Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI-curious readers, AI researchers, agent developers, AI infrastructure teams, meta-agent researchers, AI safety researchers, SRE / DevOps engineers, and engineering teams who want a runtime substrate for agent work that needs inspection, reversibility, and supervision -- and who can pair Shepherd with a Claude Code subscription or ANTHROPIC_API_KEY to drive the runtime (or use the Offl
Who should use it
Who should skip it
Skip shepherd-agents/shepherd if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
shepherd-agents/shepherd is tracked by RepoRadar as a programmable meta-agent runtime in the Agent Runtime / Meta-Agent Substrate section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for shepherd-agents/shepherd are workflow potential (10.0) and novelty (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. 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 shepherd-agents/shepherd 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 'low' 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
Alpha stage with APIs that may still change between releases -- pin the API in pyproject.toml + review the CHANGELOG + the alpha -> stable release roadmap before upgrading; the runtime is new (12 days between created_at 2026-06-24 and this cycle 2026-07-06) and the community is small (667★) -- treat the first evaluation cycle as a smoke test (pip install + shepherd init + shepherd doctor claude + shepherd demo write + python <task>.py) before granting a real GitRepo write permission; the GitRepo write privilege is the headline attack surface in the Permissions model -- audit the task signature and the user-supplied prompt before granting it; and prefer the read-only sp.May[sp.GitRepo.