← Back

Features

Everything you need to give your local AI persistent memory.

Universal Import

ChatGPT, Claude, Gemini, or any JSON conversation export. Drag and drop. Auto-detected. Facts extracted automatically from thousands of conversations.

Real-Time Learning

Every conversation through the proxy is scanned for new facts. Quality scored against existing knowledge. Never stores fiction as fact.

Smart Retrieval

Semantic search across your entire memory graph. Only relevant facts injected into context. Not your entire history dumped into the window.

Multi-Provider

Ollama, OpenAI, Anthropic, Groq. Proxy works with any OpenAI-compatible provider. Switch anytime. Memory stays consistent.

Desktop App

Native window with 8 tabs: Facts, Review, Timeline, Insights, Status, Settings, Import, Mesh. No terminal required.

Privacy Native

Local-first. API keys encrypted at rest. Binds to 127.0.0.1 by default. Nothing phones home. No telemetry.

Agent Identity

Velqua detects which agent is calling. Blackreach, coder, planner — each gets its own identity and private memory.

Shared Memory

Agents write findings to a shared pool. Other agents read it. Coordination without a framework. No SDK required.

Real-Time Dashboard

Live WebSocket view of all active agents, their tasks, shared memory writes. Zero configuration.

How we compare

VelquaMem0ZepOpenMemory
Zero code changes
Local-first
Import ChatGPT & Claude
Multi-agent mesh
Desktop app
SetupPort changeAPI integrationSDK + DBDocker stack