🧠 AI
One Threads app for every AI harness — and the engine that runs them.
One entry. Installing this gives a deployment its chat runtime and the catalogs where agents, models, providers, skills and tiers are administered. They ship in one assembly because they are one thing: an engine nobody can configure is not a feature.
What ships
- The shared Threads app — your conversations and the Store's personal-harness installation controls. Claude Code, Codex, Copilot and other harness packages open this same app; each harness owns its login flow.
- The agent runtime — threads, rounds, delegation, tool calling, harnesses, token accounting.
- The maintenance app — the Agents, Skills, Providers, Models and Tiers catalogs, plus the agent overview and details views.
- The content types —
Agent,Skill,Harness,ModelProvider,Thread,ThreadMessage,TokenUsage— served from Postgres or in-memory depending on what this deployment configures.
What does NOT ship here
Model providers are their own entries. OpenAI, Anthropic, AzureFoundry, ClaudeCode, Copilot and WebSearch each install separately, so a deployment carries only the ones it uses and drops one by uninstalling rather than by editing a list. This entry is the engine they plug into.
Shared tasks span harnesses. Shared tasks for multiple agents starts one durable
AgentTask context and ordinary sibling threads so agents can discover and message each other.
Credential administration stays in Providers & Models, and per-user settings stay in AI Settings. Both read this engine's node types; neither is folded in here, deliberately — a page that renders a key form has different rules from one every signed-in user opens.