agent-safety repositories
Trending repositories tagged agent-safety, ranked by trending score. Updated daily.
-
1
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。
GitHub · Python · 728 stars · 71 forks · +17 stars in 24 hours · Trending score 2.42
-
2
hyj28/unring
Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become permanent.
GitHub · Go · 23 stars · 0 forks · +10 stars in 24 hours · Trending score 1.62
-
3
agentrust-io/awesome-ai-governance
🛡️ A curated list of tools, frameworks, standards, and resources for AI agent governance, safety, and compliance
GitHub · Shell · 69 stars · 149 forks · +2 stars in 24 hours · Trending score 1.21
-
4
CodeAlive-AI/ai-driven-development
Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.
GitHub · Python · 187 stars · 18 forks · +1 stars in 24 hours · Trending score 1.15
-
5
GenAI-Security-Project/agent-control-standard
The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.
GitHub · Python · 266 stars · 89 forks · +1 stars in 24 hours · Trending score 1.06
-
6
otsoa-dubief/tenure
Revocable trust for your Hermes agent: given by default, taken back on a mistake, earned back on evidence.
GitHub · Python · 11 stars · 2 forks · +3 stars in 24 hours · Trending score 0.75
-
7
huanlin-labs/dsh-isolation-gate
DSH 权限隔离门禁:按目录与操作授权,拦截高危文件操作
GitHub · JavaScript · 11 stars · 0 forks · +1 stars in 24 hours · Trending score 0.61
-
8
dooly6276/claude-bulkhead
Stop Claude Code and other coding agents from running rm -rf on an empty $VAR, pkill-ing your other dev servers, taking their ports, and git add -A-ing another session's edits. Hooks that know which session owns which process, port and git tree. Zero dependencies.
GitHub · JavaScript · 35 stars · 6 forks · 0 stars in 24 hours · Trending score 0.60
-
9
anyu0804/antigravity-agent-rules
Antigravity 桌面端 & agy CLI 跨平台 Agent 安全护栏与分层规则:两档拦截强删 / 误杀代理 / 改系统代理,日志脱敏,验收先行与异构复核,194/242 项自检,一键装卸
GitHub · JavaScript · 30 stars · 2 forks · 0 stars in 24 hours · Trending score 0.56
-
10
tommasocerruti/eal-bench
EAL-Bench: Benchmarking Endogenous Authorization Laundering (EAL) in Agent Memory
GitHub · Python · 15 stars · 3 forks · 0 stars in 24 hours · Trending score 0.42
-
11
oxdeai/oxdeai
Deterministic execution authorization for AI agents and automation systems
GitHub · TypeScript · 16 stars · 7 forks · 0 stars in 24 hours · Trending score 0.39
-
12
SentinelOps-CI/provability-fabric
Provable AI agents with behavioral guarantees enforced by formal verification, runtime security, and end-to-end audit trails.
GitHub · Python · 15 stars · 2 forks · 0 stars in 24 hours · Trending score 0.37
-
13
zhaoxinghua09-cell/uibc-core
UIBC Core — an executable protocol for bounded-lifecycle autonomy:registry, evidence, gates. Reference implementation + conformance tests. Theory SSOT: zhaoxinghua09-cell/lgd-theory. 代码 Apache-2.0;理论文本保留所有权利。
GitHub · Python · 12 stars · 2 forks · 0 stars in 24 hours · Trending score 0.32
-
14
termaxa/termaxa
The agent's prompt shows you the command; Termaxa shows you the consequence. Previews, backups, policy, an audit record. Claude Code, Codex, Cursor, Copilot. A windshield, not a sandbox.
GitHub · Rust · 29 stars · 4 forks · 0 stars in 24 hours · Trending score 0.24
-
15
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.
GitHub · JavaScript · 31 stars · 2 forks · 0 stars in 24 hours · Trending score 0.24
-
16
jamjet-labs/jamjet
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
GitHub · Rust · 25 stars · 9 forks · 0 stars in 24 hours · Trending score 0.24
-
17
openguardrails/OpenAgentLaw
A universal public law for autonomous agents. Open legislation, enforcement, and adjudication; any model may take the bar and qualify as a judge.
GitHub · Python · 108 stars · 16 forks · 0 stars in 24 hours · Trending score 0.21
-
18
agentsmith-tools/maintainer-agent
An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.
GitHub · Shell · 13 stars · 3 forks · 0 stars in 24 hours · Trending score 0.18
-
19
pranee54/AgentDoctor
Codebase intelligence, repository analysis, safety controls, and MCP tools for developers and engineering teams.
GitHub · TypeScript · 11 stars · 3 forks · 0 stars in 24 hours · Trending score 0.14
-
20
Pro-GenAI/Agent-RT
⚡ Fastest and lightweight harness for AI agents
GitHub · Python · 23 stars · 1 forks · −2 stars in 24 hours · Trending score 0.09
-
21
OMD-123/agent-loop-guard
Zero-dependency guardrail framework for AI agents. Stops runaway loops, prompt injection, hallucination and unsafe tool calls before they execute. Provider-agnostic, dual ESM/CJS, TypeScript-first.
GitHub · TypeScript · 13 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
22
Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier
GitHub · Python · 7 stars · 8 forks · −2 stars in 24 hours · Trending score 0.08
-
23
VeridicalTech/Edward
The supervisor for coding agents that run when nobody's watching — deterministic guardrails + local semantic scorer + resumable interventions, every decision signed.
GitHub · Python · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.08
-
24
Hyperion-GPU/ProofFlow-v0.1
GitHub · Python · 110 stars · 8 forks · 0 stars in 24 hours · Trending score 0.06