Chats and agents
Start chats with any AI, attach files, pick models, set what an agent may do, and keep track of what's running.
Every chat on the canvas is a full AI agent. It can read and edit files, run commands and build things, in a folder you choose. Run as many as you like side by side, each with its own AI, model and settings.
Start a chat
- Double-click an empty spot on the canvas for a Claude chat, or double right-click for a Codex chat. You can change what both make in Settings → General.
- Press Ctrl + K and choose New chat in ….
- Click New chat on a project's overview card.
- Or ask Morphy: "open three Codex chats in my website folder" (see Morphy, your assistant).
A new chat works in the folder of the project you're looking at. If the project has no folder, it works in Morphy's own folder.
The title bar
From left to right:
- The title. Made from what you asked, and updated as you go. Hover it to see it in full.
- The AI's name. Click it to switch this chat to another AI. Switching starts a fresh conversation. AIs that aren't set up yet are marked, with a pointer to Settings → Account.
- The folder the chat works in (when it's not Morphy's own folder). See Working folder.
- On hover: Conversations (earlier conversations in this folder), New conversation and Close.
Send a message
Type in the box at the bottom and press Enter. Shift + Enter starts a new line, and ↑ at the start of the box brings back what you sent before.
While the agent works, its steps fold into one line ("12 steps · editing app.tsx"). Click it to see every file it read or changed and every command it ran. A timer shows how long it's been working. Code blocks in replies have a copy button.
Attach files and images
- Click ＋ (Attach files) to pick files.
- Drag files from Explorer onto the chat.
- Paste an image or screenshot straight into the text box (Ctrl + V).
The agent gets the files' locations on your computer and reads them itself, so large files and whole folders of context are fine.
To give a chat what's on some of your cards, select the cards, click Copy these cards as context in the toolbar and paste into the chat.
Slash commands
Type / in an empty box for a menu of commands.
- Claude chats list Claude Code's own commands, plus the commands and skills in the project's
.claudefolder. - Every chat has /skills, to attach one of your skills to the message.
Models and effort
Next to the text box:
- Model. The model for your next message. Claude shows Anthropic's current models; other AIs show the models your account has. Choose custom… to type any model name. In OpenRouter chats, free models are listed first.
- Effort. How hard the model thinks before answering, from low to maximum (Claude) or minimal to extra high (Codex and friends). auto lets the model decide.
Under the box you'll see the model in use and how many tokens the last turn used.
Permissions
The permission button next to the text box sets what the agent may do without asking you. Each chat keeps its own setting.
| Mode | Label in Claude chats | Label in other chats | What the agent may do |
|---|---|---|---|
| No guardrails | no guardrails | no guardrails | Edit files and run commands without asking |
| Edits only | auto-accept edits | workspace write | Change files in its folder; anything else asks first |
| Ask first | ask first | ask first | Ask before it changes a file or runs a command |
| Read only | plan only | read only | Read and plan, but change nothing |
New chats start in No guardrails. Change the default in Settings → General → New chats start in.
When an agent asks, the chat shows what it wants to do with Allow, Always and Deny. Always allows that kind of action for the rest of the session (until you quit Morphy). If you deny, the agent adjusts its approach or asks you.
No guardrails means no questions
In No guardrails an agent can change and delete files and run any command in its folder without checking with you. That's what makes it fast. For a folder you can't easily restore, use Ask first, or keep it in Git.
Antigravity can't ask from inside Morphy: in ask first and workspace write it skips any step that needs your OK, and tells you so. To let it do everything, set the chat to no guardrails.
Stop, queue and schedule
The button next to the text box changes with what the agent is doing:
- Send when it's idle.
- Stop this turn while it works and the box is empty. Stop always stops: if an agent doesn't respond, Morphy ends it after a few seconds. The conversation is kept.
- Queue message for next turn while it works and you've typed something. Your message waits and is sent as soon as the current turn finishes. If you stop the turn, queued messages come back into the box.
Schedule a message: type your message, right-click the send button, enter a number of minutes, then click Send. The message waits, marked "scheduled", and sends itself then.
Queued and scheduled messages live as long as Morphy is open; quitting or restarting drops them.
If an agent goes quiet for 10 minutes, the chat asks whether to Stop or Keep waiting.
Know when it's done
- The bell. Select a chat and click the bell in the toolbar. When the chat finishes, or stops to ask you something, a chime plays until you click, scroll or type in that chat.
- Tab badges. A blue number on a tab counts the agents that finished, or need you, while you were looking at another canvas.
- From far away. Zoomed out, every chat shows Working… or Needs you.
- The sidebar. A dot next to a project shows an agent working or waiting there.
Working folder
Every chat works in one folder: it reads, edits and runs commands there.
- Change it: click the folder in the chat's title bar and pick another one. The chat starts a fresh conversation in the new folder.
- Back to Morphy's folder: right-click the folder.
In a project folder, a chat is a normal coding agent: Claude reads that project's own CLAUDE.md, for example. In Morphy's own folder, a chat also gets Morphy's instructions, so it can build cards and manage other chats.
Conversations
Chats remember their conversation. Close Morphy, open it tomorrow, and every chat continues where it left off.
- New conversation (in the title bar) starts fresh. Files and cards are untouched.
- Conversations lists earlier conversations in this chat's folder, so you can pick one up again.
Close and bring back
Close a chat with its ✕. A chat can't be closed while its agent is working: stop it first. Ctrl + Z brings a closed chat back on the same conversation, and for 3 days you can restore it from Ctrl + K.
If agents are still working when you quit Morphy, it lists them and asks: Keep working or Quit anyway. Your chats and their conversations are kept either way.
Swarms
A swarm groups chats that use the same AI into one folder on the canvas, with one prompt box: each message goes to a free agent in the swarm. Create one by holding a chat over another while you drag, or select several and click Create a swarm from selected chats. See The canvas.