Tilde vs Arcade

The short answer

Arcade and Tilde both sit between agents and the systems they act on. Arcade calls itself an actions runtime: it handles OAuth, manages user tokens and applies policy to every tool call, with MCP gateways to combine tools.

Tilde does the tool and credential work too, and goes further along the path. It screens agent inputs and outputs, asks people to approve sensitive actions, and connects agents to users through channels and voice.

At a glance

Where Arcade is strong

Arcade publishes one of the largest catalogs of agent-ready tools, and its per-user OAuth lets an agent act on behalf of each person with their own permissions. MCP gateways let you pick exactly which tools each agent sees.

It has a SOC 2 Type 2 report, audit logs on by default, and deployment options up to fully air-gapped. Its contextual access hooks give security teams a place to plug in their own checks.

Where Tilde is different

Arcade gives you hooks to build guardrails. Tilde ships them, and covers the parts of an agent's life that sit outside the tool call.

• Integrations without the plumbing. Create MCP tool servers from our catalog of SaaS providers, proxy an existing MCP server, or forward requests to your own API.
• Credentials you don't have to build. Tilde handles OAuth, API keys and custom authentication, including encryption and rotation.
• Security middleware on every agent. Tilde blocks jailbreak attempts and redacts personal information (PII) in agent inputs and outputs.
• Access scoped to the work. Workspaces and grants limit which people and agents can reach which resources, with single sign-on through your OIDC provider.
• Control on sensitive actions. Govern checks policy, asks a person to approve and records the decision before an action runs.
• Channels in a single click. Add WhatsApp, Slack, Discord, Telegram or GitHub to an agent without writing an adapter. ChatKit adds message history, sessions, webhooks, schedules and agent-to-agent delegation.
• Secrets kept out of the model. The secure browser signs in to websites with injected credentials the agent never sees.
• Voice when you need it. Build realtime voice agents on the same tools and permissions.
• One inventory. The Registry records every agent, who owns it and who can use it, whichever framework built it.
• Runs where your data lives. Use Tilde cloud, or deploy Tilde on-prem in your own infrastructure. Embedded engineers can help you set it up.

Using Arcade and Tilde together

If you already run Arcade gateways, Tilde can proxy upstream MCP servers, so those tools can sit behind Tilde's security middleware, permissions and approvals, and reach users through Tilde channels.

Otherwise, compare the tools you need, then how much of the control layer you want to build and host yourself.

flowchart TB
  People["People on Slack, WhatsApp or voice"] --> Channels
  subgraph Tilde["Tilde"]
    Channels["Channels"]
    Guard["Security middleware: jailbreaks and PII"]
    Govern["IAM and human approvals"]
    Tools["MCP tools and managed credentials"]
  end
  Channels --> Agent["Your agent"]
  Agent --> Guard
  Guard --> Govern
  Govern --> Tools
  Tools --> Systems["SaaS APIs and your systems"]

Which should you choose?

• Choose Arcade if you want a large tool catalog with per-user authorisation, and your team is happy to build and host its own guardrail checks.
• Choose Tilde if you want security middleware built in, plus approvals, channels, voice and a secure browser, in Tilde cloud or on-prem.
• Talk to us if you're weighing both. Talk to our team if you'd like help planning it.