Meirtz/Awesome-Context-Engineering

🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.

What it is: A curated, community-driven collection (an "awesome" list) of resources, techniques, and survey material about Context Engineering — the practice of designing the full information given to an AI model at inference time, moving beyond static prompts to dynamic, context-aware systems.

What it includes:

  • A published survey paper (arXiv link) with theoretical foundations.
  • Organized sections covering definitions, why it matters, components (context scaling, management, structured data), implementations (RAG, memory systems, agent communication, tool use), evaluation, applications, limitations, and future directions.
  • Links to related surveys on large language models, prompting, RAG, memory, and agent evaluation.
  • A 2026 update expanding the scope to agent engineering: agent runtimes, memory artifacts, open protocols (like MCP, A2A), coding agents, and observability.

Key features:

  • Community discussion via WeChat and Discord.
  • Open to contributions (PRs welcome) with formatting guidelines.
  • Distributed under the MIT license.

Who it's for: Researchers, developers, and practitioners working with LLMs, AI agents, context management, and production AI systems — anyone wanting a structured overview and curated resources for building context-aware, production-grade AI.

Related

  • Project
    omnara-ai/omnara

    Omnira is an open‑source, self‑hostable platform for running AI agents on any LLM model and any machine. It provides a REST API, TypeScript SDK, and CLI to launch agents, stream events, and handle approvals. Features include model‑agnostic support, built‑in and custom tools, reusable skills, persistent memory, sub‑agents, multi‑tenant RBAC, scheduling, and integrations with Slack, Discord, GitHub, webhooks, and more. You can try it via Omnira Cloud or run it locally with Docker Compose; the Apache 2.0‑licensed code keeps all agent data in your own Postgres.

  • Project
    jjyaoao/HelloAgents

    HelloAgents is a Python library for building modular multi‑agent applications that use LLM function‑calling. It provides ready‑made agents, a tool registry, context handling, RAG/memory stores, sub‑agents, streaming, and observability, with adapters for OpenAI‑compatible, Anthropic and Gemini services.

  • Project
    minitap-ai/mobile-use

    An open-source AI agent that automates Android and iOS devices using natural language to perform tasks and scrape data from apps.

  • Project
    Derpyu520/qq-bridge

    A Node.js bridge that connects QQ (via SnowLuma OneBot v11) to a DeepSeek Harness AI agent, providing chat, tool calls, role‑play, token‑usage dashboard, and a web console.