audit-logging 开源项目推荐（630 个）

ThinkWatchProject /ThinkWatch

Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.

sandbaseai /sandbase-harness

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

open-gitagent /clawless

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

smart-mcp-proxy /mcpproxy-go

Supercharge AI Agents, Safely

vibhorkum /pg_background

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.

kontext-security /kontext

Runtime security for AI agents: discover agents, map their permissions, and enforce what they can do.

SleuthCo /clawshield-public

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.

Clawdlinux /agentic-operator-core

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

CES-Ltd /TitanX

企业AI代理编排平台——安全、可观察、可配置。多代理团队，配备IAM策略、n8n工作流程、LangChain内存、LangSmith追踪、NemoClaw安全、OpenTelemetry和20+大型语言模型提供商。

orion-belt-dev /orion-belt

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.

Masriyan /FuFuFaFa

统一缺陷与故障审计框架 终极的AWS云安全审计框架，使安全审计变得如此简单，即使你昏昏欲睡也能完成！

boxyhq /hermes

Audit logs service

microsoft /PAX

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.

altrace-dev-role /rashomon

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flags when the agent's summary says all tests pass but something failed. Open-source AI agent verification, hallucination detection, and audit tool. Local-only, no telemetry.

deltawi /deltallm

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

jenkinsci /audit-log-plugin

Audit logging plugin for Jenkins based on Apache Log4j Audit

safe-agentic-world /nomos

Deny-wins policy hook for Claude Code and Codex. Checks every shell, file, and fetch call against rules you keep in Git, holds under --dangerously-skip-permissions, refuses commands it cannot parse, and keeps a hash-linked audit log.

webpro255 /agentlock

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.

edictum-ai /edictum-console

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

openparallax /openparallax

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