zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Integrates vector databases (Milvus, Zilliz Cloud) with multiple LLM providers (DeepSeek, OpenAI, Claude, Qwen, Grok) through a pluggable configuration system, enabling hybrid search combining vector retrieval with reasoning-based answer generation. Supports local document loading and web crawling to index private data, then executes multi-step queries that search, evaluate, and synthesize findings into comprehensive reports. Modular architecture allows swapping embedding models and LLM backends without code changes.
7,700 stars.
Stars
7,700
Forks
747
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/zilliztech/deep-searcher"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
giancarloerra/SocratiCode
Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP:...
lyonzin/knowledge-rag
Local RAG System for Claude Code - Hybrid search (Semantic + BM25) with MCP integration
blueraai/bluera-knowledge
Local knowledge search for AI coding agents. Index repos, docs, and files with semantic +...
kantord/SeaGOAT
local-first semantic code search engine
datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR
Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 9...