AI for systematic literature review — search 125 million papers, extract data into tables, and screen at scale.
Semantic Search
Retrieval by meaning rather than exact wording, using embeddings to rank results.
13 apps, 5 skills and 12 MCP servers tagged Semantic Search.
Apps
Local-first AI memory for your media: index terabytes of video, audio and documents on your own machine and search them in plain language.
Turn a Postgres database into working memory for AI agents — relational rows, graph traversal and vector search fused into one ranked, token-budgeted context block.
Enterprise Work AI platform — permission-aware search across every company app, plus an assistant and agents that act on the results.
A search engine built for AI — embeddings-based retrieval that finds pages by meaning, not keyword overlap.
An open-source AI-native database combining vector search, structured filtering, and built-in model integrations.
The embedding database that starts as a Python import and grows into a distributed cloud service.
An open-source vector search engine written in Rust — fast, memory-efficient, and self-hostable.
A fully managed vector database for semantic search and retrieval at billion-scale, with no infrastructure to run.
An AI email client for Gmail that searches, drafts, organises, and schedules from a single prompt.
Pieces (formerly Pieces for Developers) is a desktop app that records your work on-device and makes it searchable for you and your AI tools.
AI notes workspace whose agent tracks tasks from your notes and meetings, with voice capture and an MCP connector for Claude and ChatGPT.
Consensus responsibly uses AI to help you conduct research faster
Skills
Persistent cross-session memory for coding agents: hooks capture each session, a local SQLite + vector store compresses it, and a mem-search skill reads it back.
Skill: Sentence Transformers Trainer
by Hugging Face
Train bi-encoders, rerankers, SPLADE sparse encoders and ColBERT multi-vector models with the loss, evaluator and template each type actually needs.
Skill: Weaviate Database Operations
by Weaviate
Weaviate's official skill for searching and managing vector collections — hybrid, semantic and keyword search, schema inspection, filtered fetches and bulk imports.
Skill: VideoDB
by VideoDB
VideoDB's official skill giving an agent one interface to ingest, index, search and edit video — including live RTSP feeds and real-time desktop capture.
Skill: NVIDIA VSS Video Q&A
by NVIDIA
NVIDIA's official skill for asking a vision-language model fresh questions about recorded video through the Video Search and Summarization blueprint — only when the pixels actually need looking at.
MCP servers
Attio's official hosted MCP server — search, read and write your CRM records, lists, notes, tasks, meetings and emails from any MCP client over OAuth.
Tiger Data's hosted MCP server and skills for PostgreSQL: version-aware semantic search over the Postgres, TimescaleDB and PostGIS manuals.
Zilliz's MCP server for semantic code search: it indexes a whole repository into Milvus or Zilliz Cloud and hands coding agents only the relevant chunks.
Connect a Zotero research library to Claude, ChatGPT and other agents — search by meaning, read PDFs by page, add papers by DOI, and place highlights and notes on the exact words.
MCP: Docs MCP Server
by arabold
Self-hosted documentation retrieval for coding agents — index any library's docs from the web, GitHub, npm, PyPI or local files and query them by exact version. An open-source Context7 alternative.
MCP: Coveo Hosted MCP Server
by Coveo
Coveo's managed MCP server exposing enterprise search, fetch, passage retrieval and grounded generative answering over your indexed content.
MCP: Sourcegraph
by Sourcegraph
Sourcegraph's MCP server — cross-repository keyword and semantic code search, go-to-definition, find-references, commit and diff search, and Deep Search, served from your own instance.
MCP: Patent & Literature Search
by Patsnap
Patsnap's MCP server for searching global patents across WIPO, EPO, USPTO, CNIPA, JPO and KIPO alongside scientific literature, returning records as AI-readable Markdown.
MCP: Compartment
by Max Freedom Pollard
Encrypted, fully offline agent memory: one local vault shared by every agent on the machine, AEAD-encrypted down to the embedding vectors, searched in about 12 ms.
MCP: Codanna
by Codanna
Local code intelligence MCP server that returns symbol context, call graphs and impact analysis in a single call — 15 languages, indexed on your own machine.
MCP: Qdrant
by Qdrant
Qdrant's official MCP server — semantic memory for AI assistants backed by a real vector database.
MCP: Exa Search
by Exa
Real-time web search and crawling built for AI — neural search with configurable tools and live content retrieval.
Related tags
Tags that appear alongside this one, ranked by how often.