Behavioral Identity Models
Serves portable behavioral identity models via MCP. Extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keyword search, and provenance tracing through 4 tools a
What is Behavioral Identity Models?
Behavioral Identity Models is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to serves portable behavioral identity models via mcp. extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keywor...
Serves portable behavioral identity models via MCP. Extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keyword search, and provenance tracing through 4 tools a
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Serves portable behavioral identity models via MCP. Extracts
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx baselayerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Behavioral Identity Models
BaseLayer builds a portable behavioral identity model from your conversation history — chat exports from ChatGPT, Claude, or journals — and serves it over MCP so any AI assistant can access a persistent, semantically searchable understanding of how you think, communicate, and make decisions. The pipeline extracts facts and episodes using the Anthropic API, embeds them into a local ChromaDB vector store, then exposes four primary tools: get_brief for a unified narrative, recall_memories for semantic search, search_facts for keyword lookup, and trace_claim for provenance tracing. This gives agents always-on identity context without re-uploading your data each session.
Prerequisites
- Python 3.10 or higher installed
- An Anthropic API key from console.anthropic.com (required for extraction and composition steps)
- A conversation export file (ChatGPT export zip, Claude export, or markdown notes)
- An MCP-compatible client (Claude Desktop, Claude Code, or Cursor)
- git installed to clone from GitHub (not yet on PyPI)
Install BaseLayer from GitHub
BaseLayer is not on PyPI yet. Install directly from the GitHub repository using pip's git support.
pip install git+https://github.com/agulaya24/BaseLayer.gitSet your Anthropic API key
Export your Anthropic API key as an environment variable. BaseLayer uses Claude models during the extraction, embedding, and composition phases of the pipeline.
export ANTHROPIC_API_KEY=sk-ant-your-key-hereRun the full pipeline on your conversation export
Point the pipeline at your exported conversation file. For a ChatGPT export, pass the zip file directly. Processing ~1,000 conversations takes about 30 minutes and costs roughly $0.50–$2.00 in API credits.
baselayer run chatgpt-export.zipRegister the MCP server with your client
Once the identity model is built, register the BaseLayer MCP server so your AI client can query it. For Claude Code or Claude Desktop, use the mcp add command.
claude mcp add --transport stdio base-layer -- baselayer-mcpVerify the tools are available
Restart your MCP client. The tools get_brief, recall_memories, search_facts, and trace_claim should now appear. Ask your assistant for a brief to confirm the identity model loaded correctly.
Behavioral Identity Models Examples
Client configuration
Claude Desktop configuration block for BaseLayer MCP server running over stdio with the Anthropic API key.
{
"mcpServers": {
"base-layer": {
"command": "baselayer-mcp",
"args": [],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-your-key-here"
}
}
}
}Prompts to try
Example prompts that use the identity model tools to give agents persistent context about the user.
- "Give me a brief overview of how I think and communicate based on my identity model"
- "What do I tend to prioritize when making technical decisions?"
- "Search my memories for anything related to how I handled the product launch last year"
- "Find facts about my communication style preferences"
- "Trace where the claim about my leadership approach comes from in my original conversations"Troubleshooting Behavioral Identity Models
baselayer command not found after installation
The pip install may have placed the binary in a location not on your PATH. Try running `python -m baselayer` instead, or check ~/.local/bin and add it to your PATH.
Pipeline fails with Anthropic API errors during extraction
Verify ANTHROPIC_API_KEY is exported correctly and the key has sufficient credits. For large exports, the extraction step can consume several dollars in API calls — run `baselayer estimate` before `baselayer extract` to preview the cost.
recall_memories returns empty results
The ChromaDB vector store must be built before the MCP server can serve results. Ensure you ran the full pipeline (baselayer extract && baselayer embed) before starting baselayer-mcp. Re-run the pipeline if the database was deleted.
Frequently Asked Questions about Behavioral Identity Models
What is Behavioral Identity Models?
Behavioral Identity Models is a Model Context Protocol (MCP) server that serves portable behavioral identity models via mcp. extracts how a person thinks, communicates, and makes decisions from text, then provides always-on identity context, semantic fact retrieval, keyword search, and provenance tracing through 4 tools a It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Behavioral Identity Models?
Follow the installation instructions on the Behavioral Identity Models GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Behavioral Identity Models?
Behavioral Identity Models works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Behavioral Identity Models free to use?
Yes, Behavioral Identity Models is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Behavioral Identity Models Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Behavioral Identity Models? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Behavioral Identity Models in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Behavioral Identity Models?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.