Summary

Pal is a personal agent designed to learn user workflows by building a compounding knowledge base from diverse data sources. It targets individuals managing significant personal or professional information, offering a unified, intelligent system for organization, recall, and action, thereby enhancing productivity and insight.

How It Works

Pal employs a team of five AI specialists coordinated by a leader. It maintains two distinct knowledge layers: a compiled wiki for conceptual understanding and a PostgreSQL database for structured data like notes and projects. This multi-modal approach, combined with a metadata routing layer, allows Pal to intelligently select the optimal source (wiki, SQL, files, external tools) for query resolution, avoiding the limitations of a single vector store. A continuous learning loop refines its performance with each interaction.

Quick Start & Requirements

• Primary install/run command: Clone the repo, cd pal, copy example.env to .env, add OPENAI_API_KEY, and run docker compose up -d --build.
• Non-default prerequisites: Docker, OpenAI API Key.
• Links: API documentation at http://localhost:8000/docs; Web UI via AgentOS at os.agno.com (connect to http://localhost:8000).

Highlighted Details

• Dual Knowledge Architecture: Integrates a text-heavy wiki (concepts, summaries) with a structured SQL database (notes, people, projects, decisions) for comprehensive data management.
• Intelligent Source Routing: Navigates and queries across raw ingested data, wiki, local files, and external tools (Gmail, Calendar, Slack, Exa) using a metadata routing layer.
• Automated Knowledge Pipeline: Features scheduled tasks for daily ingestion, wiki compilation, and weekly health checks (linting) to maintain knowledge integrity.
• Extensive Integrations: Supports Slack, Gmail, Google Calendar, and web search via Exa and Parallel.ai, enhancing its utility as a personal assistant.

Maintenance & Community

The provided README does not detail specific maintenance practices, notable contributors, sponsorships, or community channels (e.g., Discord, Slack).

Licensing & Compatibility

The repository's README does not specify a software license. Consequently, compatibility for commercial use or linking within closed-source projects is undetermined.

Limitations & Caveats

Core functionality is dependent on an OPENAI_API_KEY. Advanced integrations (Gmail, Calendar, Slack, Parallel.ai) require complex setup, including API keys, OAuth, and potentially ngrok. Gmail integration is limited to draft creation, with send capabilities disabled. Google OAuth tokens have a 7-day expiration unless the application undergoes Google's verification process. The Researcher agent is inactive without a PARALLEL_API_KEY. The absence of a declared license poses a significant adoption blocker for many use cases.