Configuration
config.json, the files in ~/.sedge, and environment variables.
Most things are set up by asking sedge in the TUI. The rest is ~/.sedge/config.json.
agents, limits and the models are read again whenever they're used, so a change
applies at once. The rest (workspace, connections, permissions, sandbox, triageModel,
piExtensions, dreaming) is read when the daemon starts: after editing those, restart it with
sedge stop && sedge start.
config.json
{
"workspace": "/Users/you/sedge-work",
"dreaming": true,
"permissions": { "bash": "ask", "write": "allow", "mcp": "ask" },
"limits": { "runsPerHour": 30, "dailyCost": 5, "subagents": 6 },
"agents": {
"ci": { "purpose": "Watch the CI signal; tell me only when main breaks." }
},
"connections": {
"telegram": { "kind": "telegram", "settings": {}, "secrets": ["token"] }
}
}| Setting | What it does | Default |
|---|---|---|
model | The model the daemon's runs use, as provider/model, with :level for thinking. See Models. | pi's default |
workspace | Where unwatched runs work (files they create land here). | ~/.sedge/workspace |
sandbox | Commands in the OS sandbox: enabled, network, writable, hidden. See Sandbox. | off |
limits | What the agents may use: runs, tokens, money, subagents. See Limits and costs. | unlimited |
triageModel | The model that triages signals with triage on, as provider/model. | see below |
dreaming | The nightly memory review. false turns it off. See Memory. | on |
permissions.bash | Shell commands in unwatched runs: allow, ask or deny. | ask |
permissions.write | File writes and edits in unwatched runs. | allow |
permissions.mcp | MCP tools and other tools in unwatched runs. | ask |
permissions.signals.bash, .write, .mcp | The same, for runs woken by outside content; the stricter of the two applies. See Security. | ask |
agents | Agents besides main, by name, each with its purpose. See Agents. | none |
piExtensions | pi extensions to load in the daemon's runs, by name or package. See Extensions. | none |
connections | Channels and signals by name. Written by connect; edit with care. | none |
Each connection has a kind, its settings (never secrets), secrets (the names of the
settings kept in the keychain), an optional instruction for a signal, an optional agent that
handles it (default main), and enabled: false to pause it. A signal can also have match and
ignore (regular expressions an event's text must or must not match), labels and wakeOn (for
triage to label each event, and the labels that wake the agent), remember (keep its latest value
as a named value instead of waking the agent), when (a
condition on its
details, like temperature > 30), throttle (how long to stay quiet after an event, like 1h),
batch (how long to hold its events and hand them over together, like 5m) and triage: true
(a cheap model decides which events need the agent); see
Filtering, throttling and triage.
Limits
Every limit is off until you set it. limits is read again whenever config.json changes, so a new
limit applies without a restart.
| Limit | What it caps |
|---|---|
limits.runsPerHour | Runs in the last hour, for each agent with its subagents. |
limits.dailyTokens | Tokens across all agents today, triage included. |
limits.dailyCost | Money across all agents today, at the models' listed prices. |
limits.subagents | Subagents one agent can have working at once. |
What happens when one is reached, and how to spend less to begin with: Limits and costs.
Sandbox
| Setting | What it does | Default |
|---|---|---|
sandbox.enabled | Runs the daemon's commands in the operating system's sandbox. | off |
sandbox.network | Whether commands may connect anywhere. | true |
sandbox.writable | More folders it may write to. | none |
sandbox.hidden | More files and folders nothing in it may read. | none |
It's set when the daemon starts; restart after changing it. See Sandbox.
Models
The daemon's runs use pi's default model (the one /model picks in the TUI, at its thinking level)
unless you choose another. Three places can, and the most specific wins:
| Where | For |
|---|---|
connections.<name>.model | Runs a channel or signal wakes on its own (when it's the only source). |
agents.<name>.model | That agent's runs. See Agents. |
model | Every other run: main, and agents without their own. |
Each is provider/model as /model lists it, and may end in a thinking level (off, minimal,
low, medium, high, xhigh, max), as --model takes it: "anthropic/claude-opus-5-5:medium".
Without one, the run thinks at your default's level. A model you aren't logged in to is skipped,
with a warning in the log, and the run uses the default.
You don't need to edit the file: ask the TUI's agent ("run Telegram on Opus at medium"), which uses
set_model and asks you first, or send /model on a channel (Channels and signals).
They apply from the next run, without a restart. /model in the TUI changes only the TUI's session
(and pi's default, which the daemon follows where nothing else is set).
Triage model
Without triageModel, triage uses the cheapest priced model of your default model's provider; if
the provider lists no prices (a subscription), one whose name says it's small (mini, haiku,
flash, …); and failing that, your default model. Set it ("triageModel": "openai/gpt-5-mini") to
choose.
Files
Everything lives in ~/.sedge (or SEDGE_HOME):
| Path | What |
|---|---|
config.json | The settings above. |
sedge.sock | The socket the TUI and the daemon talk over (a named pipe on Windows). |
daemon.lock | Holds the running daemon's process id, so only one runs. |
memory/ | main's memory, with MEMORY.md as its index; each agent's is in memory/agents/<name>/. |
workspace/ | Where unwatched runs work. |
sedge.db | Inbox, timers, outbox, approvals. |
agent/durable.sqlite | The agent's conversations. |
packages/ | Installed packages of channels and signals. |
kinds/ | Signals and channels you registered. |
logs/ | daemon.log, and the logs and runs sedge dash shows (sedge.jsonl, runs.jsonl). |
bin/ | The standalone install. |
secrets.json | Secrets, only on machines without a keychain. |
Model logins, models.json, mcp.json and skills are pi's, in ~/.pi/agent.
Environment variables
| Variable | What it does |
|---|---|
SEDGE_HOME | Use another folder than ~/.sedge (a second, separate sedge). |
SEDGE_NO_UPDATE | Set to 1 to only report updates instead of installing them. |
SEDGE_AGENT_DIR | Another pi agent folder for the daemon: logins, models, mcp.json, MCP sign-ins, skills. |
SEDGE_CODING_AGENT_DIR | The agent folder the TUI uses (logins, models, settings, themes); default ~/.pi/agent. |
SEDGE_SECRET_STORE | file keeps secrets in ~/.sedge/secrets.json (owner-only) instead of the OS keychain. |
SEDGE_REGISTRY | The npm registry to check for updates. |
SEDGE_GITHUB_API | The GitHub API to check standalone releases against. |