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

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektMCP-ServerÜber unsRanking-MethodikPresse
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

4 Repos

Awesome GitHub RepositoriesDocumentation-Based Context Persistence

Systems that use root-level documentation files to maintain project-specific knowledge across agent sessions.

Distinct from Context-Aware Knowledge Managers: Distinct from Context-Aware Knowledge Managers: focuses on flat-file persistence in the repository root rather than hierarchical resource organizers.

Explore 4 awesome GitHub repositories matching software engineering & architecture · Documentation-Based Context Persistence. Refine with filters or upvote what's useful.

Awesome Documentation-Based Context Persistence GitHub Repositories

Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
  • anus-dev/anusAvatar von anus-dev

    anus-dev/ANUS

    6,461Auf GitHub ansehen↗

    ANUS is an automated coding agent and development framework that uses a large language model to execute technical tasks and modify project files. It functions as a tool-integrated platform that combines a sandboxed shell executor with a system for maintaining persistent project goals. The framework is distinguished by its context-aware development model, which uses local markdown files to track instructions and maintain state across different sessions. It employs a loop-based autonomous development cycle to plan, code, and verify changes, while utilizing a standardized protocol to integrate e

    Uses root-level markdown documentation files to maintain project-specific knowledge and state across agent sessions.

    TypeScript
    Auf GitHub ansehen↗6,461
  • just-every/codeAvatar von just-every

    just-every/code

    3,483Auf GitHub ansehen↗

    This project is a multi-agent development framework and orchestrator designed to coordinate autonomous AI agents for software engineering tasks. It functions as an engine that plans, implements, and reviews complex code changes across multiple files and isolated worktrees from a command line interface. The system distinguishes itself through a multi-agent coordination layer that decomposes tasks into sequential phases and applies changes across isolated worktrees to validate solutions. It maintains project-specific knowledge and constraints across sessions via context persistence using dedica

    Persists project knowledge and instructions across sessions using dedicated documentation files in the root directory.

    Rustaianthropicclaude
    Auf GitHub ansehen↗3,483
  • zebbern/claude-code-guideAvatar von zebbern

    zebbern/claude-code-guide

    3,441Auf GitHub ansehen↗

    This project provides a framework for AI agent orchestration and context management, enabling the deployment of specialized AI personas and subagents to solve multi-step technical goals. It centers on managing specialized agents with isolated contexts and role-based prompts to handle domain-specific tasks. The system differentiates itself through a hierarchical project memory using markdown files to maintain coding standards and a secure execution model that utilizes sandboxed environments and git worktree isolation. It also features a Model Context Protocol integration for external tool conn

    Saves and retrieves context automatically in memory files to maintain knowledge across sessions.

    aiai-agentai-agent-tools
    Auf GitHub ansehen↗3,441
  • vanzan01/cursor-memory-bankAvatar von vanzan01

    vanzan01/cursor-memory-bank

    2,974Auf GitHub ansehen↗

    This project is an AI development workflow orchestrator and context management framework. It provides a context-aware project knowledge base and a structured prompting system designed to guide large language models through the planning, implementation, and verification phases of software development. The system optimizes AI coding contexts by using a collection of markdown files to track project state and architectural memory. It employs mode-based rule isolation and just-in-time context loading to reduce noise and ensure that only relevant rules and documentation are active for a given task.

    Uses a collection of root-level markdown files to maintain project-specific knowledge and task progress.

    Auf GitHub ansehen↗2,974
  1. Home
  2. Software Engineering & Architecture
  3. Context-Aware Tooling
  4. Context-Aware Knowledge Managers
  5. Documentation-Based Context Persistence