval closer to the agent. Now we’re tackling the next bottleneck: inference.

Moss Inference runs alongside retrieval on the same host, delivering sub-200ms inference latency for production AI agents.

We’re opening up private beta access for teams building zon agents.

Request access → moss.dev/product/infere…

Your model shouldn't need a tool loop you wrote yourself. ↓

Pass an MCP server in tools and Moss calls its tools during the reply.

Each step comes back as tool step. Every field the model sends on a tool call is kept, so replies go back into messages unchanged. ↓

Retries are on by default: 2 attempts for connection failures and 408, 409, 429, 5xx responses before a stream starts.

Indexes also load up to eight at a time now, so many content can feed from various indexed data sources.

Check the full changelog docs.moss.dev/docs/changelog

Your chat model shouldn't have to guess what's in your docs.

MossInference answers chat completions with facts from your Moss indexes. It ships in the Python, JavaScript, Browser, Swift, Elixir, Android and C SDKs. ↓

Same call shape as OpenAI's chat completions, plus indexes and retrieve.
Stream the reply, or get one completion back.

Bring your own OpenAI, Anthropic or Google key for vendor models like gpt-4o-mini. Or use model "moss" and skip the key.

Most agentic apps run retrieval as a separate step before the model sees anything.

Moss Inference folds search into the chat call.
User query → automatically search Moss index in milliseconds → search results enrich the prompt → model responds

Faster time to a response, no tool calls needed, and fewer tokens used. Same OpenAI request shape. Change the base URL and the key, and your existing client works.

Follow @usemoss to learn more about our upcoming beta.
See the full endpoint details here: docs.moss.dev/docs/api-refer…

80% of Moss customers use @livekit. 👀

LiveKit handles real-time voice. Moss handles the retrieval.

Together, your agent gets the context it needs on every turn, automatically.

No tool call. No extra roundtrip. No dead air.

Sub-10ms retrieval for voice AI.

→ moss.dev/integrations/l…