Arcade vs Smithery
Arcade scores higher on the AgentReady, 61/100 against 56/100. They differ on 7 of the 41 signals. Which ones decides whether an agent can adopt them without a person watching.
What each one is
Arcade. The runtime between your agents and every system they need to reach.
Smithery. Smithery connects AI agents to a growing catalog of tools and integrations, handling auth, credentials, and sessions.
Where Arcade is ahead
Arcade passes clear canonical domain and llms-full.txt / full agent docs, and Smithery does not. That is discover, whether an agent can find the product at all without being told it exists.
It also holds adopt: self-service signup, fast time to first request and cli available. Smithery misses those.
Where Smithery is ahead
Smithery passes clear product positioning, and Arcade does not. That is discover, whether an agent can find the product at all without being told it exists.
It also holds understand: limits / constraints documented. Arcade misses it.
What neither does
Both fail structured api reference, openapi / spec quality, pricing understandable, request examples provided, response examples provided, errors and status codes documented, no mandatory sales call, programmatic credential creation, free trial or free allowance, structured, predictable output, machine-readable errors, retry behavior documented, idempotency support, rate-limit behavior predictable. If your agent needs any of those, you will be building it yourself either way.
Score, pillar by pillar
The AgentReady splits into four pillars, scored separately, because a product can be easy to find and still impossible to adopt.
Discover. Both sit at 87/100 here. Arcade misses clear product positioning; Smithery misses clear canonical domain, llms-full.txt / full agent docs.
Understand. Smithery leads 31 to 23. Arcade misses structured api reference, openapi / spec quality, pricing understandable, request examples provided, response examples provided, errors and status codes documented, limits / constraints documented; Smithery misses structured api reference, openapi / spec quality, pricing understandable, request examples provided, response examples provided, errors and status codes documented.
Adopt is whether an agent can get a key and make its first successful call without a human in the loop. Arcade leads 76 to 50. Arcade misses no mandatory sales call, programmatic credential creation, free trial or free allowance; Smithery misses self-service signup, no mandatory sales call, programmatic credential creation, free trial or free allowance, fast time to first request, cli available.
Operate. Both sit at 56/100 here. Arcade misses structured, predictable output, machine-readable errors, retry behavior documented, idempotency support, rate-limit behavior predictable; Smithery misses structured, predictable output, machine-readable errors, retry behavior documented, idempotency support, rate-limit behavior predictable.
Pricing
Arcade does not publish a machine-readable starting price. Smithery does not publish one.
Signal by signal
| Signal | Arcade | Smithery |
|---|---|---|
| AgentReady | 61 | 56 |
| Discovery | 87 | 87 |
| Understanding | 23 | 31 |
| Adoption | 76 | 50 |
| Operability | 56 | 56 |
| Public API | Yes | Yes |
| MCP server | Yes | Yes |
| OpenAPI spec | Unknown | Unknown |
| CLI | Yes | Unknown |
| llms.txt | Yes | Yes |
| Self-serve signup | Yes | Unknown |
| Free tier | Unknown | Unknown |
Which to pick
Arcade clears more of the signals an agent needs, so it is the safer default for unattended use. Full profiles: Arcade and Smithery. Alternatives to each: Arcade, Smithery.
An agent can fetch this as data: POST /v1/compare {"slugs": ["arcade", "smithery"]}