Agents, engines and models
Chat runs on Rhizome’s own engine (ADR-0187). Prime and Hermes are no longer chat engines (ADR-0189); leftover code is still in the repo until the follow-up PRs. The vault, permissions, and saved memory stay the same.
Terms on this page
Section titled “Terms on this page”- Agent loop: the cycle that sends your message to a model, runs the tools the model asks for, and repeats until the answer is done.
- Engine: what runs that loop for Chat.
- Model: the language model the engine talks to, hosted or running locally.
- Tool: an action the agent can take, such as reading a note or running a command.
Engine for Chat
Section titled “Engine for Chat”New chats use Rhizome’s engine: the loop built into the app. It does not need Prime. You pick catalog providers or Taproot, and the vault tools below run against the open vault.
Rhizome’s engine
Section titled “Rhizome’s engine”- Models: pick a catalog model, or Taproot. See Free models and routing. Anthropic models aren’t offered here yet.
- Tools: see the table below. Read and search tools run without asking. Edits and shell commands ask first.
- Saved chats: each chat is saved as it goes and can be reopened after you quit. Chats get a title automatically from the first exchange.
- Errors: a problem that doesn’t stop the turn shows as a notice in the chat. A problem that does stop it, such as a missing key, ends the turn with a message that says what to fix.
| Tool | What it does | When it runs |
|---|---|---|
read_file, list_dir, grep, glob | Read and search files in the open vault and workspace | Auto in both permission modes. Paths outside those roots are refused |
edit_file, write_file | Change or create a file in those same roots | Asks every time unless you already allowed that tool and path for the session |
create_note | Create a new Markdown note without overwriting | Asks in Limited tools. Auto in Power User |
bash | Run one shell command with the vault as the working directory | Power User only. Asks every time. There is no session grant |
echo | Return its arguments | Auto |
bash really runs the command (sh -c on macOS and Linux, cmd /S /C on Windows). Default timeout is 60 seconds, capped at 300. The working directory cannot be chosen by the model. stdin is closed. Output is capped. See the Chat Run command card for the full command, then stdout and stderr after it finishes.
Secret files (.env* except .env.example, .git/, key material) are blocked on the file tools. That denylist does not cover bash. Settings → AI Agents → Safety can turn the denylist off for reads only.
Permission modes
Section titled “Permission modes”A permission mode decides what the agent may do without asking. It’s set per vault.
| Mode | Rhizome’s engine |
|---|---|
| Limited tools | Read and search auto-run. create_note asks. Edits ask. No bash |
| Power User | Read, search, and create_note auto-run. Edits still ask unless a session grant covers that path. bash is offered and asks every time |
Plugins
Section titled “Plugins”Rhizome will have its own plugin system: add a tool, hook into a turn, or block a tool call. It’s planned, not shipped. Today, MCP lets other apps use your vault.
Let other apps use your vault (MCP)
Section titled “Let other apps use your vault (MCP)”MCP (Model Context Protocol) lets other AI apps call Rhizome’s tools. With it, an MCP client such as Claude Code or Cursor can read and write your vault.
Run Set Up External AI Tools… from the command palette (⌘K). Rhizome shows which config files it will change (for example ~/.claude.json and ~/.cursor/mcp.json) and writes nothing until you confirm. It needs Node.js 18 or newer, or Bun, on your PATH. To paste the entry yourself, use Copy MCP config on Settings → AI Agents (ai.panel.copyMcpConfig).
Review what the agent changed
Section titled “Review what the agent changed”Agent edits are file edits. In a Git-backed vault, review them in the Changes view, look at the diff, and commit or revert. Save chat results you want to keep with Save to vault. See Your vault is the agent’s memory.