Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-09 · source-backed
Accio open-sourced it August 2, now 1,042 stars: 107 tasks across 14 containerized mock services replicating Alibaba, Shopify, and FreightOS (GitHub). Task mix is 53 CLI, 28 browser, 16 file ops, 10 API/MCP, split 65 text-only / 20 browser-text / 22 vision-requiring. Twelve model families on two harnesses. Claude Opus 5 led both at 66/107 (61.7%) on the Accio harness and 60/107 (56.1%) on OpenClaw. What separates this from most agent benchmarks is that tasks require mutating state, not answering questions. The 5.6-point harness gap on identical models is its own finding.
Each link below shares sources, entities, or timing with this story.
Shopify uses Claude Opus / Shared entities / Same source / Shared topic / Earlier coverage
Linked by a graph relationship (Shopify uses Claude Opus); both cover Accio, August, Claude Opus, CLI; cite the same source (GitHub).
OpenClaw benchmarked against RealReplicaBench / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (OpenClaw benchmarked against RealReplicaBench); both cover Accio, Alibaba, GitHub, OpenClaw; reported by the same outlet (github.com).
Linked by a graph relationship (OpenClaw benchmarked against RealReplicaBench); both cover August, CLI, MCP, OpenClaw; reported by the same outlet (github.com).
Cursor supports Claude Opus / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Cursor supports Claude Opus); both cover August, CLI, GitHub, MCP; reported by the same outlet (github.com).
Cursor supports Claude Opus / Shared entities / Same source domain / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Cursor supports Claude Opus); both cover GitHub, MCP, OpenClaw; reported by the same outlet (github.com).
Cursor supports Claude Opus / Shared entities / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (Cursor supports Claude Opus); both cover CLI, GitHub, OpenClaw; reported by the same outlet (github.com).
Linked by a graph relationship (Cursor supports Claude Opus); both cover GitHub, MCP, Task; reported by the same outlet (github.com).
Shopify uses Claude Opus / Shared entities / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Shopify uses Claude Opus); both cover August, MCP, Shopify; overlapping topics (agent, claude, harness).