agent-governance 开源项目推荐（1,054 个）

omnigent-ai /omnigent

Omnigent 是一个开源 AI 智能体框架和元框架：可编排 Claude Code、Codex、Cursor、Pi 及自定义智能体——无需重写即可更换运行框架，强制执行策略与沙箱隔离，并可从任意设备实时协作。

CopilotKit /OpenBot

开源 AI 同事，每位都拥有自己的计算机：浏览器、文件和工具；每个操作在发生前就已确定，并在发生后被记录。可接入任意 AG-UI 智能体。

trustgraph-ai /trustgraph

Write context once. Run agents anywhere. Own your data and the models.

sipyourdrink-ltd /bernstein

用于CLI编码代理（Claude Code、Codex、Gemini CLI、+40 more）的审计级多代理编排。HMAC链式审计日志、签署的代理卡、每个工件的血统、空隙部署。你的合规团队会批准的协调者。https://bernstein.run

HelpCode-ai /anythingmcp

企业 Agent Harness 与 MCP 网关：将 API、数据库、文件服务器和 600+ 连接器（SAP、Odoo、Etsy……）连接到 Claude、ChatGPT、Microsoft Copilot 和你的 Agent。内置记忆、技能、知识图谱、SSO/RBAC、审计日志与治理。你的 AI 公司大脑。

yan5xu /codexloom

Turn Codex threads into an organization of long-lived domain agents.

halofyai /halofy

Halofy 是面向组织内 AI 代理的开放访问与治理层。身份、策略、来源、审计和签名擦除。

ucsandman /DashClaw

面向无人值守 AI 智能体的远程审批、策略检查和执行证据。

infinri /Writ

Claude Code 用于 AI 编码代理的框架。混合-RAG图书管理员在0.59毫秒的第95页中选择相关规则（BM25 + 向量 + 图遍历）;进程守护者会写入直到计划+测试批准。276条规则 / 30条强制性，跨12个领域，6个跨语言分析器。Neo4j + Tantivy + hnswlib + ONNX。

KimYx0207 /Meta_Kim

Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.

dengyier /OpenWorkProof

面向 AI 智能体工作合约与可验证执行的开放协议——多智能体系统的授权、证据与验收。

markus-global /markus

不是另一个代理框架——一个为人工智能劳动力设计的操作系统。自主代理协调、跨会话记忆、相互审查工作，并在你睡觉时交付成果。一个命令。零依赖关系。用手机管理你的AI公司。

traccia-ai /traccia-py

OpenTelemetry-native SDK for AI agent observability, tracing, evaluation, debugging, governance, and runtime policy enforcement. Framework-agnostic and built for OpenAI Agents, LangGraph, CrewAI, and LLM applications in production.

lsaint /aikito

Your durable workspace across AI agents.

KeyArgo /custodian-kernel

Kernel-enforced authority and spend platform for AI agents

faramesh /faramesh-core

Governance-as-Code for AI agents. Declarative constraints with deterministic enforcement. Provisioning Identity, Tool-based rules, Brokering Credentials & Ensuring safe deployment

Towow-ai /Flowness

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

ThreeMoonsLab /agents-shipgate

The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.

elliot35 /deterministic-agent-control-protocol

Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

imran-siddique /agent-os

[DEPRECATED] Moved to microsoft/agent-governance-toolkit