moss
Moss delivers sub-10ms semantic search for conversational AI, voice agents, and copilots. Connect your data once — Moss indexes and distributes it wherever your agent runs: in-browser, on-device, or in the cloud.
moss at a Glance
- How you use it
- SDK
- Who it's for
- Teams building real-time AI systems, including voice AI and copilots
- Works with
- LiveKit Pipecat ElevenLabs LangChain DSPy Vercel AI SDK Next.js
moss Key Features
- in-process retrieval
- offline indexing
- on-device search
- real-time semantic search
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
moss Alternatives
Wax
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift - christopherkarani/Wax
xerj
A new way for AI to search for data: one local Rust binary that indexes your code, docs, specs and logs, plus Corpus Hub packs, and returns cited answers.
claude-view
10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent visibility. - tombelieber/claude-view
Exa AI
Search API for AI agents that need real-time web data, deep research, and structured content from one endpoint. Try our API for free.
Outcrawl
Outcrawl gives your AI agent the web: clean data from any page, search with the results already read, real browsers in the cloud, and agents that finish whole tasks. 1,000 free credits every month, no card.
UnifiedModel
The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph. - alibaba/UnifiedModel