# Click vs Jules (slim)

> Click scores 48.6 (D) to Jules's 47 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/click-agents-vs-jules.md (~6,700 tokens) · this version ~930 tokens · JSON https://www.anchorterminal.com/compare/click-agents-vs-jules.json · canonical https://www.anchorterminal.com/compare/click-agents-vs-jules
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Click scores 48.6 (D) on agent readiness against Jules's 47 (D), and leads in 4 of 7 scored categories. Jules leads on security & auth, payments & pricing and transparency & trust. Both do agent harnesses.

- Click: D 48.6, rank #1202 of 1557 · https://www.anchorterminal.com/tools/click-agents.min.md
- Jules: D 47, rank #1240 of 1557 · https://www.anchorterminal.com/tools/jules.min.md
- Click, good for Product teams that want to embed an agent per customer, ticket or document without running the loop, sandbox or browser themselves, with any model. Ahead on Reliability, 35 against 13; Schema & documentation, 84 against 76; Agent ergonomics, 79 against 64; Maintenance & community, 25 against 18. Also A hosted endpoint, with nothing to install.
- Jules, good for Nobody starting new work, since Jules turns read-only after 11 November 2026 and ends on 31 December 2026. Ahead on Security & auth, 57 against 41; Payments & pricing, 45 against 15; Transparency & trust, 51 against 44. Also Runs on your own machine.

| Category | Click | Jules |
| --- | --- | --- |
| Reliability (16%) | 35 | 13 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 84 | 76 |
| Agent ergonomics (13%) | 79 | 64 |
| Security & auth (14%) | 41 | 57 |
| Payments & pricing (10%) | 15 | 45 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 25 | 18 |
| Transparency & trust (7%) | 44 | 51 |

| Fact (where they differ) | Click | Jules |
| --- | --- | --- |
| Kind | HTTP API | Agent harness |
| Vendor | Click AI Labs, Inc. | Google |
| Hosted endpoint | `https://api.useclick.ai/v1` | no (local only) |
| Transports | HTTP, Streamable HTTP | HTTP, stdio |
| Licence | Proprietary hosted service under Click's Terms of Service, based on the Common Paper Cloud Service Agreement 2.1 | Proprietary service under the Google Terms of Service. The TypeScript SDK is Apache-2.0; the CLI binary is closed |
| Tools exposed | 23 | 8 |
| Read-only variant documented | no | yes |
| Last release | 2026-10-19 | 2026-03-09 |
| Terms last updated | 2026-10-12 | 2026-07-30 |
| Privacy policy last updated | 2026-10-12 | 2026-10-01 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | yes |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Payments & pricing, Jules +30: Click 15 (No x402, MPP or L402. The only 402 is `card_verification_required` (0).); Jules 45 (Published rubric.)
- Reliability, Click +22: Click 35 (Hosted lines, for the HTTP API.); Jules 13 (Hosted reading.)
- Security & auth, Jules +16: Click 41 (Platform API keys are revocable, but each has full access to its tenant, including key management.); Jules 57 (Hosted reading.)
- Agent ergonomics, Click +15: Click 79 (Entries can be read by `min_entry_id` and `max_entry_id`, `get_state` returns one snapshot, and lists take `limit`, so responses stay small (20 of 25).); Jules 64 (API and MCP reading, per the 18 October check.)
- Schema & documentation, Click +8: Click 84 (A public OpenAPI 3.2 document at useclick.ai/reference/openapi.yaml, API version 2026-10-19, rendered in full in llms-full.txt with 49 operations (25).); Jules 76 (API reading.)
- Maintenance & community, Click +7: Click 25 (Closed service with no dated changelog.); Jules 18 (Closed service.)
