AgentIndex · explore
Browse the index
2,542 resources tagged dcat:llm-inference · clear filter
By protocol
By what it does
Worked out by us from each service’s own description and its live tool list, because most publishers never declare a category. Kept separate from what publishers say below.
Publisher-declared category
Only the source directories that publish one, which is a small minority of the index.
Matching resources
- Viridis Security Injection Detector
Agent-native prompt and tool-injection screening. Detect adversarial instructions before an agent consumes them, or analyze an agent trace for tool-policy viola
- Viridis Security Canon Scanner
Source-code security scanning for AI agents against the Viridis vulnerability canon, with bounded findings and remediation guidance. Calls use the separate Viri
- Viridis Security Maxwell Defense
Adaptive proof-of-work defense for AI-agent endpoints that makes abusive requests expensive while legitimate verification stays cheap. Available on Viridis Secu
- Relaystation llms.txt
Concise agent-readable capability summary (llms.txt convention). Long form with every endpoint, the x402 wire summary, and the trust model at https://api.relays
- Recipe: Agent RAG Memory
Durable, searchable memory for your agent — no vector DB to run. Ingest text into a prepaid vector index inside a baton, then ask questions and get grounded ans
- huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure.
- huggingface-vision-trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet,
- train-sentence-transformers
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering
- Inference Providers MCP Server
Generate chat responses using various AI providers
- Inference Providers MCP Server MCP Server
Generate chat responses using various AI providers
- Prompt Optimizer MCP Server
Optimize prompts for better LLM results
- Prompt Optimizer MCP Server MCP Server
Optimize prompts for better LLM results
- Jupyter Agent
Generate executable Jupyter notebooks from natural language prompts
- Agentic AI
Generate text responses based on prompts using OpenAI API
- Agentic AI MCP Server
Generate text responses based on prompts using OpenAI API
- trl-training
Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning).
- hf-mem
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
- Cognitive Skills Engine
Generate tailored LLM system prompts with expert skill routing
- Practical Skills Assessment Prompt Engineering Challenge
Run a multi‑step LLM test on legal document questions
- Z Image Turbo
Generate high-quality images from text prompts in seconds
- Z Image Turbo MCP Server
Generate high-quality images from text prompts in seconds
- FireRed Image Edit 1.0 Fast
Edit images with text prompts using AI
- FireRed Image Edit 1.0 Fast MCP Server
Edit images with text prompts using AI
- Image To Prompt
Generate detailed captions for your images
- Qwen-Image-Edit-2509-LoRAs-Fast
Edit images with AI using prompts and style adapters
- Qwen-Image-Edit-2509-LoRAs-Fast MCP Server
Edit images with AI using prompts and style adapters
- Z Image Turbo
Generate detailed images from your text prompts
- Z Image Turbo MCP Server
Generate detailed images from your text prompts
- Qwen Image 2512
Rewrite image prompts into detailed English descriptions
- Qwen Image Edit 2511+LoRA
Edit up to 3 images with prompts and optional LoRA filters