// Guide

Work with local agents

Use your own AI tool when the task needs local files, a code repository, or a conversation you already use. ArtifactBridge supplies shared context and a review record. Your tool performs the local work.

Before you start

Install ArtifactBridge Desktop and sign in to the correct workspace.
Install and sign in to the target AI tool.
Enable the tool under desktop Settings → General → Coding tools.
For terminal sessions or automatic starts, install the command-line tool as well as any desktop AI app.
Verify the agent can read the intended workspace.

Access to your local files comes from the AI tool and the folder you give it. ArtifactBridge does not make every file on your computer a workspace document.

Send a Room to an agent

Open the Room in the browser.
Select Send to agent.
Choose a destination from the available groups below.
Allow the browser to open ArtifactBridge if prompted.
Read the opened agent session and confirm its workspace and task before continuing.

For an investigation, define the local scope before the agent starts changing files.

After opening the Room in your agent

Read this Room and its attached specification. Inspect the repository I have opened and identify the likely cause of the reported problem. Do not edit files or run database migrations. Post your findings, supporting file paths, and proposed next steps in the Room. Ask me before making changes.

Resume a saved session

Resume saved session lists supported sessions for your own agents in the Room. Saved-session resume supports Codex CLI and Claude Code CLI. It needs the matching local session on this computer. Another member’s agent is not your local session.

If the saved session is unavailable, the desktop handoff can start a fresh session in the selected tool instead. Read the status so you know whether the previous conversation was recovered. The Room record provides shared context, but it is not a copy of every private message in the original AI conversation.

Start a new terminal session

Use Start new with Codex CLI or Start new with Claude Code CLI. This also lets you bring your first agent into a Room. The tool starts with the Room context rather than a recovered transcript. Ask it to read the Room’s context, open questions, and recent events before acting.

Open a desktop AI app

Where supported, the menu offers ChatGPT, Open in Claude Code, and Open in Claude Cowork. These open the Room’s local workspace in the selected app; they do not restore a terminal transcript. Follow any folder or app confirmation. These launch options are not shown on Linux.

Copy document or Room context

Use Copy context from a document’s actions or a Room’s More room actions menu. Paste it into your connected AI tool, then state the task. The copied text identifies the workspace and item and tells the agent how to read it live. It does not grant access or copy the entire document into the clipboard.

After pasting document context

Read this document and its linked sources. Propose a revision that makes the delivery dates consistent. Explain each changed date.

Copy folder context

Open the project folder and choose Copy context.
Choose Current conversation for a one-time task.
Choose Claude project for text to add to that project’s instructions.
Choose Codex project for a section to add to the project’s AGENTS.md file.
Copy and place the text in the selected destination.

The instructions make the agent read the current folder inventory on each task, then read only relevant documents. Adding the text is a separate step; the copy action does not edit a Claude project or local file for you. The AI tool must already be connected.

Send local files for import

Open Library → New → Upload → Ask your agent, enter the source location, and choose Send to agent. The available import tools include Claude Code, Codex, Grok, Hermes, and OpenCode. The selected tool must be installed and available locally. Review the import proposal in the Inbox before any planned documents are added.

Receive and continue follow-up work

Replies and requests can create wakes for local agents. Inspect them in the desktop Inbox, or enable automatic wakes with limits in Settings → Advanced. A wake can wait because it needs your approval, the tool is unavailable, or a limit was reached. Open its status before sending the same request again.

Keep useful outcomes in the Room and put reusable content in the Library. A result left only in a terminal conversation is not automatically shared with your team.