All prompt tools
Every tool in the directory. Filter by category or search by name.
LLM Prompt Library
An experimental library of prompts, Jinja2 templates and helper scripts aimed at power users, covering analysis, writing, coding and structured reasoning tasks.
Arthur
An AI governance and monitoring platform that gives security, risk and engineering teams a shared control plane for evaluating and supervising deployed models.
Dotprompt
A Google specification for executable prompt files that keep the template, model settings and input and output schemas together in a single portable text file.
Guardrails AI
A Python framework that wraps model calls with input and output validators from a shared hub, re-asking the model or failing closed when a check does not pass.
LangWatch
An open-source platform for LLM evaluation and agent testing with prompt versioning, scenario-based agent simulations and an optimization studio built on DSPy.
OpenAI Cookbook
OpenAI's official examples repository with notebooks and guides covering prompting techniques, structured outputs, function calling, embeddings and evaluation.
Adaline
An observability and evaluation platform that turns production traces into datasets and prompt improvements, marketed for teams running self-improving agents.
Agentic Security
An open-source red-teaming kit that fuzzes LLM endpoints with adversarial prompt datasets and multimodal attacks, producing a report of which defences failed.
DeepLearning.AI
Andrew Ng's education company, publishing short courses on prompt engineering, LLM application development, agents and evaluation, many of them free to audit.
LLM Engineer's Handbook
The companion code repository for a published handbook on building and deploying language model applications, including prompt design and evaluation chapters.
LMMs-Eval
An evaluation toolkit for multimodal models covering text, image, video and audio tasks with a unified interface, used to benchmark vision-language prompting.
Patronus AI
An evaluation platform offering managed judge models and test suites for scoring model output, including document-heavy workflows measured by pages processed.
Prompt Hunt
A site for exploring, creating and sharing AI art prompts across Stable Diffusion, DALL-E and Midjourney, with templates that can be reused with new subjects.
Prompt Security
A security product, now part of SentinelOne, that inspects prompts and responses across an organisation to block injection attacks and sensitive data leakage.
Respan (Keywords AI)
An LLM engineering platform, previously branded Keywords AI, that combines observability, evaluations, prompt optimization and a model gateway behind one API.
Tree of Thoughts
A plug-and-play implementation of tree-of-thoughts prompting, where a model explores and evaluates multiple reasoning branches before committing to an answer.
IntellAgent
A framework that builds a policy graph from an agent's prompt and generates simulated user conversations to diagnose where the agent breaks its instructions.
OpenAI Agents SDK
OpenAI's lightweight framework for multi-agent workflows, built around agents with instructions, handoffs between agents, guardrails and tracing of each run.
Promptmetheus
A prompt engineering IDE for composing prompts from reusable blocks, testing variants across providers and tracking cost and output quality for each version.
Promptr
A command-line tool that applies plain-language instructions to files in a project, using Liquid templates so reusable instruction sets can be parameterised.
CL4R1T4S
A transparency-focused archive of system prompts and operating instructions gathered from many commercial AI products, maintained as a public reference set.
CLIP Interrogator
A tool that runs image captioning and CLIP similarity in reverse to suggest the prompt text and artist or style modifiers that would recreate a given image.
Coze Loop
ByteDance's open-source agent development platform covering prompt development and versioning, evaluation datasets and production observability in one loop.
FuzzyAI
A CyberArk fuzzing tool that applies a catalogue of jailbreak and obfuscation techniques against model endpoints to find prompts that bypass safety filters.
LangChain Academy
LangChain's free course platform teaching agent development with LangGraph and related tooling, including how prompts and state are managed in agent graphs.
Opper AI
A European-hosted gateway that exposes hundreds of models through a single API with built-in task definitions, spend controls and data residency guarantees.
Relevance AI
A no-code platform for building specialist AI agents and multi-step workflows, where each agent's instructions and tools are configured in a visual builder.
SD.Next
An all-in-one web interface for generative image and video models with prompt parsers, captioning tools and support for a wide range of model architectures.
SuperPrompt
An experimental prompt built around structured XML-like reasoning scaffolds, published as an attempt to probe how models handle complex nested instructions.
Agently
A development framework for generative AI applications with a chained request syntax that builds structured prompts and enforces an expected output schema.
DataDreamer
A Python library for reproducible synthetic data and prompting workflows, with caching, resumable sessions and export of the full prompt history for a run.
Laminar
An open-source observability platform purpose-built for AI agents, combining span tracing, online and offline evaluations and labelling of production data.
Pezzo
An open-source LLMOps platform for designing, versioning and publishing prompts from a central console, with observability over the requests that use them.
AI Product Development Toolkit
A set of prompt templates and agent configurations for user-centred product development, walking from research and requirements through to specifications.
Athina Evals
The open-source Python SDK behind the Athina platform, used to run evaluation suites over model responses and log the scored results for later comparison.
Awesome Claude Prompts
A curated list of prompts written specifically for Claude, covering writing, analysis, coding and business tasks with notes on Claude-specific formatting.