<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> Arkon provides organizations with centralized control over employee AI client usage, addressing fragmented knowledge and inconsistent AI context. It acts as an enterprise AI knowledge hub, enabling employees to securely connect to organizational data and AI models via a unified portal, ensuring they always have the correct, scoped context. This empowers teams with consistent, reliable AI-assisted workflows.

How It Works

<2-4 sentences on core approach / design (key algorithms, models, data flow, or architectural choices) and why this approach is advantageous or novel.> Arkon compiles organizational documents into a persistent, interlinked wiki using an LLM agent, enriching knowledge over time. This structured wiki, raw documents, and custom AI skills are then served to employee AI clients (e.g., Claude Desktop) through the Model Context Protocol (MCP). This approach ensures employees automatically receive relevant, permission-scoped context without manual data input, treating AI clients as managed organizational resources.

Quick Start & Requirements

• Primary install / run command (pip, Docker, binary, etc.).
• Non-default prerequisites and dependencies (GPU, CUDA >= 12, Python 3.12, large dataset, API keys, OS, hardware, etc.).
• Estimated setup time or resource footprint.
• If they are present, include links to official quick-start, docs, demo, or other relevant pages.
• Install: Docker Compose.
• Prerequisites: Docker, Docker Compose, AI provider API key (OpenAI, Anthropic, Google, etc.).
• Run: Clone repo, configure .env.docker (SECRET_KEY, admin credentials), then run docker compose --env-file .env.docker up -d --build. Access via http://localhost:3119.
• Post-setup: Configure embedding, LLM, and vision models in Settings.
• Docs: Setup Guide, Architecture, MCP & Claude.

Highlighted Details

• Bullet 1 (benchmarks, performance claims, novel integration, etc.)
• Bullet 2
• Bullet 3
• Bullet 4 (optional)
• Knowledge Wiki: LLM-generated, persistent, interlinked wiki with version history, graph visualization, and three-panel browser.
• Workspaces: Scoped knowledge contexts for projects/clients with role-based membership.
• AI Skills: Versioned, department-scoped custom agent packages distributed via MCP.
• Access Control: Fine-grained RBAC at department and workspace levels.
• Tech Stack: FastAPI, PostgreSQL+pgvector, Redis, MinIO, Next.js. Supports multiple AI providers.

Maintenance & Community

• Notable contributors, sponsorships, partnerships, deprecations, migrations, or other health signals if notable.
• Links to Discord/Slack, social handles, roadmap, etc. No specific community links (Discord/Slack) or contributor details were found in the provided README. The roadmap indicates ongoing development with several features marked as planned.

Licensing & Compatibility

• License type and notable restrictions (GPL -> copyleft, SSPL, etc.).
• Compatibility notes for commercial use or closed-source linking.
• License: PolyForm Noncommercial License 1.0.0.
• Compatibility: Free for internal tooling, research, personal projects, and non-profit use. Commercial use requires a separate license or custom integration engagement.

Limitations & Caveats

<1-3 sentences on caveats: unsupported platforms, missing features, alpha status, known bugs, breaking changes, bus factor, deprecation, etc. Avoid vague non-statements and judgments.> The PolyForm Noncommercial License restricts commercial deployment without explicit licensing. Features such as Regex Search, an Arkon CLI, a notification system, and usage analytics are currently listed as future roadmap items.