iflytek/skillhub
SkillHub is a self-hosted, open-source agent skill registry for enterprises to publish, version, discover, and govern reusable skill packages for AI agents with RBAC and audit logs.
Awesome Infra for AI › AI Governance & Compliance
semantica-agi/semantica
Semantica addresses the lack of auditability, explainability, and traceability in current AI agent systems by providing a 'Context and Accountability Layer'. It operates alongside LLMs and vector stores, augmenting them with structured intelligence, causal reasoning, and a complete audit trail for every agent decision. Key capabilities include Context Graphs, which are structured, queryable graphs of agent knowledge, decisions, and reasoning; Decision Intelligence, making every decision a first-class, traceable, and causally linked object; and AI Governance, featuring built-in policy enforcement, SHACL constraints, and conflict detection. The framework offers full auditability with W3C PROV-O provenance, allowing export to various formats, and incorporates reasoning engines like forward chaining, Rete network, Datalog, and SPARQL for explainable paths. Unlike traditional RAG or plain LLM memory, Semantica offers graph traversal-based recall, rich decision history, full provenance, explicit reasoning, conflict detection, time-travel capabilities through snapshots, and comprehensive compliance export features. It is designed for AI agents, GraphRAG systems, enterprise knowledge intelligence, and temporal reasoning applications, ensuring deterministic operation without requiring an LLM for its core reasoning and KG construction.
https://github.com/semantica-agi/semantica
Also in AI Governance & Compliance
kitops-ml/kitops
KitOps is a CNCF open-source tool for packaging, versioning, and securely sharing AI/ML models, datasets, code, and configuration into an OCI Artifact for simplified deployment and governance.
verifywise-ai/verifywise
VerifyWise is an AI governance platform providing tools for LLM evaluation, risk management, and compliance with AI regulations including the EU AI Act, ISO 42001, and NIST AI RMF.
Floe-Labs/floe-guard
In-process spend meter and budget gate for AI agents that hard-stops the next model call, voice turn or paid tool invocation before it crosses a configured cost ceiling.