AI Hub & Tools Directory — Curated LLMs, Agents & Workflows
Discover and filter the highest-rated AI tools, coding assistants, and automation agents curated by ThingDaily.
Claude 3.7 Sonnet
Frontier hybrid reasoning and software engineering model with instant mode switching.
NotebookLM (Google DeepMind)
Grounds frontier Gemini 1.5 Pro models strictly on your PDFs and notes to create instant study guides, FAQs & audio podcasts.
Perplexity Pro
Deep Research engine with multi-source citation verification and structured exports.
Midjourney v6.1
Photorealistic text-to-image synthesis with precise parameter controls and web interface.
n8n AI Agents
Self-hostable visual workflow automation with 400+ integrations & autonomous LLM nodes.
Cursor AI Code Editor
AI-assisted code editor with codebase-aware chat, inline edits, and multi-file changes.
Ollama
Run and manage open-source language models locally with a straightforward command-line tool and API.
Cursor AI Code Editor
AI-assisted code editor with codebase context, inline edits, and agent workflows for development tasks.
Ollama
Run and manage open-weight language models locally with a straightforward command-line tool and API.
Ollama
Run and manage open-weight language models locally, with a straightforward CLI and local API.
Ollama
Run and manage open-weight language models locally, with command-line and API access.
Unsloth
Open-source tools for faster LLM fine-tuning; hardware and model compatibility still matter.
vLLM Inference Engine
Open-source serving engine with speculative decoding options; speedups depend on model pair and workload.
llama.cpp
Run quantized language models locally with broad GGUF support and CPU/GPU placement options.
vLLM Inference Engine
Open-source LLM serving engine; verify MLA support for your model revision and hardware.
Ollama
Run and manage open-weight language models locally with a straightforward command-line and desktop workflow.
Ollama
Run and manage open-weight language models locally on your computer.
LangGraph
Build stateful, multi-step LLM workflows with graph-based control over agents, tools, and human review.
Unsloth
Open-source toolkit for memory-efficient fine-tuning of language models with LoRA and QLoRA.
Unsloth
Open-source toolkit for efficient LLM fine-tuning, including LoRA and QLoRA workflows.
Pydantic
Python data validation for checking structured arguments before tools run.
vLLM Inference Engine
Open-source LLM serving engine with PagedAttention and continuous batching for supported models.
BGE-M3 via FlagEmbedding
Local multilingual embeddings with dense, sparse, and multi-vector retrieval options.
llama.cpp
Run quantized language models locally and explore speculative decoding on supported model pairs.
Qdrant
Purpose-built vector search; score reflects editorial fit, not a measured latency result.