Joined February 2025
- Tweets 101
- Following 3
- Followers 545
- Likes 65
49 Photos and videos
Pinned Tweet
13 Nov 2025
Moss adoption is growing 200% MoM ๐
๐ 130 projects live
๐ฆ 300 indexes created
๐ข 50 companies are actively testing @usemoss
๐ฅ Strong inbound from voice AI & multimodal agent teams
If you are an agent developer, try our product at - usemoss.dev
1
9
5,114
Moss (YC F25) retweeted
Jun 12
Attended the conversational AI hackathon by @usemoss at @ycombinator last weekend โ built a voice agent that compares health insurance plans over a phone call. Good fun, great people! Love the vibe of SF โฅ๏ธ
2
4
135
Moss (YC F25) retweeted
May 29
Come build agents that can finally hold a fluid conversation at the 24-Hour Conversational AI Hackathon, hosted by @usemoss at the YC Office, June 6-7. First place wins an interview with a YC partner: events.ycombinator.com/conveโฆ
15
20
233
137,252
Apr 8
๐ญ๐ฌ๐ฌ๐๐ต ๐ฃ๐ฅ ๐บ๐ฒ๐ฟ๐ด๐ฒ๐ฑ ๐ถ๐ป ๐๐ต๐ฒ ๐ ๐ผ๐๐ ๐ฟ๐ฒ๐ฝ๐ผ.
What started as an idea is now being shaped by a growing community. Every bug fix, feature, and improvement brought us here.
Thank you to everyone who opened a PR, filed an issue, or left a review. You're building this with us.
The best is ahead.
#OpenSource #Moss #SemanticSearch #DevTools
2
8
851
Apr 7
๐ ๐ผ๐๐ ๐ฐ๐ฟ๐ผ๐๐๐ฒ๐ฑ ๐ญ๐ฌ๐ฌ๐ ๐ฝ๐ฎ๐ฐ๐ธ๐ฎ๐ด๐ฒ ๐ฑ๐ผ๐๐ป๐น๐ผ๐ฎ๐ฑ๐.
One bet: make semantic search fast enough that conversations flow at the speed of thought.
Your conversational AI agent deserves sub-10 ms retrieval.
With teams shipping Moss in production, our product did the talking.
#SemanticSearch #AIAgents #VoiceAI
2
3
441
Apr 2
๐๐๐ถ๐น๐ฑ๐ฒ๐ฟ๐ ๐ช๐ต๐ผ ๐ฆ๐ต๐ถ๐ฝ ๐ฉ๐ผ๐ถ๐ฐ๐ฒ is back.
Happy hour for Voice AI builders and founders in SF.
Agents, pipelines, real-time infra, if you're building on the voice stack, come through.
No panels. No pitch decks. Just good conversations with people actually shipping to production.
๐ San Francisco
๐
Thursday, 16th April ยท 5:30 โ 8:30 PM
โ RSVP: luma.com/l2fb0s4s
#VoiceAI #AIAgents #VoiceAgents #SFTech #Developers
1
240
Apr 1
๐ง๐๐ฝ๐ฒ ๐ฎ๐ ๐ณ๐ฎ๐๐ ๐ฎ๐ ๐๐ผ๐ ๐ฐ๐ฎ๐ป. ๐ช๐ฒ'๐น๐น ๐ธ๐ฒ๐ฒ๐ฝ ๐๐ฝ.
We just shipped Moss semantic search plugin for VitePress docs.
Runs entirely in the browser. Sub-10ms.
Your user can type "how do I authenticate?" and gets the right answer, even if no page contains those exact words.
Nothing sits between the keystroke and the answer.
One plugin. Five minutes to set up.
Try Demo: vitepress-docs.moss.dev/
1
1
6
255
Apr 1
๐ ๐ผ๐๐ ๐ถ๐ ๐ผ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฎ๐น๐น๐ ๐ฆ๐ข๐๐ฎ ๐ฐ๐ผ๐บ๐ฝ๐น๐ถ๐ฎ๐ป๐
Shipping agents to enterprise usually means months of security reviews and compliance headaches. We handled the heavy lifting so you don't have to.
Start building for enterprise with Moss's real-time retrieval engine.
Quick Start โ docs.moss.dev/docs/start/quiโฆ
#AI #Enterprise #YC #Developers #SOC2
4
255
Mar 31
๐ช๐ฒ ๐๐ต๐ถ๐ฝ๐ฝ๐ฒ๐ฑ ๐ฎ ๐๐ผ๐ถ๐ฐ๐ฒ ๐ฎ๐ด๐ฒ๐ป๐ ๐ผ๐ป ๐ผ๐๐ฟ ๐ต๐ผ๐บ๐ฒ๐ฝ๐ฎ๐ด๐ฒ.
because the best way to explain sub-10ms retrieval is to let you talk to it.
Ask it anything about Moss. It pulls from our docs. You'll hear the difference.
Every other retrieval layer adds latency you can feel in a conversation. Ours doesn't.
moss.dev โ Start Conversation โ see for yourself.
#VoiceAI #SemanticSearch #YCombinator #DevTools #AIInfra
1
2
141
Mar 31
Ever tried search that works the moment you upload a doc ?
We built exactly that with @usemoss and @llama_index
Upload a PDF. Tables, columns, layout, all preserved. Search it seconds later Locally. No database, no external services.
Just sub-10ms retrieval with the exact page and source.
Built on Moss. Local first. Fast by default.
Try it โ llamaparse.moss.dev/
227
Mar 30
๐ถ๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ฑ๐ด๐ฒ-๐บ๐ผ๐๐ ๐ฃ๐๐๐ต๐ผ๐ป ๐ฆ๐๐ ๐๐ญ.๐ฌ.๐ฌ๐ฏ๐ญ๐ต ๐ถ๐ ๐น๐ถ๐๐ฒ
โ comes with full python 3.14 support.
โ embedding generation is faster now. should make a noticeable difference in your pipelines.
โ we started collecting query-level analytics. how many queries ran locally, how many went through moss cloud. all to give you better insights.
Sneak Peek: Portal dashboards that bring all your analytics to the surface coming soon!
1
101
Mar 28
๐ฉ๐ผ๐ถ๐ฐ๐ฒ ๐ฎ๐ด๐ฒ๐ป๐๐ ๐ณ๐ฒ๐ฒ๐น ๐ฏ๐ฟ๐ผ๐ธ๐ฒ๐ป ๐๐ต๐ฒ๐ป ๐ฟ๐ฒ๐๐ฟ๐ถ๐ฒ๐๐ฎ๐น ๐ถ๐ ๐๐น๐ผ๐.
So we built an open-source app that shows what happens when search is fast and the stack is yours to choose.
Moss handles semantic retrieval in 10 ms, local, no external calls. The rest of the pipeline? Mix and match.
In this build:
โ @hume_ai forย TTS - expressive, natural voice output
โ @ollama for the local LLM
โ @DeepgramAI for STT
โ @pipecat_ai for orchestration
Your agent, your stack. Moss fits in.
Clone it. Try it. Build something fast.
1
119
Mar 27
๐๐ฟ๐ฒ๐ฎ๐ ๐๐๐ฟ๐ป๐ผ๐๐ ๐ฎ๐ ๐๐ช๐ฆ ๐๐ผ๐ณ๐ ๐ฆ๐ ๐น๐ฎ๐๐ ๐ฒ๐๐ฒ๐ป๐ถ๐ป๐ด.
@srimalireddi took the stage to talk Real-Time Voice AI in production.
Sharp questions. Lots of post-talk conversations with engineers building in the voice and real-time AI space.
The problems people are running into are exactly what we're solving at Moss.
Great talks from @titus_k from @civickey on adding guardrails to autonomous AI agents, and @PeterCorless from @redpandadata on the convergence of real-time data and AI.
Big thanks to @aicampai for organizing and @awscloud for hosting the event.
If you're building voice or real-time AI and want to connect, follow along. We're just getting started!
#VoiceAI #RealtimeAI #AIAgents #GenAI #LLMs #SanFrancisco #AIInfrastructure
4
5
352
Mar 26
๐ ๐ผ๐๐ ๐ป๐ผ๐ ๐๐ฝ๐ฒ๐ฎ๐ธ๐ ๐ ๐๐ฃ
moss-tools/mcp-server gives any MCP client sub-10ms semantic search as a native tool.
โ tools: create, load, query, manage indexes, all from your agent
โ Local-first querying.
Same API. Same speed. Now inside your agent's MCP toolchain.
#MCP #SemanticSearch #AIAgents #DevTools #VoiceAI
1
167