Tutorials Intermediate
MiniMax M3: Master 1M-Token Long Context With MSA
MiniMax M3 hands-on: MSA sparse attention plus real 1M-token long context, with runnable Python.
10 min read·Kodetra Technologies
TodayGuides
AI Guides for Builders
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Tutorials 
Tutorials Intermediate
Handle Fable 5 Refusals With Fallbacks in Python
Catch Claude Fable 5's stop_reason refusal and auto-retry on Opus 4.8 without breaking production.
10 min read·Kodetra Technologies
Yesterday
Tutorials Intermediate
Gemma 4 Tool Calling: Build a Local AI Agent
Run Google's open Gemma 4 locally with Ollama and wire up real function calling for an agent.
10 min read·Kodetra Technologies
Yesterday
Tutorials Intermediate
Claude Opus 4.8 Fast Mode: 2.5x Faster Output in Python
Use speed:"fast" on Claude Opus 4.8 for up to 2.5x faster output, with a safe rate-limit fallback.
9 min read·Kodetra Technologies
2d ago
Tutorials Intermediate
Build an Apple-Style Multi-Model AI Router in Python
WWDC let iPhone users pick ChatGPT, Gemini, or Claude. Build the same model router in Python.
9 min read·Kodetra Technologies
3d ago
Tutorials Intermediate
MiniMax M3 Tool Calling: Build an Agentic Loop in Python
Wire MiniMax M3's OpenAI-compatible API into a real tool-calling agent loop.
8 min read·Kodetra Technologies
3d agoMore guides like this?
New AI guides for builders, in your inbox. Free.
Join 2,013 builders reading daily.
Tutorials Intermediate
Run a Local LLM on Android with llama.cpp + Vulkan
Compile llama.cpp with Vulkan in Termux and run a quantized LLM on your Android GPU, no root.
9 min read·Kodetra Technologies
6d ago
Tutorials Intermediate
MAI-Code-1-Flash in Python: 5B Coder Beats Haiku 4.5
Call Microsoft's June 2 coding model via OpenRouter for cheap, fast refactors.
10 min read·Kodetra Technologies
9d ago
Tutorials Intermediate
Agent Harness in Python: Give LLMs Shell and File Access
Build a safe local agent harness with shell, files, approvals, and logs in Python.
10 min read·Kodetra Technologies
9d ago
Tutorials Intermediate
Claude Opus 4.8 Effort Levels: A Hands-On Python Guide
Tune token spend on Opus 4.8 with the effort parameter. Runnable Python, real I/O, real numbers.
7 min read·Kodetra Technologies
11d ago
Tutorials Intermediate
GLM-4.7 in Python: Build a Cheap Coding Assistant
Use Zhipu's GLM-4.7 through the OpenAI SDK to build a tool-calling coding assistant for pennies.
9 min read·Kodetra Technologies
16d ago
Tutorials Intermediate
Qwen 3.7 Max: Drop-In Anthropic SDK Swap in Python
Point the Anthropic SDK at Qwen 3.7 Max with one base-URL change: 1M context, thinking, caching.
8 min read·Kodetra Technologies
16d agoPage 1 of 2