Persome is an open-source tool that builds a private, local personal model on macOS from captured activity and provides evidence-linked context to MCP-compatible AI agents like Codex and Claude Code.

Stars

384

7-day growth

No data

Forks

30

Open issues

7

License

Apache-2.0

Last updated

2026-07-16

Why it is worth attention

It creates a persistent, hierarchical model of the user's thinking and work patterns that AI agents can query via the Model Context Protocol, enabling grounded decisions and proactive task continuation while keeping all data local and private.

Who it is for

  • Developers using AI coding agents (Codex, Claude Code) who want personalized context
  • Privacy-conscious professionals seeking a local alternative to cloud-based personal AI models
  • Power users who want to automate their workflow with AI agents aware of their priorities and open tasks

Use cases

  • Give any MCP-compatible AI agent a living model of your goals, priorities, and working patterns to get personalized responses
  • Let a coding agent automatically identify and continue unfinished work based on your actual activity
  • Run background task execution while you sleep—agent completes safe local work and presents a morning report

Strengths

  • Runs fully locally with no cloud dependencies, and user can inspect, correct, export, and delete all data
  • Uses a deterministic multi-layer model (Points → Lines → Faces → Volumes → Root) where every claim has evidence receipts
  • Integrates seamlessly via MCP with multiple clients—register once and agents use the same model
  • Supports both synthetic demo (no personal data) and real install with granular macOS permissions

Considerations

  • Requires macOS 13+ and macOS Accessibility permissions for activity capture (no other OS support)
  • Semantic modeling requires an LLM—optional for collection but required for building the model hierarchy
  • First useful recall is operationally expected after about ten minutes of capture, not guaranteed as a benchmark

README quick start

Persome: Build your Personal Model

The open-source Personal Model that makes every AI yours.

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.

Runs locally on your Mac. Private by default. Yours to inspect, correct, export, and delete.

Try the synthetic demo · Install with your data · Connect an MCP client · Star Persome on GitHub

Concept illustration of a mature Personal Model. The deterministic Runtime proof is shown in the demo below.


What is it?

Your HUMAN.md

Persome connects activity into progressively deeper context:

LayerMeaning
PointA sourced observation or event
LineA relationship or change over time
FaceA pattern supported by related evidence
VolumeA higher-order structure across projects or areas of life
RootThe current integrated model of you

New evidence can strengthen, revise, or overturn an earlier inference. Every important claim keeps receipts.


Use cases

1. One Root — A Model of You

Thousands of moments. One evolving model of you.

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.

From Points to Lines, Faces, Volumes, and one Root—a living model of who you are and what matters now.

2. Same AI. Different You.

The model is the same. The person it understands is different.

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.

The same prompt should not produce the same answer for everyone. Give AI a model of yo

Description

Build your HUMAN.md.

Related repositories

Similar projects matched by category, topics, and programming language.

SuperJJ007
Featured
SuperJJ007 GitHub avatar

CSswitch

Use any third-party OpenAI-compatible API to run Claude Science's AI agent research platform without a Claude subscription.

AI & Machine LearningDesktop Apps
131
William-Lu-stack
William-Lu-stack GitHub avatar

Flawless

Flawless is an AI-native SRE control plane for Kubernetes that connects alerts, evidence, topology, approval, remediation, and recovery verification into a closed-loop AgenticOps system.

Python
655
QuantumByteOSS
QuantumByteOSS GitHub avatar

quantumbyte

QuantumByte is an open-source app builder that generates applications from user intent and continuously verifies each agent turn against explicit business requirements.

Python
313