Vibe Coding Discoverseekdb
View on GitHubThe 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.
MySQL-compatible embedded/server database unifying vector, full-text and relational data in one engine. Two-level HNSW hybrid search, async index pipeline for streaming writes, and FORK/MERGE copy-on-write sandboxes make it a state store for agent memory and RAG.
Use Cases
Persistent memory and state store for AI agentsRAG knowledge retrieval with vector + full-text + scalar filtersSemantic search over text and multimodal embeddingsCOW database forking for safe agent experimentation and rollbackSemantic code search for IDE plugins and code agentsEnterprise QA and customer support retrievalOn-device/embedded AI for edge and resource-constrained devicesDocument intelligence and business insight over legacy MySQL systems
Built With
- Language
- C++
- Frameworks
- LangChain · LlamaIndex · Dify · SQLAlchemy · OceanBase
Tags
vector-database · hybrid-search · rag · agent-memory · full-text-search · hnsw · mysql-compatible · embedded-database · copy-on-write · sql · semantic-search · acid · vector-index · state-store · sandbox · python-sdk