agent-safety 开源项目推荐（1,014 个）

FuRongJun-1999 /dsh-memory

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

SponsioLabs /Sponsio

Deterministic safety solutions for probabilistic AI agents

AI45Lab /OpenART

OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

GenAI-Security-Project /agent-control-standard

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

CodeAlive-AI /ai-driven-development

人工智能驱动软件开发的实践、规范和技能。18 项技能 + 1 个 Bash 安全钩子，适用于 Claude Code、Codex CLI、OpenCode、Cursor、Gemini CLI、Antigravity 以及任何支持 Agent Skills 标准的代理。

XSafeAI /XSafeClaw

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

x-zheng16 /Awesome-Embodied-AI-Safety

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System

eli-labz /Agent-Execution-Partnership

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable while it runs, and verifiable after it completes.

GenseeAI /gensee-crate

为 AI 编码代理提供运行时安全保障，具备实时强制执行、系统事件监控和长周期溯源能力。在原生 macOS 上支持 Claude Code 和 Codex。

OraclesTech /guardian-sdk

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

kajogo777 /the-agent-sandbox-taxonomy

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

SteelUnion /dsh-confirm-gate

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.

agentrust-io /awesome-ai-governance

🛡️ A curated list of tools, frameworks, standards, and resources for AI agent governance, safety, and compliance

shiftynick /jev-axi

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

jacksonjp0311-gif /Perci

Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and a Temporal Router. Local MCP server + CLI in Rust. Preview.

hussainn7 /plip-oss

Open-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.

bridge-mind /BridgeWard

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

CaydenChik /doover

Undo for AI agent shell commands. Snapshots files before Claude Code runs destructive bash (rm -rf, git reset, rsync), so agent mistakes are reversible, even for files git never tracked.

ali-ulu /huqan

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a claim, memory write, or action is trusted.

i1see1you /VirbiusAgent

Open-source AI Agent security platform — prompt injection defense, MCP tool-call guardrails, eBPF runtime observability. Four-tier Edge→Gateway→Kernel→Cloud architecture.