Athena-Public: Your Local-First Agentic PKM for Smarter AI Decisions
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
Athena-Public is a powerful local-first agentic Personal Knowledge Management (PKM) system designed to enhance your decision-making. It provides persistent memory, structured reasoning, and governed AI agents that operate across various Large Language Models. This unique approach allows you to own your data and context, while renting the intelligence from any LLM.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
Athena-Public is a powerful local-first agentic Personal Knowledge Management (PKM) system designed to enhance your decision-making. It provides persistent memory, structured reasoning, and governed AI agents that operate across various Large Language Models (LLMs). The core philosophy behind Athena is "Own the state. Rent the intelligence," ensuring your data and context remain yours, regardless of the AI model you choose. Unlike typical assistants that aim to agree with you, Athena is built to remember you well enough to challenge your assumptions and offer truly personalized, critical insights.
This project addresses the common problem of platform memory being unreliable, opaque, and locked to a single provider. Athena moves the memory layer to your local machine, using plain Markdown files that you own, version-control, and can point at any LLM, from ChatGPT to Claude or Gemini. This approach ensures your accumulated knowledge compounds over time, providing a unique continuity advantage.
Installation
Getting started with Athena-Public is straightforward and works across macOS, Windows, and Linux.
Clone the repository:
git clone https://github.com/winstonkoh87/Athena-Public.git cd Athena-PublicClone this folder anywhere you keep projects. This directory will be your Athena workspace, housing your memory, protocols, and configuration.
Set up a virtual environment (recommended):
# Create and activate a virtual environment python3 -m venv .venv source .venv/bin/activate # macOS / Linux # .venv\Scripts\activate # WindowsThis step prevents potential installation issues related to
externally-managed-environment.Install the SDK (optional, enables CLI commands):
# Lightweight install (~30 seconds, no ML dependencies) pip install -e . # Full install (~5–10 min, enables vector search and reranking) pip install -e ".[full]"Important: Do not
pip install athena-cli, as it is a different, unrelated package. Always install from inside the cloned repository.Open the folder in an AI-enabled IDE:
Open the
Athena-Public/directory as your workspace root in a compatible editor such as Zoo Code, Antigravity, Cursor, Claude Code, VS Code + Copilot, Kilo Code, or Gemini CLI. Crucially, Athena does NOT work through web interfaces like ChatGPT.com, Claude.ai, or Gemini web. You need an application that can read files directly from your disk.Boot (in the AI chat panel, not the terminal):
/start/start,/end, and/tutorialare AI chat commands, meant for the chat window where you interact with the AI agent.First time? Take the guided tour:
/tutorialThis guided tour explains Athena, how it works, helps build your profile, and demonstrates its tools (approximately 20 minutes).
When you're done:
/endNo API keys or database setup are required. The folder itself is the product.
Examples
Athena excels at providing deeply personalized and context-aware guidance, moving beyond generic LLM responses.
Here's how Athena approaches various problem types:
| Problem Type | What Athena Does | Example |
|---|---|---|
| Solvable | Solves it | "What's the Kelly fraction for this bet?" ? calculates, answers |
| Optimisable | Optimises within your chosen path | "I've decided to freelance, help me price it" ? constraint optimization |
| Unsolvable | Maps every option, prices every trade-off, hands the choice back to you | A closeted husband with children weighing whether to stay married or come out, Athena ensures full information. |
| Ruin-path | Vetoes before you walk off the cliff | "This bet risks everything" ? Law #1 override, regardless of your preference |
Athena's capabilities extend to various real-world use cases:
- Life Management: Manage health, career, relationships, finances, and client work in one unified system. Athena learns your patterns and can offer cross-domain advice, like prioritizing sleep debt over a client deadline.
- Problem Solving: For complex personal challenges, Athena can conduct structured schema interviews, map internal protective parts (using IFS methodology), and connect patterns to your documented history, offering insights akin to a therapist.
- Decision Making: When faced with significant choices, Athena cross-references your risk profile, financial runway, career history, and regret patterns from similar past decisions to provide highly specific recommendations that a generic LLM cannot.
Why Use Athena?
Athena offers a fundamental shift in how you interact with AI, prioritizing your ownership and personalized growth:
- Your Memory, Your Machine: All your data resides on your local disk as plain Markdown files. You own them, can read and edit them, and even version-control them with Git. This eliminates vendor lock-in and ensures full transparency.
- Switch Models Freely: Athena acts as a portable memory and governance layer. Whether you use Claude today, Gemini tomorrow, or GPT next week, your accumulated context remains consistent and accessible. The model is simply the "intelligence" you rent.
- It Compounds: With each session, Athena extracts decisions, patterns, and learnings into your memory bank. Subsequent sessions load this accumulated intelligence, leading to increasingly sharper and more relevant outputs. The durable asset is your data, not the AI's code.
- Meta-Game Reasoning: Generic LLMs optimize within the game you're playing. Athena, armed with your context, can question whether you should be playing that game at all, offering a higher level of strategic insight.
- Governed Autonomy: Built with six constitutional laws and four capability levels, Athena provides bounded agency, ensuring that AI actions are aligned with your principles and prevent irreversible ruin.
- Human Augmentation Thesis: Athena's core design principle is to augment human cognition, not replace it. It leverages your context not just to agree with you, but to reason differently and, crucially, to tell you when your own documented patterns suggest you might be wrong. This personalization makes disagreement credible and constructive.
Unlike cloud-based platform memories that are opaque and locked to a single provider, Athena gives you full control, inspectability, and portability of your personal AI context.
Links
- GitHub Repository: winstonkoh87/Athena-Public
- Getting Started Documentation: docs/GETTING_STARTED.md
- License: MIT License
- Author's Website: Winston Koh
Related repositories
Similar repositories that may be relevant next.

LoopX: Long-Horizon Agent Control Plane for Governed AI Workflows
August 25, 2026
LoopX is an open, provider-neutral, and stateful control plane designed for long-horizon AI agents. It enables durable, governed work across various agent harnesses, including Codex App and Claude Code. LoopX provides essential capabilities for managing complex, long-running tasks, ensuring objectives, gates, and handoffs remain stable and reviewable.

CLI Agent Orchestrator: Multi-Agent Orchestration for AI Coding CLIs
August 24, 2026
The CLI Agent Orchestrator (CAO) is a powerful tool designed to coordinate multiple AI coding CLIs, enabling a supervisor to delegate tasks to specialist agents in parallel or sequence. It achieves this by running a local `cao-server` and launching provider CLIs within isolated tmux terminal sessions. This setup allows for efficient management and orchestration of various AI coding assistants.

Micstec Skills: A Comprehensive Collection for AI Coding Agents
August 21, 2026
Micstec Skills is a centralized GitHub repository offering a vast collection of skills, plugins, and extensions for various AI coding agents. It supports platforms like Claude Code, Gemini CLI, Copilot, and Cursor, providing a unified approach to managing AI agent capabilities. Developers can easily discover, install, and enhance their AI-powered development workflows across multiple environments.

microsoft/skills: Empowering AI Coding Agents with Domain-Specific Knowledge
August 19, 2026
The microsoft/skills repository provides a comprehensive collection of skills, custom agents, and configurations designed to enhance AI coding agents. It offers domain-specific knowledge for working with Azure SDKs and Microsoft AI Foundry, enabling more effective and context-driven development. Developers can leverage these resources to ground agents like GitHub Copilot with specialized expertise.
Source repository
Open the original repository on GitHub.