AgentWeb vs SandBase

AgentWeb 20

Read as a closed hosted service. No dated API or server release or changelog was found (/changelog answers 404 on 4 November 2026). The terms (7 October 2026), privacy policy (14 October) and llms.txt task guides (October) carry recent dates, per the 23 October check, but none records an API or server change, and a closed service's recency is read from its last API change, so they don't count (0 of 30). The official MCP registry lists us.agentweb/agentweb 0.9.0, published 26 October 2026, the same version the OpenAPI file carried on 23 October, so a listing of an existing version that doesn't set recency. One dated entry in the 90 days from 6 August, fewer than three (0). Support is by email with a promised 24-hour answer for security reviews, untested, and there's no community channel or public issue tracker (5 of 25). Listed in the official MCP registry under us.agentweb, a domain namespace matching agentweb.us (15). No public repository, CI or package to judge (0). 0+0+5+15+0 = 20.

SandBase 68

Read for a hosted service with an open CLI and SDKs. sandbaseai/cli tagged v0.3.9 on 7 November 2026, npm @sandbaseai/cli 0.3.8 was published on 25 October, and the catalogue repository refreshed on 8 November (30). Tags v0.1.14 to v0.1.17 on 15 and 19 August, v0.3.0 to v0.3.6 on 11 and 12 October, v0.3.8 on 24 October and v0.3.9 on 7 November (20). The platform is closed and GitHub's API refused the graders, so issue queues are unread and the 0 to 15 scale for closed services applies. No public changelog for the API or MCP server, support by GitHub Discussions, issue forms and Discord (untested), and every merged pull request came from a sandbaseai branch, with commits from two people under three account names. Paid earned 5 with a support channel and no changelog, and Monid 6 with merged outside pull requests (5 of 15). The official MCP registry couldn't be read (the fetch needed an approval that didn't come), so presence there scores absent although server.json declares io.github.sandbaseai/cli. Official SDKs in Python, TypeScript and Go exist only in the GitHub repository at 0.1.0, a week old, and the TypeScript README says to copy the file until the npm package is published (5 of 15). CI runs lint, tests, a build and a package audit that rejects lifecycle scripts, with a lockfile and three runtime dependencies, and npm publishing is configured with provenance. CI results weren't read (8 of 10). 30+20+5+5+8 = 68.

AgentWeb 30

Graded with the hosted lines, on the remote MCP server and REST runtime. The provenance names AgentWeb's own status page at /status. The page is drawn by script, and the 23 October reading of its four components and 14 days of uptime came only from /api/status, the page's data feed, which this benchmark doesn't use. It is struck, and nothing is readable today (0 for the status page, 5 for the incident record, the no-readable-history score). No rate limit is published with numbers; the only figure is an example error string in the OpenAPI file, "Max 60 requests per hour", re-read on 4 November 2026 (5 of 15, a partial kept). The streaming docs say rate-limited responses carry Retry-After, and REST execute takes an Idempotency-Key so a retry is charged once (15). The Enterprise plan lists a performance SLA with no figure or text; a listed SLA nobody could read gives 0 (0). Nothing is labelled beta, but the API is 0.9.0 (5 of 10, a partial kept). 0+5+5+15+0+5 = 30.

SandBase 63

Hosted lines, graded on the HTTP API and the remote MCP server at api.sandbase.ai/v1/mcp, the surfaces an agent calls. status.sandbase.ai is a live Better Stack page with a 90-day view of the website, the API, the docs and the blog, and no component for the MCP path or sandbox.sandbase.ai. Monid earned 15 for a live Better Stack page that didn't monitor its MCP host (15 of 20). Read on 8 November 2026, it showed all services operational, the API at 99.957 per cent over 30 days and 99.983 per cent over 90, and 'No incidents reported' for September, October and November 2026. That is under 20 minutes of API downtime in the last 30 days and no outage of an hour, so minor incidents at most (20). The rate-limits page says requests a minute are assigned per organisation over a one-minute sliding window, shared by its keys, with a video concurrency limit, and publishes no numbers. Paid and Monid earned 7 for limits described without numbers (7 of 15). A 429 carries {"error":"organization rate limit exceeded"}, Retry-After is 'not guaranteed' and honoured when present, and the docs give exponential backoff with jitter and say not to retry a state-changing request without documented idempotency. Idempotency-Key is taken on Agents writes, session events and cancel, not on POST /v1/run, which spends money. Monid earned 11 on the same pattern (11 of 15). No SLA, and the terms promise no uptime, response time or availability (0). No beta or preview label on the API or the MCP server (10). 15+20+7+11+0+10 = 63.