Memory For AI

Created By

solonai-com18 days ago

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.

Overview Content Tools Comments

Overview

GrantAi

Infinite Memory for AI
Local. Private. Secure.

Website • Download • Pricing • Documentation

What is GrantAi?

GrantAi is the shared memory layer for AI agents.

Coordination frameworks are everywhere — CrewAI, AutoGen, LangGraph. But agents still lose everything when a session ends. Context windows reset. Knowledge evaporates. Each agent starts from zero.

GrantAi solves this:

Persistent Memory — Knowledge survives sessions, accumulates over time
Shared Across Agents — Multiple AI tools read and write to the same brain
12ms Recall — Sub-second retrieval regardless of memory size
100% Local — Your data never leaves your machine
AES-256 Encrypted — Secure at rest, zero data egress

Quick Start

macOS / Linux (Native)

# 1. Download from https://solonai.com/grantai/download
# 2. Extract and install
./install.sh YOUR_LICENSE_KEY

# 3. Restart your AI tool (Claude Code, Cursor, etc.)

Docker (All Platforms)

docker pull ghcr.io/solonai-com/grantai-memory:1.8.5

Add to your Claude Desktop config (~/.config/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "grantai": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--pull", "always",
               "-v", "grantai-data:/data",
               "-e", "GRANTAI_LICENSE_KEY=YOUR_KEY",
               "ghcr.io/solonai-com/grantai-memory:1.8.5"]
    }
  }
}

Supported Platforms

Platform	Method	Status
macOS (Apple Silicon)	Native	✅
Linux (x64)	Native	✅
Windows	Docker	✅
All Platforms	Docker	✅

MCP Tools

GrantAi provides these tools to your AI:

Tool	Description
`grantai_infer`	Query memory for relevant context
`grantai_teach`	Store content for future recall
`grantai_learn`	Import files or directories
`grantai_health`	Check server status
`grantai_summarize`	Store session summaries
`grantai_project`	Track project state
`grantai_snippet`	Store code patterns
`grantai_git`	Import git commit history
`grantai_capture`	Save conversation turns for continuity

Multiple agents can share knowledge through GrantAi's memory layer.

Basic shared memory (no setup required)

# Any agent stores
grantai_teach(
    content="API rate limit is 100 requests/minute.",
    source="api-notes"
)

# Any agent retrieves
grantai_infer(input="API rate limiting")

All agents read from and write to the same memory pool. No configuration needed.

With agent attribution (optional)

Use speaker to track which agent stored what, and from_agents to filter retrieval:

# Store with identity
grantai_teach(
    content="API uses Bearer token auth.",
    source="api-research",
    speaker="researcher"  # optional
)

# Retrieve from specific agent
grantai_infer(
    input="API authentication",
    from_agents=["researcher"]  # optional filter
)

When to use `speaker`

Scenario	Use speaker?	Why
Shared knowledge base	No	All contributions equal, no filtering needed
Session continuity	No	Same context, just persist and retrieve
Research → Code handoff	Yes	Coder filters for researcher's findings only
Role-based trust	Yes	Security agent's input treated differently

Framework integration

GrantAi works with any MCP-compatible client. Point your agents at the same GrantAi instance:

{
  "mcpServers": {
    "grantai": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--pull", "always",
               "-v", "grantai-data:/data",
               "-e", "GRANTAI_LICENSE_KEY=YOUR_KEY",
               "ghcr.io/solonai-com/grantai-memory:1.8.5"]
    }
  }
}

All agents using this config share the same memory volume (grantai-data).

Pricing

Free Trial — 30 days, no credit card required
Personal — $29/month or $299/year
Team — $25/seat/month

View full pricing →

Documentation

Support

Issues — Open an issue
Email — support@solonai.com

License

GrantAi is proprietary software. See Terms of Service.

Get Started →

Server Config

{
  "mcpServers": {
    "grantai": {
      "command": "grantai-mcp",
      "env": {
        "GRANTAI_LICENSE_KEY": "your-key-here"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

ChatWiseThe second fastest AI chatbot™

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

WindsurfThe new purpose-built IDE to harness magic

RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

DeepChatYour AI Partner on Desktop

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

Playwright McpPlaywright MCP server

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.