Back to browse
GitHub Repository
125 starsPython

How context engineering works, a runnable reference

by linsys·Apr 17, 2026·46 points·15 comments

AI Analysis

MidShip It

Five-component architecture adds output enforcement to standard RAG pipelines.

Strengths
  • Clear five-component breakdown separates retrieval from output enforcement.
  • Runnable Bedrock examples avoid abstract theory without working code.
  • Comparisons folder shows concrete differences between RAG and context engineering.
Weaknesses
  • Requires AWS Bedrock setup and Claude FTU form approval to run.
  • Conceptual rename of existing orchestration patterns found in LangChain.
Category
Target Audience

AI engineers building enterprise RAG systems

Similar To

LangChain · LlamaIndex · DSPy

Post Description

I've been presenting at local meetups about Context Engineering, RAG, Skills, etc.. I even have a vbrownbag coming up on LinkedIn about this topic so I figured I would make a basic example that uses bedrock so I can use it in my talks or vbrownbags. Hopefully it's useful.

Similar Projects

Education●●Solid

CEL by Example

CEL by Example fills a real doc gap for a language used by Google Cloud, Firebase, and Envoy.

Solve My ProblemCozy
bufbuild
84403mo ago
Developer Tools●●Solid

Self-Integrating AI Agent

This repo actually wires an OpenCode agent to Membrane so the agent can find existing connectors and synthesize missing ones on the fly — intent becomes action, not just a toy prompt example. It ships a runnable Next.js UI and clear quick-start steps, which makes the idea tangible fast; what I'd like to see next are security notes, more examples of complex connector synthesis, and tests that prove the approach scales beyond demos.

Bold BetBig Brain
hcle25
103mo ago
Infrastructure●●●Banger

Sayiir – A simple durable workflow engine (Rust core, Python/Node.js)

Checkpoint-based recovery beats determinism constraints; embed without separate server, unlike Temporal/Airflow.

Big BrainDark HorseSolve My Problem
ybsoft
103mo ago
Developer Tools●●Solid

SpecFact CLI – reverse engineer Python repos into enforceable specs

This repo actually wires the specfact CLI to a tiny, reproducible codebase so you can import-from-code, generate .specfact bundles, and run enforcement presets with one-liners. The backlog-sync adapter and a deliberately buggy sidecar demo make failure modes easy to exercise, and the README lists exact smoke commands and logs to verify results. Inferred specs will always risk false positives, but the project shows practical artifacts (change_tracking, results logs) rather than theory.

Niche GemSolve My Problem
noldai
113mo ago