Grantai

Name: Grantai
Author: solonai-com

@solonai-com

About Grantai

Fast, sub millisecond, local on device long term memory for LLMs, Coding Tools and AI Agents. Recall exact details from yesterday of five years ago. Install in 5 minutes.

#long-term-memory-continued-context-agentic-collaboration-secure-local-memory

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "grantai": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GRANTAI_LICENSE_KEY",
        "ghcr.io/solonai-com/grantai-memory:1.8.7"
      ],
      "env": {
        "GRANTAI_LICENSE_KEY": "<YOUR_LICENSE_KEY>"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is GrantAi?

GrantAi is a shared memory layer for AI agents that provides persistent, local, and encrypted memory. It solves the problem of agents losing context when sessions end by allowing knowledge to survive across sessions and be shared among multiple AI tools. It is designed for developers using coordination frameworks like CrewAI, AutoGen, or LangGraph.

How to use GrantAi?

Install GrantAi via native macOS/Linux (run ./install.sh YOUR_LICENSE_KEY) or Docker for all platforms. Add it as an MCP server to your Claude Desktop config or any MCP-compatible client. GrantAi exposes tools such as grantai_teach, grantai_infer, grantai_learn, and others for storing and querying memory.

Key features of GrantAi

Persistent memory that survives sessions and accumulates over time
Shared across multiple AI agents with no configuration needed
Sub-12ms recall regardless of memory size
100% local — data never leaves your machine
AES-256 encrypted at rest with zero data egress
MCP tools for storing, querying, and importing memory

Use cases of GrantAi

Maintain continuous context for a single AI agent across multiple sessions
Enable multiple agents (e.g., researcher and coder) to share a common knowledge base
Hand off information between agents with optional speaker attribution for role‑based retrieval
Import large codebases or git history for agent‑assisted development

FAQ from GrantAi

What makes GrantAi different from other memory solutions?

GrantAi offers persistent memory shared across agents, sub‑second recall, 100% local storage, and AES‑256 encryption. It works with any MCP‑compatible client and requires no external services.

How do multiple agents share memory with GrantAi?

All agents that point to the same GrantAi instance automatically read from and write to the same memory pool. Optionally, use the speaker parameter to attribute stored content and from_agents to filter retrieval.

Is my data secure with GrantAi?

Yes. GrantAi runs 100% locally, encrypts all data at rest with AES‑256, and guarantees zero data egress from your machine.

What are the system requirements for GrantAi?

Native support for macOS (Apple Silicon) and Linux (x64). All platforms are supported via Docker.

How much does GrantAi cost?

GrantAi offers a 30‑day free trial with no credit card required. Paid plans start at $29/month or $299/year for Personal, and $25/seat/month for Team.