audit-logging

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

Supercharge AI Agents, Safely

Production-grade PostgreSQL extension to execute arbitrary SQL in background worker processes — with async execution, autonomous transactions, cookie-protected handles, cancellation, progress reporting, and observability.

Secure agents in seconds with permissions enforced at runtime.

Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases.

Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain memory, LangSmith traces, NemoClaw security, OpenTelemetry, and 20+ LLM providers.

Self-hosted SSH/RDP access gateway with PAM workflows — reverse-tunnel agents, session recording, JIT approvals, and ReBAC. A lighter self-hosted alternative to the big zero-trust access platforms.

Runtime-agnostic Kubernetes governance for AI agents: gVisor isolation, egress policy, cost controls, and offline audit verification primitives.

Framework for Unified Flaw & Fault Auditing The ultimate AWS Cloud Security Audit Framework that makes security auditing so easy, you can do it even when you're sleepy!

Secure mcp infrastructure to audit and control every data access by AI agents with minimal efforts

Audit logs service

Portable Audit eXporter (PAX) Solution: Enterprise-grade tools for Microsoft 365 audit logs analysis. Export and process Copilot and M365 apps usage data from multiple audit log sources.

Audit logging plugin for Jenkins based on Apache Log4j Audit

Self-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.

An adversarially benchmarked reference implementation for pre-action AI agent authorization. Provenance-based gating for LLM agent tool calls: deny-by-default permissions, parameter lineage, signed receipts, audit logging.

Secure every action your AI agents take (Claude Code, Codex, MCP). Blocks secret access, gates risky commands, and enforces allow/deny/approval before actions run.

Self-hostable operations console for governed AI agents. Contract management, HITL approvals, audit feeds, fleet monitoring.

CDS plugin providing integration to the SAP Audit Log service as well as out-of-the-box personal data-related audit logging based on annotations.

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.