Projects are the credibility layer of mlllm.io. They show that the news desk and the writing are backed by real software work: ingestion pipelines, publication tooling, dashboards, MCP integrations, local knowledge workflows, and agent orchestration experiments.
Each project page should answer practical questions. What problem does it solve? What is running today? What is public? Which repository or channel proves it exists? What still needs work? This makes the site useful for human collaborators and also easier for LLM agents to summarize without guessing.
TG-NEWS is the core production system. Task-Plan v2 Dashboard is the strongest open-source candidate for agent workflow visibility. MCP experiments provide reusable integration surfaces. Together they form a coherent author profile: AI media infrastructure plus tools for agentic development.
The next production step is to connect these cards to richer project pages with repository metadata, screenshots, changelog entries, and links back to articles that use the same infrastructure.