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.
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 a agent workflow in the Agent Workflows section. It was first seen on 2026-06-28 and last updated 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 evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned craft-ai-agents/craft-agents-oss a composite score of 8.5 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
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.