lingxinmind

Vecmindb SDK — AI skill for Claude Code

AI community

Self-hosted, sovereign memory layer for AI coding agents.

How to install Vecmindb SDK

This entry records only its repository, not the path inside it, so there is no exact command to give. Open lingxinmind/vecmindb-sdk and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Vecmindb SDK does

Self-hosted, sovereign memory layer for AI coding agents. MCP-ready, local BGE-M3 ONNX embeddings, zero external API. pip/npm/cargo install vecmindb.

Alternatives in AI

Azure OpenAI .net — GPT-4, embeddings, DALL-E, and Whisper client 1.8k ★
Pilotfish — Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verificati 688 ★
Claudish CLI — for external AI models) 679 ★

README

VecminDB SDK

The self-hosted memory layer for your AI coding agents. Give Cursor, Claude Code, and friends a shared, long-term memory that runs entirely on your machine — no external embedding API, no data leaving your network.

`pip install vecmindb` · `npm install vecmindb` · Docker one-liner

Free tier: 5 agents / 100K vectors. · [lingxinmind.com](https://lingxinmind.com)

⚠️ **License & Boundary Note**:

SDK (This Repository): The client libraries (Python & TypeScript) hosted in this repository are open-source under the MIT License. We welcome community contributions, integrations, and pull requests!
VecminDB Server (Pre-compiled Binaries & Docker): The core database server is proprietary commercial software protected by copyright, patent, and trade secret laws, governed by the VecminDB Proprietary Software License Agreement. The Free Tier supports up to 5 agents and 100K vectors/agent. For enterprise scale-out or clusters, please visit our official website to register and obtain a commercial license: https://lingxinmind.com.

Deployment & Installation

VecminDB can be run via Docker or as optimized, standalone pre-compiled native binary packages. No local compilers, dependencies, or Python runtimes are needed.

Method A: Docker Deployment (All Platforms - Windows, macOS, Linux)

The fastest way to spin up VecminDB with automatic in-database bilingual embedding support and zero-downtime rolling update capabilities.

Option 1: One-Line Docker Compose (Recommended for Production & Hot Updates)

# 1. Download production docker-compose.yml in one command
curl -sSL https://raw.githubusercontent.com/lingxinmind/vecmindb-sdk/main/docker-compose.yml -o docker-compose.yml

# 2. Spin up production container
docker compose up -d

# 3. Daily Online Hot Upgrade:
# docker compose pull && docker compose up -d