# f/prompts.chat

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

Repository: https://github.com/f/prompts.chat
Canonical: https://ross.abutalabs.com/products/promptschat
Homepage: https://prompts.chat
Language: HTML
License: NOASSERTION
License Family: other
Topics: chatgpt, ai, artificial-intelligence, awesome-list, chatgpt-prompts, claude, gemini, gpt, gpt-4, llm, machine-learning, nextjs, open-source, openai, prompt-engineering, prompts, typescript, prompts-chat
Last push: 2026-08-26T03:25:26+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 97
- inputs: {"age_days": 1367, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 167975, forks 21671 (observed 2026-08-28T04:12:24.426586+00:00)

## What it is
prompts.chat (formerly Awesome ChatGPT Prompts) is the world's largest open-source, CC0-licensed prompt library for AI models like ChatGPT, Claude, and Gemini. It combines a curated community prompt collection with a Next.js web app that can be self-hosted with custom branding, auth, and an MCP-first API for programmatic prompt discovery.

## Use cases
- find good prompts for chatgpt
- share prompts with my team privately
- self-host a prompt library for my organization
- search ai prompts programmatically via mcp
- use chatgpt prompts as a dataset for training or research
- discover community prompts for claude and gemini

## When to choose
- you want a large, freely licensed (CC0) collection of community-tested prompts
- you need a self-hosted prompt platform with privacy, branding, and multi-provider auth
- you want an MCP endpoint or dataset (Hugging Face) to integrate prompts into tools or research

## When to avoid
- you need a prompt engineering or evaluation framework rather than a prompt collection
- you require a strictly permissive OSI license for the application code (license is listed as NOASSERTION; only the prompts are CC0)
- you want managed enterprise support out of the box

## Facets
- artifact type: dataset
- maturity: active
- function: prompt-engineering, search-engine, chatbot, mcp, self-hosted
- domain: artificial-intelligence, large-language-models, developer-tools, awesome-lists
- platform: self-hosted, browser
- tags: chatgpt-prompts, prompt-library, awesome-list, nextjs, cc0, community, huggingface-dataset, web-server, nodejs

## Member repositories
- f/prompts.chat (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.426586+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:10:53.082333+00:00, confidence not recorded.
  - readme: https://github.com/f/prompts.chat (fetched 2026-08-28T04:12:24.426586+00:00, sha c5355e338485)
  - homepage: https://prompts.chat (fetched 2026-08-28T17:24:15.495201+00:00, sha 3607533e4e62)
  - site_page: https://prompts.chat/about (fetched 2026-08-28T17:24:15.504441+00:00, sha e58ffad128ae)
  - site_page: https://prompts.chat/docs/self-hosting (fetched 2026-08-28T17:24:15.506252+00:00, sha e70395e4467b)
  - site_page: https://prompts.chat/docs/api (fetched 2026-08-28T17:24:15.508088+00:00, sha 5a7a6b916fa5)
- Data as of 2026-08-30T08:39:29.467469+00:00.