How autonomous is the agent, really — will it just start sending emails on my behalf?

You control exactly how much the agent does on its own. Three modes: ask-first (it proposes every action and waits for your tap to approve), act-then-report (it acts and tells you what it did), or fully-autonomous (silent execution). You can set different modes per integration — so the agent can read your GitHub repos freely but always ask before touching Gmail. On top of that, certain actions — deleting data, sending to a new contact, financial transactions, revoking access — require your confirmation regardless of which mode you're in. There's also an emergency kill switch that halts all activity instantly.

What integrations does Sidekick actually support today?

Built-in adapters ship for Gmail, Google Calendar, Outlook and Microsoft 365 (email, calendar, OneDrive), Slack, GitHub, Linear, Notion, Telegram, Discord, and WhatsApp Business. Beyond those, Sidekick connects to the ClawHub skill ecosystem — a marketplace with 13,729+ community-built skills you can search, install, and configure directly from the dashboard. If you're coming from OpenClaw, there's a dedicated migration guide to import your existing skills and reconnect your accounts.

How does the agent remember things about me over time?

Sidekick uses a three-tier memory architecture. Working memory holds recent context so mid-conversation corrections ('actually make it Manchester') work naturally. Episodic memory stores daily summaries so the agent recalls what you worked on last week. Semantic memory uses vector search to surface long-term patterns — your communication preferences, recurring priorities, how you like to handle certain types of requests. Past conversations are searchable and resumable, and you can configure how long data is retained before it's automatically purged.

How do I know what the agent is doing in the background?

Every decision the agent makes is logged in a real-time activity feed: what it did, what triggered it, and the full reasoning chain behind it. When it's about to act, it renders an interactive card in chat showing exactly what will happen before it happens — approve, edit, or reject without leaving the conversation. You can also set rate limits per integration (for example, a cap on how many emails it can send per hour) and configure quiet hours so it queues actions rather than firing them while you're asleep.

What are the pricing tiers, and what do I lose if I stay on Free?

Free gives you three connected integrations and 50 agent actions per day, with access to community skills from ClawHub. Pro removes the integration cap, raises the action limit to 1,000 per day, and adds the ability to build and publish your own custom skills plus priority support. Enterprise is uncapped, adds SSO, a dedicated support contact, and an SLA — and includes usage-based billing for high-volume months so you're not paying for headroom you don't use. If you downgrade, features phase out gradually rather than disappearing the moment you switch.

Can I build my own skills, and how do I share them?

Yes. The custom skill builder walks you through writing natural-language instructions for what the agent should do, specifying which integrations the skill needs, and testing it in a sandbox before you turn it on. Sensitive values the skill needs — API keys, tokens — are stored encrypted at rest with AES-256-GCM and managed in a dedicated variable manager that shows exactly which skill needs which key. When a skill is ready to share, you export it as a SKILL.md file and publish it to ClawHub, where other Sidekick users can find it through semantic search.

SECURITY & PRIVACY

Your data stays yours.

Sidekick holds access to your email, calendar, and repos. That's a serious responsibility. Here's exactly what we do — and don't do — with it.

Every credential encrypted at rest. Every agent decision logged. Every action requiring confirmation before it's irreversible. Security isn't a feature here — it's the foundation.

[CREDENTIAL VAULT / ENCRYPTED]

Credentials encrypted the moment you connect

Every OAuth token and API key you hand to Sidekick is encrypted with AES-256-GCM before it reaches the database. The plaintext never persists. Automatic key rotation re-encrypts stored credentials with zero downtime, and you can trigger a manual rotation at any time from your settings page.

AES-256-GCM encryption at rest Every token and API key — never stored as plaintext
Automatic key rotation Re-encryption runs without dropping active connections
Manual rotation on demand Trigger re-encryption from your settings page anytime
Per-skill environment variables Scoped to the skills that need them — never shared globally

Sidekick agent settings — autonomy and security controls

[AGENT CONTROLS / AUDITABLE]

You control what the agent can do — and can't

Autonomous doesn't mean unaccountable. Three safety layers keep you in control regardless of how you configure the agent.

Emergency kill switch

One button halts the agent immediately — cancels pending actions, disconnects all integrations, stops the loop. Always accessible, even on mobile.

Destructive action gate

Deleting data, emailing a new contact, revoking access — these always require your explicit confirmation, even in fully-autonomous mode. No exceptions.

Sidekick approvals queue — pending agent actions awaiting confirmation

[APPROVALS / ASK-FIRST MODE]

Every pending action is reviewable before it runs

When the agent is in ask-first mode, it queues each proposed action for your review. You see exactly what it wants to do and why before a single message is sent or issue created. Approve, reject, or edit — inline, in one click.

[DECISION LOG / FULL TRANSPARENCY]

The agent's reasoning is never a black box

Every decision the agent makes is logged: what triggered it, what it chose to do, and why. The activity feed gives you a real-time audit trail you can filter by integration, action type, or date.

Sidekick activity feed — real-time agent decision log

CREDENTIAL-VAULTAES-256-GCM encryption confirmednow

KEY-ROTATIONZero-downtime re-encryption completed2m ago

KILL-SWITCHEmergency halt available — all sessionslive

APPROVAL-QUEUEPending actions held for reviewlive

DECISION-LOGReasoning chain persisted for auditnow

RATE-LIMITERPer-integration caps enforcedlive

MEMORY-TIERWorking, episodic, and semantic tiers encryptednow

[MEMORY / THREE-TIER ARCHITECTURE]

Memory built for security, not just recall

Sidekick's three-tier memory system — working, episodic, and semantic — is designed with data minimisation in mind. Each tier stores only what's necessary for its purpose, with configurable retention periods and GDPR-compliant deletion.

Working memory

Recent events held in Redis — short-lived, in-session context. Cleared automatically. Never persisted beyond its purpose.

Episodic memory

Daily summaries stored in Postgres. Configurable retention periods auto-purge old decisions. You can delete your episodic history at any time.

[GDPR / DATA RIGHTS]

Export everything. Delete everything. Your choice.

GDPR data rights are built into the product, not bolted on. Export all your data in machine-readable format, or request complete account deletion — agent decisions, memory, credentials, everything. Data retention policies auto-purge agent history after configurable periods, so you don't have to think about it.

Full data export in machine-readable format
Complete account deletion — no residual data
Configurable retention periods for agent decisions and memory
Auto-purge of old data after retention windows close

[RATE LIMITS / SPENDING CAPS]

Runaway agents don't happen here

Configurable rate limits and spending caps per integration mean a misconfigured agent can't spiral into thousands of emails or API calls. Set a daily maximum for each platform, and the agent alerts you when you're approaching the threshold — before it stops.

Sidekick analytics dashboard — usage metrics and integration activity

[FAQ / SECURITY]

Questions we get asked

Security questions? We'll answer them directly.

We'd rather over-explain our security posture than have you guess. Reach out at sf-core-org-support-sidekick@saas-factory.ai or join the waitlist and ask us there.

Email the security team

Your data stays yours.

Credentials encrypted the moment you connect