Cette page est affichée en anglais. Une traduction française est en cours.
KnowledgeMay 13, 2026·2 min de lecture

Awesome Context Engineering — Prompt to Production

Awesome Context Engineering is a survey of papers, frameworks, and guides bridging prompt engineering to production-grade agent systems.

Prompt Lab
Prompt Lab · Community
Prêt pour agents

Cet actif peut être lu et installé directement par les agents

TokRepo expose une commande CLI universelle, un contrat d'installation, le metadata JSON, un plan selon l'adaptateur et le contenu raw pour aider les agents à juger l'adaptation, le risque et les prochaines actions.

Native · 96/100Policy : autoriser
Surface agent
Tout agent MCP/CLI
Type
Knowledge
Installation
Git
Confiance
Confiance : Community
Point d'entrée
git clone https://github.com/Meirtz/Awesome-Context-Engineering && cd Awesome-Context-Engineering
Commande CLI universelle
npx tokrepo install 5052fa57-2484-502e-8ec6-d4b457295349
contrat d'installationJSON metadataplan adaptateurcontenu raw
Introduction

Awesome Context Engineering is a survey of papers, frameworks, and guides bridging prompt engineering to production-grade agent systems.

Best for: teams building agent systems who need a context-engineering reading and implementation map

Works with: prompt design, memory/RAG, eval harnesses, production agent architectures

Setup time: 5-10 minutes

Key facts (verified)

  • GitHub: 3128 stars · 225 forks · pushed 2026-05-09.
  • License: MIT · Owner avatar and repo URL verified via GitHub API.
  • README-verified entrypoint: git clone https://github.com/Meirtz/Awesome-Context-Engineering && cd Awesome-Context-Engineering.

Main

  • Use it to avoid reinventing context: pick one topic and follow the linked guides into implementation.

  • Adopt it as a team reading list and implementation backlog, not a one-off bookmark.

  • Quantitatively, you can turn sections into weekly experiments and benchmarks to track progress.

Source-backed notes

  • Repo description frames it as a survey from prompt engineering to production-grade AI systems.
  • It curates papers, frameworks, and implementation guides for LLMs and AI agents.
  • MIT license and recent pushes are verified via GitHub metadata.

FAQ

  • Is it only papers?: No. It also links to frameworks and implementation guides.
  • How do I get value quickly?: Pick one area (memory/eval/routing) and implement one small experiment.
  • How do I keep it current?: Watch the repo and periodically sync your internal notes with new sections.
🙏

Source et remerciements

Source: https://github.com/Meirtz/Awesome-Context-Engineering > License: MIT > GitHub stars: 3128 · forks: 225

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires

Awesome Agent Memory — Long-Term Context Index

Awesome Agent Memory curates systems, benchmarks, and papers on long-term context for LLMs/MLLMs—use it to compare approaches and pick tools to try.

Knowledge
AI Open Source

Awesome Agentic Patterns — Practical Blueprints

awesome-agentic-patterns is a curated catalogue of reusable agent patterns covering planning, tool use, memory, evaluation, and safety loops.

Knowledge
Agent Toolkit

Cohere Command R — Long-Context Tool-Use Model for Agents

Command R+ is Cohere's flagship LLM. 128K context, native tool use, RAG-tuned, multilingual. Cheaper than Claude Sonnet, comparable on tool-use benchmarks.

Knowledge
Cohere

Self-Evolving Agents Survey — Lifelong Systems

Awesome-Self-Evolving-Agents is a survey collection on self-evolving AI agents and lifelong systems, focusing on feedback, memory, and iteration loops.

Knowledge
Agent Toolkit
◈Accueil🔍Rechercher👤Moi