ai-safety repositories
Trending repositories tagged ai-safety, ranked by trending score. Updated daily.
-
1
ifixai-ai/iFixAi
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
GitHub · Python · 46,281 stars · 1,828 forks · +76 stars in 24 hours · Trending score 4.01
-
2
microsoft/PyRIT
Open-source AI red teaming toolkit from Microsoft. Test generative AI systems with automated scans, adaptive multi-turn attacks, and a web UI.
GitHub · Python · 4,980 stars · 1,088 forks · +42 stars in 24 hours · Trending score 3.34
-
3
PrismorSec/prismor
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
GitHub · Python · 581 stars · 72 forks · +88 stars in 24 hours · Trending score 3.33
-
4
lobehub/awesome-rsi
A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
GitHub · 1,063 stars · 91 forks · +88 stars in 24 hours · Trending score 3.29
-
5
Tencent/AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
GitHub · Python · 7,594 stars · 780 forks · +45 stars in 24 hours · Trending score 3.20
-
6
kenryu42/cc-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
GitHub · TypeScript · 2,081 stars · 98 forks · +17 stars in 24 hours · Trending score 2.49
-
7
Cygnux-Labs/Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
GitHub · Python · 722 stars · 131 forks · +6 stars in 24 hours · Trending score 2.40
-
8
lacs-project/sysknife
An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.
GitHub · Rust · 309 stars · 43 forks · +11 stars in 24 hours · Trending score 2.36
-
9
onlyreadai/onlyread
Make AI browser agents read-only: a Chrome extension that refuses writes (send, post, edit, delete) before they leave the browser.
GitHub · TypeScript · 110 stars · 13 forks · +14 stars in 24 hours · Trending score 2.25
-
10
strands-agents/box
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
GitHub · Rust · 559 stars · 60 forks · +6 stars in 24 hours · Trending score 1.99
-
11
Alejandros17487/ai-jailbreaks
AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.
GitHub · 451 stars · 103 forks · +8 stars in 24 hours · Trending score 1.86
-
12
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
GitHub · Python · 6,585 stars · 1,129 forks · +5 stars in 24 hours · Trending score 1.59
-
13
h5i-dev/h5i
An Axum-based Rust web framework with Lean 4-verifiable application kernels that run on servers, bare-metal embedded devices, and GPUs, plus integrated security testing.
GitHub · Rust · 931 stars · 82 forks · +3 stars in 24 hours · Trending score 1.52
-
14
PerryLink/dsh-auto-review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
GitHub · TypeScript · 254 stars · 9 forks · +5 stars in 24 hours · Trending score 1.51
-
15
lalipa2003-arch/JailbreakHub
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
GitHub · Roff · 414 stars · 74 forks · 0 stars in 24 hours · Trending score 1.50
-
16
datumbrain/claude-code-privacy-guard
🛡️ Claude Code plugin that blocks prompts containing secrets, API keys, and PII before they reach Claude.
GitHub · TypeScript · 27 stars · 6 forks · +5 stars in 24 hours · Trending score 1.38
-
17
canivel/dynolab
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
GitHub · Python · 220 stars · 162 forks · 0 stars in 24 hours · Trending score 1.24
-
18
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
-
19
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
-
20
tjcrims0nx/OpenMind-Jailbreak-Lab
Open-source AI security research lab for reproducible adversarial testing, jailbreak resistance evaluation, and LLM guardrail validation across multiple model providers.
GitHub · Python · 42 stars · 5 forks · +8 stars in 24 hours · Trending score 1.11
-
21
OWASP/www-project-agent-memory-guard
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
GitHub · Python · 208 stars · 64 forks · +2 stars in 24 hours · Trending score 0.95
-
22
honestDS/MonoLight
MonoLight is a General Autonomous Agent runtime with IM interaction as its primary interaction modality, focusing on safe execution and human-machine collaboration.
GitHub · Python · 24 stars · 1 forks · +2 stars in 24 hours · Trending score 0.88
-
23
guardana/guardana
Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
GitHub · Python · 228 stars · 19 forks · 0 stars in 24 hours · Trending score 0.87
-
24
PerryLink/dsh-permission-rules
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
GitHub · TypeScript · 138 stars · 4 forks · +2 stars in 24 hours · Trending score 0.86