Titan Memory

by henryhawke

59 stars
Not rated
GitHub

About

Integrates neural network-based memory encoding for enhanced long-term information storage and contextually-aware interactions across multiple conversations.

Details

Author
henryhawke
Repository
henryhawke/mcp-titan
GitHub stars
59
License
MIT License
Categories
Productivity, Developer Tools, Design, File Management, AI, Knowledge Base, Infrastructure, Frontend

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Titan Memory
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @henryhawke/mcp-titan

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

init_model

Initialize or reconfigure memory system.

bootstrap_memory

Quick-load context from text or URL.

get_memory_state

Inspect current memory contents.

memory_stats

Get statistical summary of the memory.

prune_memory

Clean up low-value memories.

forward_pass

Query memory and get prediction.

train_step

Explicit learning from example pair.

reset_gradients

Clear training state.

save_checkpoint

Save memory to file.

load_checkpoint

Restore memory from checkpoint.

init_learner

Start background learning service.

pause_learner

Pause the learning process.

resume_learner

Resume the learning process.

get_learner_stats

Monitor learning metrics.

add_training_sample

Feed training data.

get_token_flow_metrics

Perform sequence pattern analysis.

get_hierarchical_metrics

Analyze memory tier distribution.

health_check

Check system health and performance.

help

List all available tools with descriptions.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "titan memory": {
            "cwd": "/path/to/your/memory/storage",
            "env": {},
            "args": [
                "-y",
                "@henryhawke/mcp-titan"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "cwd": "/path/to/your/memory/storage",
    "env": [],
    "args": [
        "-y",
        "@henryhawke/mcp-titan"
    ],
    "command": "npx"
}

Macos

{
    "cwd": "/path/to/your/memory/storage",
    "env": [],
    "args": [
        "-y",
        "@henryhawke/mcp-titan"
    ],
    "command": "npx"
}

Windows

{
    "cwd": "/path/to/your/memory/storage",
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@henryhawke/mcp-titan"
    ],
    "command": "cmd"
}

TITAN Memory: AI That Remembers Like You Do

I've kind of given up on this as I don't have money to train it. Feel free to submit any sort of pull requests :)

Turn any AI into a learning companion that remembers across conversations

npm version
TypeScript
Node.js
License: MIT

---

What is MCP-TITAN??

Think about how you remember things:
- 💭 Short-term memory - What you heard 5 seconds ago
- 📝 Long-term memory - Important facts you recall later
- 🗄️ Deep storage - Things you "just know" from years ago

HOPE (Hierarchical Online Persistent Encoding) is the second generation of TITAN and gives AI this same ability. Instead of forgetting everything after each conversation, it builds up knowledge like a human brain.

The Problem HOPE Solves

```
❌ Standard AI (e.g., ChatGPT without plugins):

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.