Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Tests narrow text-to-CAD to a measurable benchmark instead of open-ended generation, and the multi-agent split lets each stage be tuned independently. STEP output is directly usable in build123d, CadQuery, OpenCascade, and 3D-printing slicers.
Where this stands now
pan-chera/multi-agent-cad ranks #237 of 1042 tracked Developer Tools items by composite score (5.7 against a section median of 4.9). The section currently carries 811 Bronze, 127 Silver, 103 Gold, 1 Low Signal. RepoRadar has retained observations for this record since 2026-08-04 (55 days in the current window). Signal extremes versus the section: novelty at the 77th percentile.
Who should use it
Who should skip it
Consider pan-chera/multi-agent-cad lower priority if you already have a working solution in this category.
About this signal
pan-chera/multi-agent-cad is tracked by RepoRadar as a framework in the Developer Tools section. First seen 2026-08-04; the source record was last checked on 2026-08-21. The current verdict is 'try now' with a Silver tier and moderate setup difficulty. pan-chera/multi-agent-cad leads on open-source/build quality (8.4) and evidence quality (7.2); its lowest signal is momentum (3.5), so factor that in before investing setup time. This page summarizes the evidence RepoRadar captured from https://github.com/Pan-Chera/Multi-Agent-CAD.
How this item is evaluated
The pan-chera/multi-agent-cad record combines a 5.7/10 composite score with separate popularity (0.0), risk (none), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
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
Generates and executes Python CAD code locally (build123d/cadpy). The Autonomous Skill Loop may iterate autonomously until a gate is met; caution: not_hands_on_tested; caution: new_or_experimental; caution: self_reported_benchmarks.