Skip to main content
Guild is a platform for building and running AI agents. Install pre-built agents from the catalog, or build custom agents with the Agent SDK and publish them to your workspace.

​
Core concepts

Workspaces

A workspace is your team’s shared environment. It connects to a GitHub repository and holds the agents your team has installed.

Agents

Agents are programs that accept input, use tools and LLMs, and produce output. They range from simple scripted programs to autonomous LLM-driven workflows.

Sessions

A session is a conversation with an agent. You provide input, the agent runs, asks questions if needed, and returns its output.

​
How agents work

Requests flow from the browser or CLI to guildcore (API layer), which queries the database and forwards the request to the runtime, which executes the agent. 
Browser/CLI → guildcore (API) → runtime (agent executor) → Agent
                    ↓
               Database
  1. You start a session and send a message to an agent.
  2. guildcore receives the request, authenticates it, and forwards it to the runtime.
  3. The runtime loads the agent code, executes it, and manages the agent lifecycle.
  4. The agent can call tools, invoke sub-agents, make LLM calls, and ask you questions.
  5. When the agent finishes, its output is returned to your session.

​
Next steps

Quickstart

Build and publish your first agent in five minutes.

CLI reference

Install the CLI and learn the development workflow.

Agent SDK

Build advanced agents with typed inputs, tools, and platform services.