# x1xhlol/system-prompts-and-models-of-ai-tools

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

Repository: https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools
Canonical: https://ross.abutalabs.com/products/system-prompts-and-models-of-ai-tools
License: GPL-3.0
License Family: copyleft
Topics: ai, cursor, lovable, system-prompts, v0, cursorai, devin, replit, windsurf, windsurf-ai, bolt, open-source, copilot, github-copilot, vscode, trae, trae-ai, trae-ide, cluely, perplexity
Last push: 2026-08-11T13:01:09+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 39
- inputs: {"age_days": 546, "days_push": 22, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 143156, forks 34849 (observed 2026-08-28T04:12:24.335418+00:00)

## What it is
A curated collection of leaked and open-sourced system prompts, internal tools, and AI model specifications from popular AI products like Cursor, Devin, Lovable, Windsurf, and v0. It serves as a reference resource for studying how commercial AI coding assistants and agents are instructed.

## Use cases
- study how AI coding assistants structure their system prompts
- research prompt engineering patterns used by commercial AI agents
- compare system prompt designs across AI tools like Cursor and Devin
- learn techniques for building AI agent instructions
- analyze how AI products define tool usage and guardrails
- find reference prompts for designing your own AI assistant

## When to choose
- you want to study real-world system prompts from popular AI products
- you're designing prompts for an AI coding agent or assistant
- you're researching prompt engineering and agent architecture patterns

## When to avoid
- you need production-ready code or a usable library
- you want legally licensed prompts for direct reuse in your product
- you need up-to-date official documentation rather than leaked snapshots

## Facets
- artifact type: dataset
- maturity: active
- function: prompt-engineering, developer-tools
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cross-platform
- tags: system-prompts, leaked-prompts, ai-coding-tools, reference-collection, prompt-extraction, ai-agents

## Member repositories
- x1xhlol/system-prompts-and-models-of-ai-tools (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.335418+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 2026-08-29T16:11:05.276254+00:00, confidence not recorded.
  - readme: https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools (fetched 2026-08-28T04:12:24.335418+00:00, sha 13bd1e88a01d)
- Data as of 2026-08-30T08:39:29.467469+00:00.