Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
It tests whether a general VLM, wired into a control loop, can substitute for task-specific robot policies. That question decides how much robotics work becomes a prompting problem.
Where this stands now
Show Harness: a VLM agent that plays robots ranks #1035 of 1451 tracked Radar items by composite score (7.0 against a section median of 7.8). The section currently carries 643 Gold, 443 Silver, 365 Bronze. RepoRadar has retained observations for this record since 2026-09-12 (1 days in the current window). Signal extremes versus the section: novelty at the 83th percentile.
Who should use it
Who should skip it
Pass on Show Harness: a VLM agent that plays robots if you need something non-technical and turnkey rather than a tool that requires comfort with CLI, dependencies, or system configuration.
About this signal
Show Harness: a VLM agent that plays robots is tracked by RepoRadar as a code repository in the Radar section. First seen 2026-09-12; the source record was last checked on 2026-09-12. The current verdict is 'watch' with a Silver tier and Hard setup difficulty. Show Harness: a VLM agent that plays robots leads on novelty (8.5) and open-source/build quality (8.4); its lowest signal is setup ease (4.2), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The Show Harness: a VLM agent that plays robots record combines a 7.0/10 composite score with separate popularity (100.0), risk (none), and setup (Hard) signals. See the scoring methodology for the current weights and evidence definitions.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
No inherent user-impacting risk: research harness and evaluation code.