# boxes.dev vs Qwen Code (slim)

> Qwen Code scores 72.4 (BB) to boxes.dev's 53.2 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.md (~7,250 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code.json · canonical https://www.anchorterminal.com/compare/boxes-dev-vs-qwen-code
- 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)

Qwen Code scores 72.4 (BB) on agent readiness against boxes.dev's 53.2 (D), and leads in 6 of 7 scored categories. boxes.dev leads on security & auth. Both do agent harnesses.

- boxes.dev: D 53.2, rank #1055 of 1557 · https://www.anchorterminal.com/tools/boxes-dev.min.md
- Qwen Code: BB 72.4, rank #220 of 1557 · https://www.anchorterminal.com/tools/qwen-code.min.md
- boxes.dev, good for Developers who want Claude Code or Codex running on cloud copies of their dev environment, started from Slack, Linear, a schedule, an API call or another assistant. Ahead on Security & auth, 69 against 53. Also A hosted endpoint, with nothing to install; No incidents deducted, where Qwen Code loses 4 points for them.
- Qwen Code, good for Developers and CI jobs that want an open-source harness tied to no single model vendor, with run budgets and SDKs. Ahead on Reliability, 69 against 32; Schema & documentation, 91 against 57; Agent ergonomics, 85 against 60; Payments & pricing, 90 against 50; Maintenance & community, 88 against 48; Transparency & trust, 66 against 60. Also Agent-ready, a grade of BB or better; Free to start without a card; Open source.

| Category | boxes.dev | Qwen Code |
| --- | --- | --- |
| Reliability (16%) | 32 | 69 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 57 | 91 |
| Agent ergonomics (13%) | 60 | 85 |
| Security & auth (14%) | 69 | 53 |
| Payments & pricing (10%) | 50 | 90 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 48 | 88 |
| Transparency & trust (7%) | 60 | 66 |

| Fact (where they differ) | boxes.dev | Qwen Code |
| --- | --- | --- |
| Kind | MCP server | Agent harness |
| Vendor | Boxes, Inc. | Alibaba (Qwen team) |
| Hosted endpoint | `https://api.boxes.dev/mcp` | no (local only) |
| Transports | Streamable HTTP, HTTP |  |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Free |
| Licence | Proprietary. The service runs under the Common Paper Cloud Service Agreement 2.1, and the `@boxes-dev/cli` package is marked UNLICENSED | Apache-2.0 |
| Last release | 2026-11-17 | 2026-11-01 |
| Terms last updated | 2026-10-20 | 2026-10-01 |
| Privacy policy last updated | 2026-10-21 | 2026-10-01 |
| Popularity | none | 28k stars, 105k npm/wk |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Payments & pricing, Qwen Code +40: boxes.dev 50 (No x402, MPP or L402 (0).); Qwen Code 90 (Self-hosted rule.)
- Maintenance & community, Qwen Code +40: boxes.dev 48 (Closed service.); Qwen Code 88 (0.26.5 on 1 November 2026 (30).)
- Reliability, Qwen Code +37: boxes.dev 32 (Hosted reading, for the remote MCP server at api.boxes.dev/mcp and the automation run endpoints.); Qwen Code 69 (Local-package reading.)
- Schema & documentation, Qwen Code +34: boxes.dev 57 (No OpenAPI document, and the MCP tool list could not be read because the endpoint answers 401 before `initialize` without an OAuth token.); Qwen Code 91 (Framework reading.)
- Agent ergonomics, Qwen Code +25: boxes.dev 60 (The MCP tool count is unknown.); Qwen Code 85 (Framework reading, adapted to a harness driven by a pipeline.)
- Security & auth, boxes.dev +16: boxes.dev 69 (OAuth for the MCP server, with protected-resource metadata naming mcp.boxes.dev and four scopes (`threads:read`, `threads:write`, `events:subscribe`…); Qwen Code 53 (Framework reading (telemetry defaults, approvals, guardrails, sandboxing), five lines.)
