Results for “llm-safety”
17 skills
orchestra-research llamaguard
Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.
10.4k
mukul975 defending-llms-with-guardrails
Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.
24.6k · bundle
projectious-work llm-evaluation
LLM output evaluation — automated metrics, LLM-as-judge, A/B testing, regression testing. Use when measuring LLM output quality, comparing prompt or model versions, building an automated eval pipeline, setting up regression tests for prompt changes, or evaluating RAG systems and bias/safety.
0
orchestra-research nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on local Docker, Slurm HPC, or cloud platforms.
10.4k · bundle
More results
deep-chavda ai-engineering-standards
Enforces production-grade Python and AI engineering standards for FastAPI, LangChain/LangGraph, RAG pipelines, and LLM integrations, covering type safety, error handling, testing, and security.
mukul975 implementing-llm-guardrails-for-security
Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.
24.6k · bundle
qcmuu llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
0
tianhao909 llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
1
orchestra-research prompt-guard
Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.
10.4k
antigravity langfuse
Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.
42.4k
tinh2 free-keys
Provisions free LLM API keys from 20+ providers, health-checks existing keys, opens signup pages, validates new keys, and saves them to your project.
13
tianhao909 prompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
1
yanacuti1121 deepeval
DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration
2
mukul975 continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.
24.6k · bundle
bytesagain acme
ACME protocol and SSL/TLS certificate automation reference. Covers challenge types (HTTP-01, DNS-01, TLS-ALPN-01), major clients (certbot, acme.sh, lego, Caddy), certificate lifecycle management, Kubernetes cert-manager, Docker/Traefik integration, and security best practices.
12 · bundle
tianhao909 nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
1 · bundle
qcmuu nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
0 · bundle