Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).
-
Updated
Aug 26, 2026 - Python
Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).
Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply
Declarative coordination for agent skills — multi-platform, deny-by-default, local-first. One manifest. One command. Only what you declared.
Sanitized starter kit for Hermes Agent memory, skill, cron, and Kanban governance
The skillsvault agent skill. Connect your agent to your organisation's skillsvault control plane: install the org-approved skills, keep them current, and check a skill is allowed before use.
Governed security-supply-chain framework for AI agents: 388 pinned skills, 39 commands and 33 personas, each behind a reviewed adapter and a CI-enforced authorization gate.
AI Agent 技能的生命周期治理与评估实验室:机器可读治理契约 + 受守卫晋升/回滚 + 跨会话观察
Local-first AI skill library governance and read-only ZIP preflight: inspect structure, choose minimal workflows, track evidence and keep changes reversible.
Skill governance for AI agents: one SKILL.md registry, a contract that gates what enters it, provenance with a hash, declared usage per harness, seeds that say what is always recommended, and links into Claude Code, Codex, Cursor, Hermes, Reasonix and any harness. No copies, no drift.
Local SkillOps inventory and governance workbench for Claude Code, Codex, OpenCode, Qoder, WorkBuddy, and other AI agents.
Proactive routing and governance layer for high-cost agent skills
To associate your repository with the skill-governance topic, visit your repo's landing page and select "manage topics."