AI Section

Artificial Intelligence

Projects I've built, and deep dives into the frontier models I work with every day.

Projects

Multi-agent orchestration with automation, dashboards, and department management

15+ agents running across 6 departments with live monitoring

WPF desktop AI assistant with local LLM, cloud providers, and swarm coordination

Version 2.0.0 — local LLM + 4 cloud providers + MCP tool use

Graph-based semantic memory with real-time recall and MCP integration

694+ nodes in live graph with sub-100ms semantic recall

Zhipu AI / Zai-Org

Frontier reasoning model with 128K context and agentic capabilities

Frontier reasoning with FP8 efficiency — 2x faster inference, near-lossless quality

Anthropic

Constitutional AI with exceptional code understanding and safety

Constitutional AI with 200K context — best for safety-critical and code-heavy tasks

OpenAI

Unified model with adaptive reasoning depth and multimodal capabilities

Adaptive reasoning with 256K context — auto-scales compute based on task difficulty

Google DeepMind

Massive 2M token context with native multimodal and tool integration

2M token context — process entire codebases, books, and videos in a single prompt

DeepSeek

Open-weights reasoning model with Mixture-of-Experts architecture

Open-weights MoE with 671B params — self-hostable frontier reasoning