awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
steipete avatar

steipete/agent-rulesArchived

0
View on GitHub↗
5,690 stars·510 forks·Shell·MIT·8 vuessteipete.me↗

Agent Rules

Agent-Rules is a structured system for defining how AI coding agents behave within software projects. It provides a framework of rules and knowledge files that shape an agent's interpretation of tasks and its interactions with code, serving as a configuration layer for agent behavior guidelines.

The system organizes rules as plain markdown files in a conventional directory structure, which agents read at startup. Rules are scoped to specific project directories, with a file-name convention that agents recognize and load automatically. A rule inheritance hierarchy allows project-specific instructions to merge with global defaults, creating layered configurations that adapt to different project contexts.

The knowledge base consists of static markdown documents that agents reference during task execution, embedding project conventions and best practices without dynamic generation. The project also includes governance rules for transferring an open-source project to a foundation structure, ensuring independent community stewardship.

Features

  • Agent Behavioral Configuration - Defines rules and knowledge files that shape how an AI coding agent interprets tasks and interacts with code.
  • AI Coding Agent Platforms - Defines rules and knowledge files that shape how an AI coding agent interprets tasks and interacts with code.
  • Behavioral Guideline Configuration - Provides predefined instructions that shape an AI agent's operational behavior within a software project.
  • Agent Instruction Formats - Uses Markdown with frontmatter metadata as a structured format for agent behavior instructions.
  • Static Markdown Documentation - Embeds static markdown documents as a knowledge base that agents reference during task execution.
  • Agent Knowledge Formats - Provides a structured set of knowledge files that inform AI agents about project conventions and best practices.
  • AI Coding Assistant Rules - Provides curated rules and knowledge files that define how an AI coding agent interprets tasks and interacts with code.
  • Markdown File Systems - Provides a structured markdown file system for organizing and loading agent behavior rules at startup.
  • Agent File Conventions - Defines file naming conventions that agents recognize to automatically load behavior rules.
  • Inherited Configurations - Implements hierarchical inheritance of agent rules from parent directories and global defaults.
  • Agent Rule Scoping - Organizes agent rules in directory-scoped subdirectories for automatic context-specific loading.

Historique des stars

Graphique de l'historique des stars pour steipete/agent-rulesGraphique de l'historique des stars pour steipete/agent-rules

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Questions fréquentes

Que fait steipete/agent-rules ?

Agent-Rules is a structured system for defining how AI coding agents behave within software projects. It provides a framework of rules and knowledge files that shape an agent's interpretation of tasks and its interactions with code, serving as a configuration layer for agent behavior guidelines.

Quelles sont les fonctionnalités principales de steipete/agent-rules ?

Les fonctionnalités principales de steipete/agent-rules sont : Agent Behavioral Configuration, AI Coding Agent Platforms, Behavioral Guideline Configuration, Agent Instruction Formats, Static Markdown Documentation, Agent Knowledge Formats, AI Coding Assistant Rules, Markdown File Systems.

Quelles sont les alternatives open-source à steipete/agent-rules ?

Les alternatives open-source à steipete/agent-rules incluent : agentsmd/agents.md — Agents.md is a configuration framework designed to standardize how AI coding assistants interact with a repository. It… instructa/ai-prompts — This project provides a centralized repository and configuration framework for managing system instructions,… dontriskit/awesome-ai-system-prompts — This project is a comprehensive library of structured system prompts and configuration templates designed to define… freecodexyz/free-code — Free Code is a terminal-native AI coding agent that edits files, runs shell commands, and answers questions through… affaan-m/ecc — ECC is an LLM agent orchestration framework and cross-platform AI tooling suite designed to coordinate multi-model… cloudflare/sandbox-sdk — The sandbox-sdk is a development kit designed for building secure, isolated execution environments on a global edge…

Alternatives open source à Agent Rules

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Agent Rules.
  • agentsmd/agents.mdAvatar de agentsmd

    agentsmd/agents.md

    22,264Voir sur GitHub↗

    Agents.md is a configuration framework designed to standardize how AI coding assistants interact with a repository. It provides a structured format for defining project context, behavioral guidelines, and operational instructions, ensuring that AI tools maintain consistency and adhere to project-specific standards throughout the development process. The system distinguishes itself through a hierarchical configuration approach, allowing developers to define settings that inherit and override instructions across different subdirectories. By utilizing markdown-based files, it enables the injecti

    TypeScript
    Voir sur GitHub↗22,264
  • instructa/ai-promptsAvatar de instructa

    instructa/ai-prompts

    1,048Voir sur GitHub↗

    This project provides a centralized repository and configuration framework for managing system instructions, behavioral constraints, and coding standards within AI-assisted development environments. It serves as a library of curated prompts and rules designed to standardize the output of autonomous coding agents, ensuring that generated code consistently adheres to project-specific architectural patterns and technical requirements. The tool distinguishes itself by employing an agent-agnostic schema that allows behavioral guidelines to be interpreted across various development platforms. It su

    JavaScriptagentai-agentai-prompts
    Voir sur GitHub↗1,048
  • dontriskit/awesome-ai-system-promptsAvatar de dontriskit

    dontriskit/awesome-ai-system-prompts

    5,206Voir sur GitHub↗

    This project is a comprehensive library of structured system prompts and configuration templates designed to define the behavior, persona, and operational boundaries of autonomous artificial intelligence agents. It serves as a framework for prompt engineering, providing modular instructions that help models parse complex tasks, maintain consistent interaction tones, and adhere to specific domain constraints. The repository distinguishes itself by offering specialized configurations for agent safety and security, including protocols to prevent prompt injection and unauthorized data access. It

    TypeScript
    Voir sur GitHub↗5,206
  • affaan-m/eccAvatar de affaan-m

    affaan-m/ECC

    221,981Voir sur GitHub↗

    ECC is an LLM agent orchestration framework and cross-platform AI tooling suite designed to coordinate multi-model workflows. It provides a system for managing specialized agent roles, reusable skills, and structured planning to execute complex software development tasks across different AI-powered code editors. The project distinguishes itself as a Model Context Protocol manager, providing a configuration layer to integrate external servers and audit tool execution. It further implements an agentic security sandbox that restricts sensitive file access and scans for secret leakage to secure a

    JavaScript
    Voir sur GitHub↗221,981
Voir les 30 alternatives à Agent Rules→