Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for builders who want a less terminal-heavy way to operate coding and knowledge-work agents while still being able to connect local tools, MCP servers, and external services.
Where this stands now
craft-ai-agents/craft-agents-oss ranks #3 of 5 tracked Agent Workflows items by composite score (8.5 against a section median of 8.5). The section currently carries 3 Gold, 2 Silver. RepoRadar has retained observations for this record since 2026-06-28 (104 days in the current window).
Who should use it
Who should skip it
Skip craft-ai-agents/craft-agents-oss unless the captured evidence suggests it solves a problem you are actively working on.
About this signal
craft-ai-agents/craft-agents-oss is tracked by RepoRadar as an agent project in the Agent Workflows section. First seen 2026-06-28; the source record was last checked on 2026-06-28. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Across RepoRadar's eight signals, craft-ai-agents/craft-agents-oss is strongest on workflow potential (10.0) and momentum (9.0) and weakest on setup ease (6.4) — a profile worth weighing against your own priorities. 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 craft-ai-agents/craft-agents-oss record combines a 8.5/10 composite score with separate popularity (1.0), risk (conditional), 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
Craft Agents can wire credentials, databases, and local MCP subprocesses into one workspace, so first evaluation should use test accounts and non-production data sources; The one-line install and agent-driven connector flow reduce setup friction, but operators still need to review what permissions and secrets the workspace is allowed to touch.