awesome-context-engineering
A curated collection of resources, papers, tools, and best practices for Context Engineering in AI agents and Large Language Models (LLMs).
https://github.com/yzfly/awesome-context-engineering
Last synced: 4 days ago
JSON representation
-
🙏 Acknowledgments
-
Contribution Categories
-
-
📖 Featured Articles
-
Advanced Context Engineering for Coding Agents
-
Anthropic / Claude
-
Claude Code Best Practices
-
Context Engineering (Simon Willison)
-
dbreunig Context Engineering Series
-
Don't Build Multi-Agents (Cognition)
-
LangChain Context Engineering
-
Manus Context Engineering
-
SWE-grep: RL for Fast Context Retrieval (Cognition)
-
The New Skill in AI is Not Prompting, It's Context Engineering (Philipp Schmid)
-
Wide Research: Beyond the Context Window (Manus)
-
-
🔗 Model Context Protocol (MCP)
-
Context7 MCP Server
-
MCP Ecosystem
- Filesystem Server - based context management
-
-
📑 Research Papers
-
Core Research Areas
-
Survey Papers
-
-
⭐ Star History
-
Contribution Categories
- ![Star History Chart - history.com/#yzfly/awesome-context-engineering&Date)
- ![Star History Chart - history.com/#yzfly/awesome-context-engineering&Date)
-
-
🛠️ Tools & Projects
-
Comprehensive Resources
-
Context Engineering Systems & Kits
- get-shit-done (GSD) - prompting, context engineering and spec-driven development system for Claude Code
- Agent Skills for Context Engineering - agent architectures
- GSD-2 - prompting / context engineering system enabling long-running autonomous agent work
- MineContext - aware AI companion
- how-claude-code-works
- pro-workflow - correcting memory Claude Code workflow, including context engineering
- Advanced Context Engineering for Coding Agents
- Context Engineering Kit
- ACE (Agentic Context Engineering)
- Practical Guide to Context Engineering - on guide (in Chinese) to context engineering for LLM applications
- kit
- RepoPrompt CE
- context-engineering (outcomeops) - to-end on Amazon Bedrock
- Project Context Records (PCR) - engineering methodology that keeps a durable, repo-versioned archive of a project's meta-context (the why, architecture, and maintainer decisions) so AI collaborators inherit its judgment instead of re-deriving it
- interview-prep-template - layer context-engineering template (immutable sources → agent-maintained wiki → operating-manual file) where the agent synthesizes raw material into reusable answers, frameworks, and scored debriefs that compound over time
- context-space
- ax - agent sessions, costs, skills, routing, and hooks
- MFS - like, searchable namespace (`ls`/`cat`/`grep` + hybrid semantic search), so agents pull context incrementally instead of injecting it all up front; self-hosted and local-first (local ONNX embeddings + Milvus, no API key)
-
Development Frameworks
-
Memory & Compression
- Letta (MemGPT) - term memory
- Mem0
- LLMLingua - efficient LLM inference
- claude-mem - session memory for Claude Code that automatically captures, compresses, and re-injects context across sessions
- LeanCTX (lean-ctx) - first design
- headroom - 95% of tokens
- Accordion - relevant blocks in the background via pluggable "conductors" that rank block relevance, instead of lossy all-or-nothing compaction
- Vestige - first MCP memory server (single ~23MB Rust binary, data stays on-device) with entity/causal retrieval — links memories by shared file/env-var/service/symbol to recall the earlier change behind a later failure that similarity search can miss"
- Cognee - source AI memory platform giving agents persistent long-term memory via a self-hosted knowledge-graph engine
- Graphiti - time, temporal knowledge graphs for AI agents (the engine behind Zep's memory)
- Supermemory
-
Programming Languages
Categories
Sub Categories
Context Engineering Systems & Kits
18
Memory & Compression
11
Comprehensive Resources
7
Anthropic / Claude
6
Survey Papers
5
Core Research Areas
5
Contribution Categories
3
Development Frameworks
2
dbreunig Context Engineering Series
2
Advanced Context Engineering for Coding Agents
2
Wide Research: Beyond the Context Window (Manus)
1
Claude Code Best Practices
1
Don't Build Multi-Agents (Cognition)
1
MCP Ecosystem
1
Context7 MCP Server
1
LangChain Context Engineering
1
Context Engineering (Simon Willison)
1
The New Skill in AI is Not Prompting, It's Context Engineering (Philipp Schmid)
1
Manus Context Engineering
1
SWE-grep: RL for Fast Context Retrieval (Cognition)
1
Keywords
rag
8
llm
8
context-engineering
8
ai
7
ai-agents
7
claude-code
6
mcp
4
agent
4
openai
3
developer-tools
3
agents
3
python
3
codex
3
vector-database
3
memory
3
context-window
2
spec-driven-development
2
ai-memory
2
token-optimization
2
typescript
2
meta-prompting
2
embeddings
2
anthropic
2
llms
2
mcp-server
2
long-term-memory
2
agent-memory
2
prompt-engineering
2
chatgpt
2
knowledge
1
knowledge-graph
1
neo4j
1
memory-management
1
open-source
1
amp
1
genai
1
chatbots
1
human-in-the-loop
1
deep-learning
1
humanlayer
1
application
1
language-model
1
opencode
1
graph
1
remix
1
tailwindcss
1
postgres
1
drizzle-orm
1
vite
1
cloudflare-workers
1