safelabs-eval
Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy
AgentSafeLabs/safelabs-eval
View on GitHub ↗Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy
safelabs-eval grew -21.6% in the last 30 days, ranks 190th of 872 in Evaluation & Guardrails, last commit 15 days ago.
Star trajectory
71 days tracked-21.6% in 30d, below the Evaluation & Guardrails median of +1.4%.
Last commit 15 days ago, staler than the median of 15d.
How it compares in Evaluation & Guardrails
Ranked 190th of 872 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere safelabs-eval sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use…
+10 (+1.7%) in 30d · Committed 31d ago · Python · Apache-2.0
Shares Evaluation & Guardrails, Agent SDK / Framework
Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University
+1 (+0.6%) in 30d · Committed 134d ago · Python · MIT
Shares Evaluation & Guardrails, Agent SDK / Framework
- ifixai-ai/iFixAi46.7k
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in…
+13.4k (+40%) in 30d · Committed yesterday · Python · Apache-2.0
Shares Evaluation & Guardrails, Agent SDK / Framework
MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker…
+498 (+553%) in 30d · Committed 49d ago · Python · Other license
Shares Agent SDK / Framework, Evaluation & Guardrails
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it…
+161 (+38%) in 30d · Committed today · Python · Apache-2.0
Shares Evaluation & Guardrails, Agent SDK / Framework
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro…
+44 (+8.3%) in 30d · Committed 23d ago · JavaScript · MIT
Shares Agent SDK / Framework, Evaluation & Guardrails
SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in…
+51 (+10%) in 30d · Committed 219d ago · MIT
Shares Evaluation & Guardrails, Agent SDK / Framework
Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch…
+1 (+0.2%) in 30d · Committed 21d ago · TypeScript · MIT
Shares Evaluation & Guardrails, Agent SDK / Framework
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement…
-96 (-16%) in 30d · Committed today · Python · Other license
Shares Agent SDK / Framework, Evaluation & Guardrails
WCAG 2.2 AA accessibility review for AI coding tools: Agent Skills, an edit gate and accessibility scanners…
+25 (+5.8%) in 30d · Committed 5d ago · JavaScript · MIT
Shares Agent SDK / Framework, Evaluation & Guardrails
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 1
- Forks
- 76
- Watchers
- 13
- Open issues
- 0
- Releases
- 10
- Created
- 2026-05-25
- Stars this week
- -117
You've seen where safelabs-eval stands today.
Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.