8.6 KiB
summary, title, read_when, status
| summary | title | read_when | status |
|---|---|---|---|
| Multi-agent routing: isolated agents, provider accounts, and bindings | Multi-Agent Routing | You want multiple isolated agents (workspaces + auth) in one gateway process. | active |
Multi-Agent Routing
Goal: multiple isolated agents (separate workspace + agentDir + sessions), plus multiple provider accounts (e.g. two WhatsApps) in one running Gateway. Inbound is routed to an agent via bindings.
What is “one agent”?
An agent is a fully scoped brain with its own:
- Workspace (files, AGENTS.md/SOUL.md/USER.md, local notes, persona rules).
- State directory (
agentDir) for auth profiles, model registry, and per-agent config. - Session store (chat history + routing state) under
~/.clawdbot/agents/<agentId>/sessions.
Skills are per-agent via each workspace’s skills/ folder, with shared skills
available from ~/.clawdbot/skills. See Skills: per-agent vs shared.
The Gateway can host one agent (default) or many agents side-by-side.
Workspace note: each agent’s workspace is the default cwd, not a hard sandbox. Relative paths resolve inside the workspace, but absolute paths can reach other host locations unless sandboxing is enabled. See Sandboxing.
Paths (quick map)
- Config:
~/.clawdbot/clawdbot.json(orCLAWDBOT_CONFIG_PATH) - State dir:
~/.clawdbot(orCLAWDBOT_STATE_DIR) - Workspace:
~/clawd(or~/clawd-<agentId>) - Agent dir:
~/.clawdbot/agents/<agentId>/agent(oragents.list[].agentDir) - Sessions:
~/.clawdbot/agents/<agentId>/sessions
Single-agent mode (default)
If you do nothing, Clawdbot runs a single agent:
agentIddefaults tomain.- Sessions are keyed as
agent:main:<mainKey>. - Workspace defaults to
~/clawd(or~/clawd-<profile>whenCLAWDBOT_PROFILEis set). - State defaults to
~/.clawdbot/agents/main/agent.
Agent helper
Use the agent wizard to add a new isolated agent:
clawdbot agents add work
Then add bindings (or let the wizard do it) to route inbound messages.
Verify with:
clawdbot agents list --bindings
Multiple agents = multiple people, multiple personalities
With multiple agents, each agentId becomes a fully isolated persona:
- Different phone numbers/accounts (per provider
accountId). - Different personalities (per-agent workspace files like
AGENTS.mdandSOUL.md). - Separate auth + sessions (no cross-talk unless explicitly enabled).
This lets multiple people share one Gateway server while keeping their AI “brains” and data isolated.
One WhatsApp number, multiple people (DM split)
You can route different WhatsApp DMs to different agents while staying on one WhatsApp account. Match on sender E.164 (like +15551234567) with peer.kind: "dm". Replies still come from the same WhatsApp number (no per‑agent sender identity).
Important detail: direct chats collapse to the agent’s main session key, so true isolation requires one agent per person.
Example:
{
agents: {
list: [
{ id: "alex", workspace: "~/clawd-alex" },
{ id: "mia", workspace: "~/clawd-mia" }
]
},
bindings: [
{ agentId: "alex", match: { provider: "whatsapp", peer: { kind: "dm", id: "+15551230001" } } },
{ agentId: "mia", match: { provider: "whatsapp", peer: { kind: "dm", id: "+15551230002" } } }
],
whatsapp: {
dmPolicy: "allowlist",
allowFrom: ["+15551230001", "+15551230002"]
}
}
Notes:
- DM access control is global per WhatsApp account (pairing/allowlist), not per agent.
- For shared groups, bind the group to one agent or use Broadcast groups.
Routing rules (how messages pick an agent)
Bindings are deterministic and most-specific wins:
peermatch (exact DM/group/channel id)guildId(Discord)teamId(Slack)accountIdmatch for a provider- provider-level match (
accountId: "*") - fallback to default agent (
agents.list[].default, else first list entry, default:main)
Multiple accounts / phone numbers
Providers that support multiple accounts (e.g. WhatsApp) use accountId to identify
each login. Each accountId can be routed to a different agent, so one server can host
multiple phone numbers without mixing sessions.
Concepts
agentId: one “brain” (workspace, per-agent auth, per-agent session store).accountId: one provider account instance (e.g. WhatsApp account"personal"vs"biz").binding: routes inbound messages to anagentIdby(provider, accountId, peer)and optionally guild/team ids.- Direct chats collapse to
agent:<agentId>:<mainKey>(per-agent “main”;session.mainKey).
Example: two WhatsApps → two agents
~/.clawdbot/clawdbot.json (JSON5):
{
agents: {
list: [
{
id: "home",
default: true,
name: "Home",
workspace: "~/clawd-home",
agentDir: "~/.clawdbot/agents/home/agent",
},
{
id: "work",
name: "Work",
workspace: "~/clawd-work",
agentDir: "~/.clawdbot/agents/work/agent",
},
],
},
// Deterministic routing: first match wins (most-specific first).
bindings: [
{ agentId: "home", match: { provider: "whatsapp", accountId: "personal" } },
{ agentId: "work", match: { provider: "whatsapp", accountId: "biz" } },
// Optional per-peer override (example: send a specific group to work agent).
{
agentId: "work",
match: {
provider: "whatsapp",
accountId: "personal",
peer: { kind: "group", id: "1203630...@g.us" },
},
},
],
// Off by default: agent-to-agent messaging must be explicitly enabled + allowlisted.
tools: {
agentToAgent: {
enabled: false,
allow: ["home", "work"],
},
},
whatsapp: {
accounts: {
personal: {
// Optional override. Default: ~/.clawdbot/credentials/whatsapp/personal
// authDir: "~/.clawdbot/credentials/whatsapp/personal",
},
biz: {
// Optional override. Default: ~/.clawdbot/credentials/whatsapp/biz
// authDir: "~/.clawdbot/credentials/whatsapp/biz",
},
},
},
}
Example: WhatsApp daily chat + Telegram deep work
Split by provider: route WhatsApp to a fast everyday agent and Telegram to an Opus agent.
{
agents: {
list: [
{
id: "chat",
name: "Everyday",
workspace: "~/clawd-chat",
model: "anthropic/claude-sonnet-4-5"
},
{
id: "opus",
name: "Deep Work",
workspace: "~/clawd-opus",
model: "anthropic/claude-opus-4-5"
}
]
},
bindings: [
{ agentId: "chat", match: { provider: "whatsapp" } },
{ agentId: "opus", match: { provider: "telegram" } }
]
}
Notes:
- If you have multiple accounts for a provider, add
accountIdto the binding (for example{ provider: "whatsapp", accountId: "personal" }). - To route a single DM/group to Opus while keeping the rest on chat, add a
match.peerbinding for that peer; peer matches always win over provider-wide rules.
Per-Agent Sandbox and Tool Configuration
Starting with v2026.1.6, each agent can have its own sandbox and tool restrictions:
{
agents: {
list: [
{
id: "personal",
workspace: "~/clawd-personal",
sandbox: {
mode: "off", // No sandbox for personal agent
},
// No tool restrictions - all tools available
},
{
id: "family",
workspace: "~/clawd-family",
sandbox: {
mode: "all", // Always sandboxed
scope: "agent", // One container per agent
docker: {
// Optional one-time setup after container creation
setupCommand: "apt-get update && apt-get install -y git curl",
},
},
tools: {
allow: ["read"], // Only read tool
deny: ["exec", "write", "edit", "apply_patch"], // Deny others
},
},
],
},
}
Benefits:
- Security isolation: Restrict tools for untrusted agents
- Resource control: Sandbox specific agents while keeping others on host
- Flexible policies: Different permissions per agent
Note: tools.elevated is global and sender-based; it is not configurable per agent.
If you need per-agent boundaries, use agents.list[].tools to deny exec.
For group targeting, use agents.list[].groupChat.mentionPatterns so @mentions map cleanly to the intended agent.
See Multi-Agent Sandbox & Tools for detailed examples.