All prompt tools
Every tool in the directory. Filter by category or search by name.
PromptBase
A marketplace where prompt engineers sell individual prompts for text and image models. Buyers browse by model and use case, and the site says it lists more than 330,000 prompts.
Agenta
An open-source workspace where engineers and subject-matter experts iterate on prompts and agent configurations side by side, with versioning, evaluation runs and observability.
Fabric
An open-source framework built around a large library of reusable prompt patterns invoked from the command line, each pattern being a markdown system prompt for a specific task.
Google Agent Development Kit
Google's open-source Python toolkit for building and deploying agents, with agent instructions, tools, sessions and a built-in evaluation runner for checking agent trajectories.
Kiln
A desktop application and Python library for building AI systems, covering prompt iteration, dataset collection, evaluations, synthetic data and fine-tuning in one project file.
Microsoft 365 Copilot Prompt Samples
A community sample repository maintained under the Microsoft Patterns and Practices programme, collecting prompt examples for Microsoft 365 Copilot across common work scenarios.
Midjourney
One of the best known text-to-image services, driven entirely by prompts with parameters for aspect ratio, style weighting and image references documented in its official guide.
AG2
The community-maintained continuation of the original AutoGen codebase, providing conversational multi-agent patterns with configurable system messages and group chat managers.
Arize Phoenix
Arize's open-source observability tool that runs locally or self-hosted, offering OpenTelemetry tracing, a prompt playground with saved prompt versions and built-in evaluators.
ChainForge
An open-source visual environment for stress-testing prompts. Prompt variants, models and evaluators are wired together as nodes, and results are compared in charts and tables.
Galileo
An evaluation and observability platform for generative applications, with automated metrics for hallucination and instruction adherence plus guardrails for production traffic.
Giskard
An open-source testing library that automatically scans LLM applications and agents for issues such as hallucination, prompt injection, harmful content and robustness failures.
Prompty
A Microsoft specification and tooling for the .prompty file format, storing a prompt plus its model configuration and sample inputs in one readable asset with a VS Code runner.
Helicone
An open-source observability and gateway platform that logs every model request through a one-line proxy change, with prompt versioning, caching and experiment tooling on top.
Langtrace
An open-source, OpenTelemetry-based observability tool for LLM applications that captures traces, manages prompt versions in a registry and runs evaluations on collected data.
MLflow
The widely used open-source ML platform, which now includes a prompt registry for versioning prompt templates alongside tracing and LLM evaluation for generative applications.
Prompt Poet
A library from Character.AI for composing prompts from YAML and Jinja2 templates, with automatic truncation that respects section boundaries when the context limit is reached.
Rig
A Rust library for building LLM-powered applications with typed agents, embeddings and vector store integrations, aimed at teams that want prompt logic in a compiled language.
12-Factor Agents
A written set of principles for building reliable LLM software, including factors on owning your prompts, owning context construction and treating tools as structured output.
Prompt flow
A Microsoft toolkit for building LLM applications as directed flows of prompts, Python code and tools, with batch runs, built-in evaluation flows and a VS Code visual editor.
Chainlit
An open framework and hosted service for building conversational AI interfaces with built-in observability, feedback collection and evaluation of the conversations produced.
Langfuse
An open-source LLM engineering platform combining tracing, evaluations and a prompt management layer where prompts are versioned, labelled and fetched at runtime by the SDK.
Strands Agents SDK
An open-source SDK, originally from AWS, for building production agents in Python and TypeScript with an explicit model-tools-prompt loop that developers control end to end.
FastChat
The LMSYS platform for serving and evaluating chat models, including the MT-Bench multi-turn judge harness and the infrastructure used for crowd-sourced model comparisons.
WhyLabs
An observability platform for AI and data pipelines that profiles inputs and outputs to detect drift and quality problems, including text from language model applications.
Arize AX
Arize's commercial platform for agent observability and evaluation, adding hosted tracing, online evaluators and issue tracking on top of the open-source Phoenix project.
Prompt Engineering Techniques (NirDiamant)
A tutorial repository of twenty-two prompt engineering techniques, each explained with a runnable Jupyter notebook that moves from basic structure to advanced strategies.
Superagent
An open-source guardrail layer that inspects model traffic for prompt injection, data leakage and harmful output, and can be embedded in an application or run as a proxy.
Weights & Biases
The experiment tracking company whose Weave product records LLM calls, versions prompts and datasets as objects, and runs scored evaluations for generative applications.
Anthropic Interactive Prompt Engineering Tutorial
Anthropic's hands-on tutorial that teaches prompting for Claude through nine chapters of exercises run in notebooks, from basic structure to complex multi-step prompts.
Bifrost
An open-source AI gateway that fronts many model providers behind one API, adding routing, load balancing, guardrails and governance for prompts sent from applications.
ContextGem
A Python framework for extracting structured data from documents where the extraction prompts and schemas are generated from declarative aspect and concept definitions.
Generative AI for Beginners
A free twenty-one-lesson Microsoft course covering generative AI fundamentals, with dedicated lessons on prompt engineering, prompt templates and building applications.
LightEval
Hugging Face's evaluation toolkit for running benchmark tasks across several inference backends, with custom task and metric definitions and detailed per-sample output.
Prometheus Eval
An open-source evaluator language model and toolkit for grading responses against a user-supplied scoring rubric, offered as an alternative to proprietary judge models.
Promptify
A Python library with prompt templates for common NLP tasks such as named entity recognition, classification and question answering, returning parsed structured output.