Sessions
Create, prompt, fork, cancel, trim, and stream agent sessions.
Hoody Agent
Section titled “Hoody Agent”The Hoody Agent is a fully HTTP-driven AI coding agent that runs as an in-container Kit service. Every operation, from creating a session and prompting it, to managing skills, memory, GitHub workflows, hooks, MCP servers, tools, and background tasks, is exposed as a REST endpoint under /api/v1/agent/.... There is no SDK wrapper or native client to install: drive headless coding sessions entirely over HTTP with curl, the hoody-sdk TypeScript client, or any standard HTTP library.
Use this page as the entry point into the agent. Each card below links to a focused sub-page that documents the operations for one area of the agent.
Base URL
Section titled “Base URL”The agent runs as the agent-1 Kit inside your container. Its base URL follows the pattern:
https://{projectId}-{containerId}-agent-1.{server}.containers.hoody.comEvery endpoint is then prefixed with /api/v1/agent/. For example, the sessions endpoint resolves to:
https://{projectId}-{containerId}-agent-1.{server}.containers.hoody.com/api/v1/agent/sessionsReplace {projectId} and {containerId} with the actual 24-character hexadecimal identifiers of your project and container, and {server} with the regional server assigned to your workspace (for example, eu-1).
Sub-pages
Section titled “Sub-pages”Todos
File, claim, run, snooze, and triage the agent todo queue.
Models & Providers
List models and manage LLM providers, including OAuth pools and API keys.
Skills
Skill hub, CRUD, install, import, and toggles.
Chat Agents
Create and customise chat-agent definitions, tools, and models.
Memory
Persistent memory items, the project graph, and hybrid recall search.
GitHub
Auth, clone, commit, sync, branches, repos, and pull requests.
Hooks
Lifecycle hooks: upsert, toggle, test, reload, and trust.
MCP Servers
Configure MCP servers: list with live state, add, enable, remove, import, probe, and reconnect.
Tools
Tool catalogue, schemas, and sessionless or in-session tool runs.
Workflows
Define, run, and manage multi-step agent workflows.
Bots
Long-lived assistants that open delegate sessions, follow them, and report back.
Settings
Agent settings, fusion composites, and BYOA or ACP backends.
Logs
Query, stream, and inspect agent logs.
Change tokens
Learn which work lists changed, by polling or over SSE, before re-listing them.
Loops
Scheduled self-prompting loops on a session.
Tasks
Inspect and cancel a session’s background tasks.
Jobs
Poll and cancel async jobs and read their results.
Statistics
Cross-session statistics and usage rollups.
Discovery
List realms and containers for session binding.
Headless
Fire one-shot headless agent runs.
System
Health, metrics, and the live OpenAPI spec.