hybrid-search repositories
Trending repositories tagged hybrid-search, ranked by trending score. Updated daily.
-
1
Marker-Inc-Korea/AutoRAG
Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.
GitHub · TypeScript · 6,094 stars · 524 forks · +79 stars in 24 hours · Trending score 3.74
-
2
meilisearch/meilisearch
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
GitHub · Rust · 59,948 stars · 2,796 forks · +52 stars in 24 hours · Trending score 3.20
-
3
qdrant/qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
GitHub · Rust · 35,651 stars · 2,833 forks · +19 stars in 24 hours · Trending score 2.80
-
4
paradedb/paradedb
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
GitHub · Rust · 9,550 stars · 520 forks · +10 stars in 24 hours · Trending score 2.25
-
5
taladb/taladb
TalaDB - An open-source embedded vector and document database for building local-first AI applications.
GitHub · Rust · 89 stars · 10 forks · +17 stars in 24 hours · Trending score 2.25
-
6
oceanbase/seekdb
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.
GitHub · C++ · 3,253 stars · 1,373 forks · +3 stars in 24 hours · Trending score 1.72
-
7
pipeshub-ai/pipeshub-ai
The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.
GitHub · Python · 4,138 stars · 684 forks · +2 stars in 24 hours · Trending score 1.72
-
8
zilliztech/memsearch
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
GitHub · Python · 2,900 stars · 291 forks · +1 stars in 24 hours · Trending score 1.52
-
9
punit2911/meridian-multimodal-rag
Evidence-grounded multimodal RAG for industrial maintenance documentation, with hybrid retrieval, citations, conflict resolution, claim verification and abstention. Includes an optional tool-using LLM agent and deterministic offline mode.
GitHub · Python · 71 stars · 0 forks · +17 stars in 24 hours · Trending score 1.40
-
10
weaviate/weaviate
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
GitHub · Go · 16,958 stars · 1,440 forks · +2 stars in 24 hours · Trending score 1.34
-
11
paradedb/django-paradedb
The official Django integration for ParadeDB
GitHub · Python · 76 stars · 5 forks · +4 stars in 24 hours · Trending score 1.24
-
12
infiniflow/infinity
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
GitHub · C++ · 4,770 stars · 460 forks · +2 stars in 24 hours · Trending score 1.12
-
13
xerj-org/xerj
AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
GitHub · Rust · 19,104 stars · 1,204 forks · −159 stars in 24 hours · Trending score 1.05
-
14
tom1030507/OpenNotebookLM
Self-hosted alternative to Google's NotebookLM: import PDFs, web pages and YouTube transcripts, then get answers with citations back to the source. Hybrid dense + BM25 retrieval over a local SQLite database, with Claude, any OpenAI-compatible provider, or a model on your own machine.
GitHub · Python · 128 stars · 21 forks · +3 stars in 24 hours · Trending score 1.00
-
15
caelum29/calibre-mcp
The most capable Calibre MCP server — full read/write tools plus multilingual semantic search over your whole ebook library or a single book. For Claude & any MCP client.
GitHub · TypeScript · 33 stars · 4 forks · +2 stars in 24 hours · Trending score 0.99
-
16
fstamatelopoulos/cerefox
Shared memory for your AI agents: what one agent learns, every other agent can find. Hybrid search, versioning and audit, over MCP, CLI and HTTP. Supabase or local Docker.
GitHub · TypeScript · 20 stars · 5 forks · +3 stars in 24 hours · Trending score 0.98
-
17
yoloshii/ClawMem
On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.
GitHub · TypeScript · 212 stars · 42 forks · +2 stars in 24 hours · Trending score 0.97
-
18
dingodb/dingo
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.
GitHub · Java · 1,706 stars · 263 forks · +3 stars in 24 hours · Trending score 0.90
-
19
alphasolutionsrepo/interakt
Open-source, self-hosted search and AI chat for your website, grounded in your own data
GitHub · TypeScript · 40 stars · 2 forks · 0 stars in 24 hours · Trending score 0.87
-
20
lixuanqun/fast-knowledge
面向中小企业的开源私有化知识库:单实例部署、数据本地可控、LLM 中立。LangChain4j RAG、PgVector 混合检索、Docker 一键部署。
GitHub · Java · 7 stars · 2 forks · +2 stars in 24 hours · Trending score 0.83
-
21
kurcontko/mnemotree
Memory module for LLMs and Agents with MCP
GitHub · Python · 8 stars · 0 forks · +2 stars in 24 hours · Trending score 0.83
-
22
nczz/pi-knowledge
Local-first RAG knowledge base for Pi agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing.
GitHub · TypeScript · 36 stars · 9 forks · +2 stars in 24 hours · Trending score 0.81
-
23
shekharmaheshwari/intelligent-search-platform
Self-hosted AI search + chat platform that keeps LLM costs low: hybrid (BM25 + vector) search, RAG product chat, and rule-based query understanding that skips the LLM when it isn't needed. Works with OpenAI, Claude, Gemini, Groq, Ollama, or LiteLLM. Built on Typesense + FastAPI.
GitHub · Python · 44 stars · 0 forks · 0 stars in 24 hours · Trending score 0.77
-
24
dolev31/lasagna
Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.
GitHub · Python · 37 stars · 14 forks · +1 stars in 24 hours · Trending score 0.72