Lancedb Python Packages

haiku-rag-slim

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

15K 624 53

hermes-scope-recall

Long-term memory for Hermes and Codex, with local storage, source-backed recall, and tools to inspect, correct, or delete remembered information.

15K 282 34

haiku-rag

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

14K 624 53

manicule

Self-hosted retrieval infrastructure for AI assistants. MCP-first search and grounded answers over a private corpus, with citations that resolve to a real location in a real document — a page, a heading, a line, a cell.

8K 0 0

basemind

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

4K 108 21

mempalace-code

Offline-first AI memory for coding — 29 MCP tools, temporal knowledge graph, and local vector search. No API keys, no cloud, no server.

3K 23 2

basemind-hermes-plugin

3K 108 21

nexus-mcp-ci

Unified MCP server: hybrid search + code graph + semantic memory. 10 tools, <350MB RAM, fully local. No API keys.

1K 0 0

java-codebase-rag

A rag + rag-graph native code intelligence layer for Java microservice estates, exposed to LLM agents via CLI

1K 9 1

transcendence-memory-server

Self-hosted multimodal RAG cloud memory service — a shared brain for your AI agents. Multi-agent cross-query, LanceDB + LightRAG + RAG-Anything.

1K 6 0

pmb-ai

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

1K 281 28

embex

High-performance infrastructure libraries built in Rust, with seamless bindings for Python, Node.js, and WebAssembly.

850 27 1

vector-inspector

The missing developer tool for working with vector databases. A comprehensive desktop app for visualizing, querying, and managing vector data.

600 6 0

firn

The cost efficiency of S3 with the speed of local RAM. A multi-tenant vector and full-text search engine featuring a tiered RAM -> NVMe -> S3 architecture for microsecond latency on top of object storage

588 477 26

context-lens

Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.

587 24 2

jrag-cli

A rag + rag-graph native code intelligence layer for Java microservice estates, exposed to LLM agents via CLI

561 9 1

yt-mem-ai

A local YouTube memory for your AI assistant — transcribe, remember, summarize. CLI + MCP server + agent skills.

542 7 0

bridgetime

High-performance infrastructure libraries built in Rust, with seamless bindings for Python, Node.js, and WebAssembly.

442 27 1

raggity

Local-first, top-tier RAG over your notes, docs & PDFs — answered by Claude (Agent SDK). Hybrid retrieval + cross-encoder rerank + verified citations; CPU-first & cross-vendor; CLI + FastAPI; LanceDB/Qdrant. AGPL-3.0.

440 0 0