system-prompts-and-models-of-ai-tools and awesome-system-prompts

These are complementary resources that serve the same purpose—curating system prompts for AI coding tools—with A offering significantly broader coverage (131+ tools across multiple categories) while B focuses on a narrower subset of established agents, making them useful together for comprehensive prompt engineering reference material rather than direct alternatives.

system-prompts-and-models-of-ai-tools
71
Verified
awesome-system-prompts
52
Established
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 10/25
Adoption 10/25
Maturity 15/25
Community 17/25
Stars: 131,884
Forks: 33,428
Downloads: —
Commits (30d): 6
Language: —
License: GPL-3.0
Stars: 134
Forks: 22
Downloads: —
Commits (30d): 0
Language: JavaScript
License: GPL-3.0
No Package No Dependents
No Package No Dependents

About system-prompts-and-models-of-ai-tools

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

Based on the README, here's a technical summary: Curated repository of extracted system prompts, internal architectures, and model configurations from 30+ AI coding assistants and development tools. Serves as a reverse-engineering resource for understanding prompt injection vulnerabilities and agent design patterns across commercial and open-source platforms. Includes security documentation highlighting prompt extraction risks, with integration guidance for researchers auditing AI system robustness.

About awesome-system-prompts

EliFuzz/awesome-system-prompts

A collection of system prompts and tool definitions from various AI coding agents: Augment Code, Claude Code, Cluely, Cursor, Devin AI, Kiro, Perplexity, VSCode Agent, Gemini, Codex, OpenAI

Organizes reverse-engineered system prompts and tool schemas across 20+ AI coding agents, including mode-specific variants (e.g., Aider's Architect/Ask/Patch modes) and dated versions tracking prompt evolution. Structures prompts as markdown/JSON files with agent-specific tool definitions, enabling developers to understand agentic behavior patterns, instruction hierarchies, and tool-calling interfaces. Targets AI agent developers, prompt engineers, and researchers studying LLM coding assistant design.

Related comparisons

system-prompts-and-models-of-ai-tools and prompts

Scores updated daily from GitHub, PyPI, and npm data. How scores work