personal-model
starsforks
How to install personal-model?
intuition-lab/personal-model
$git clone https://github.com/Intuition-Lab/personal-modelREADME.md
| 1 | # Persome: Build your Personal Model |
| 2 | |
| 3 | <p align="center"> |
| 4 | <a href="https://github.com/Intuition-Lab/personal-model/releases/download/v0.3.2/demo.mp4"><strong>▶ Watch the Personal Model demo</strong></a> |
| 5 | </p> |
| 6 | |
| 7 | <!-- mcp-name: io.github.Intuition-Lab/personal-model --> |
| 8 | |
| 9 | **The open-source Personal Model that makes every AI yours.** |
| 10 | |
| 11 | Persome learns how you actually think and work from focused activity captured on your Mac after you grant macOS permission—then gives Codex, Claude Code, and other trusted MCP-compatible clients evidence-linked context to continue your work and make grounded decisions. |
| 12 | |
| 13 | **Runs locally on your Mac. Private by default. Yours to inspect, correct, export, and delete.** |
| 14 | |
| 15 | [](https://github.com/Intuition-Lab/personal-model/actions/workflows/ci.yml) [](https://github.com/Intuition-Lab/personal-model/releases) [](LICENSE) [](#2-install-with-your-data) [](MCP.md) [](https://registry.modelcontextprotocol.io/?q=Persome) |
| 16 | |
| 17 | [Try the synthetic demo](#1-five-minute-synthetic-demo) · [Install with your data](#2-install-with-your-data) · [Connect an MCP client](#3-connect-a-trusted-mcp-client) · [Star Persome on GitHub](https://github.com/Intuition-Lab/personal-model) |
| 18 | |
| 19 |  |
| 20 | |
| 21 | _Concept illustration of a mature Personal Model. The deterministic Runtime proof is shown in the demo below._ |
| 22 | |
| 23 | --- |
| 24 | |
| 25 | ## What is it? |
| 26 | |
| 27 | Your `HUMAN.md` |
| 28 | |
| 29 | Persome connects activity into progressively deeper context: |
| 30 | |
| 31 | | Layer | Meaning | |
| 32 | | --- | --- | |
| 33 | | **Point** | A sourced observation or event | |
| 34 | | **Line** | A relationship or change over time | |
| 35 | | **Face** | A pattern supported by related evidence | |
| 36 | | **Volume** | A higher-order structure across projects or areas of life | |
| 37 | | **Root** | The current integrated model of you | |
| 38 | |
| 39 | New evidence can strengthen, revise, or overturn an earlier inference. Every important claim keeps receipts. |
| 40 | |
| 41 | --- |
| 42 | |
| 43 | ## Use cases |
| 44 | |
| 45 | ### 1. One Root — A Model of You |
| 46 | |
| 47 | **Thousands of moments. One evolving model of you.** |
| 48 | |
| 49 | Persome turns sourced observations into relationships, patterns, higher-order structure, and one current Root: what matters now, how you tend to decide, and where your attention is moving. |
| 50 | |
| 51 | <p align="center"><img src="docs/assets/readme/one-root.png" alt="One Root — A Model of You. An activity stream becomes 1,000+ Points, 300+ Lines, 80+ Faces, 20+ Volumes, and one evolving model. A Personal Model example on the right shows current goals and quality standards." width="100%"></p> |
| 52 | |
| 53 | From Points to Lines, Faces, Volumes, and one Root—a living model of who you are and what matters now. |
| 54 | |
| 55 | ### 2. Same AI. Different You. |
| 56 | |
| 57 | <p align="center"><img src="docs/assets/readme/same-ai-different-you.png" alt="" width="100%"></p> |
| 58 | |
| 59 | **The model is the same. The person it understands is different.** |
| 60 | |
| 61 | Two people can give the same AI the same prompt and deserve different answers. Your Personal Model changes how an agent prioritizes, decides, writes, and acts—because it understands who it is working for. |
| 62 | |
| 63 | The same prompt should not produce the same answer for everyone. Give AI a model of you. |
| 64 | |
| 65 | ### 3. One MCP — Turn coding agents into proactive agents |
| 66 | |
| 67 | <p align="center"><img src="docs/assets/readme/one-mcp.png" alt="" width="100%"></p> |
| 68 | |
| 69 | **Your coding agent finds its own work** |
| 70 | |
| 71 | Connect Persome once through MCP. Codex, Claude Code, and other trusted agents can use the same model of your goals, priorities, working patterns, and boundaries. |
| 72 | |
| 73 | Persome identifies un |
People who liked this also viewed
6 picksType
- excel-mcpA Model Context Protocol (MCP) server for working with Excel (.xlsx) files without requiring Microsoft Excel. Enables AI assistants to create, read, modify, and format spreadsheets using openpyxl, fully in Python and cross-platform.MCP ServersOct 2025
- memories-with-lessons-mcp-serverI enhance the existing memory mcp server from the official mcp github, so big thanks and credits for creating thisMCP ServersFeb 2025
- anytype-mcpAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.MCP ServersJul 2026
- mcp-server-kubernetesMCP Server for kubernetes management commandsMCP ServersJul 2026
- thoughtboxThoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.MCP ServersJul 2026
- google-drive-mcpA Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.MCP ServersJul 2026
