25 projects
agentmesh_platform
Public Preview — The Secure Nervous System for Cloud-Native Agent Ecosystems - Identity, Trust, Reward, Governance
agent_governance_toolkit
Public Preview — Unified installer and runtime policy enforcement for the Agent Governance Toolkit
agent_sre
Public Preview — Reliability Engineering for AI Agent Systems
agentmesh_lightning
Public Preview — Agent-Lightning RL integration for the Agent Governance Toolkit: governed training with policy enforcement
agentmesh_runtime
Public Preview — AgentMesh Runtime: Execution supervisor for multi-agent sessions with privilege rings, saga orchestration, and audit trails
agent_os_kernel
Public Preview — A kernel architecture for governing autonomous AI agents with Nexus Trust Exchange
agent_hypervisor
Public Preview — Agent Hypervisor: Runtime supervisor for multi-agent Shared Sessions with Execution Rings, Joint Liability, Saga Orchestration, and hash-chained audit trails
ai-agent-compliance
Unified installer and compliance documentation for the Agent Governance Toolkit
ai-agent-governance
The complete AI agent governance stack - kernel, trust mesh, runtime supervisor, and reliability engineering
emk
Community Edition — Episodic Memory Kernel for AI agent experience storage
openai-agents-trust
Trust & governance layer for OpenAI Agents SDK — policy enforcement, trust-gated handoffs, and Merkle audit trails
langgraph-trust
Trust-gated checkpoint nodes for LangGraph — cryptographic identity, policy enforcement, and trust-aware routing for multi-agent graphs
nexus-trust-exchange
Agent Trust Exchange - viral registry and communication board for AI agents (RESEARCH PROTOTYPE)
agent-control-plane
Layer 3: The Framework - A deterministic kernel for zero-violation governance in agentic AI systems with POSIX-style signals, VFS, and kernel/user space separation
langchain-agentmesh
AgentMesh trust layer integration for LangChain - cryptographic identity and trust-gated tool execution
mcp-kernel-server
MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust
agent-os-observability
Production observability for Agent OS - OpenTelemetry traces, Prometheus metrics, Grafana dashboards
mute-agent
Layer 5 Reference Implementation - Listener Agent with Dynamic Semantic Handshake Protocol
scak
Self-Correcting Agent Kernel: A specialized extension for Control Plane that implements Laziness Detection and Self-Correction loops using CMVK
agent-tool-registry
A decentralized marketplace for agent capabilities - The Hands of AI Agents
amb-core
A lightweight, broker-agnostic message bus designed specifically for AI Agents
inter-agent-trust-protocol
Inter-Agent Trust Protocol (IATP) - The Envoy for AI Agents. A sidecar architecture with typed IPC pipes for preventing cascading hallucinations in autonomous agent networks.
caas-core
A pure, logic-only library for routing context, handling RAG fallacies, and managing context windows. Layer 1 Primitive - no agent dependencies.
cmvk
Mathematical and adversarial verification library for calculating drift/hallucination scores between outputs
agent-primitives
Shared primitive data models for Agent OS - failure types, severity levels, and base structures
