Sessions
Create, prompt, fork, cancel, trim, and stream agent sessions.
Hoody Agent
Section titled “Hoody Agent”The Hoody Agent API exposes a fully HTTP-driven AI coding agent. Every action a developer normally performs inside the IDE — opening a session, prompting a model, running a tool, managing a todo, committing code, configuring a provider — is reachable over a single, versioned REST surface rooted at /api/v1/agent/. The service is headless by design: it has no required frontend, so any client that can speak HTTP (curl, a server-side worker, a CI job, another service) can drive a complete coding session from creation through completion.
Use these endpoints when you need to:
- Spawn and orchestrate long-running agent sessions, including streaming responses and tool calls.
- Manage the operational state around a session: todos, background tasks, async jobs, logs, and statistics.
- Configure the agent itself: models and providers, skills, chat agents, memory, hooks, tools, and workflows.
- Integrate with external systems: GitHub (auth, repos, commits, branches, pull requests), loops (scheduled self-prompting), and headless one-shot runs.
- Discover and inspect the runtime: realms, containers, health, metrics, and the live OpenAPI specification.
The pages below cover every operational area of the Hoody Agent. Each page lists its endpoints, parameters, request bodies, response shapes, and SDK calls.
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 (API keys, OAuth pools).
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.
Tools
Tool catalogue, schemas, and sessionless or in-session tool runs.
Workflows
Define, run, and manage multi-step agent workflows.
Settings
Agent settings, fusion composites, and BYOA/ACP backends.
Logs
Query, stream, and inspect agent logs.
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.