The Free AI Stack: What $0 Gets You
A capability map of what's genuinely free from AI providers in 2026: chat, APIs, image generation, speech tools, and coding help, with the real quotas.
Tag: ai
All the articles with the tag "ai".
Agentic Browsers: Browser-Use & Skyvern Reviewed
Browser-Use and Skyvern let LLMs drive real browsers via natural language goals. Here's what they can actually do, where they break, and when Playwright is still the right call.
Local Voice Assistant: Whisper + Piper + Home Assistant
Ditch Alexa and Google Home. Build a fully local voice assistant with Whisper STT, Piper TTS, and Home Assistant using the Wyoming protocol.
Your Agent Doesn't Need a Shell
Coding agents get unrestricted shell access by default because it's easy, not because they need it. Here's the short list of what actually breaks without one.
Llamafile: Single-Binary LLMs That Actually Just Run
Llamafile bundles llama.cpp + Cosmopolitan libc into one portable binary that runs on Linux, macOS, Windows, and BSD with zero install.
DeepSeek V4 Flash: 28 Cents a Million
DeepSeek V4 Flash 0731 hits 50 on the independent intelligence index at $0.14/$0.28 per million tokens. Same weights as the preview, redone post-training.
Where Should Your Coding Agent Run?
Claude Code and other AI coding agents need somewhere to run. Compare laptop, Docker, throwaway VMs, and Cloudflare Workers on blast radius, cost, and setup.
DIY Perplexity: SearXNG + Local LLM = Private Web Search
Replace Perplexity with SearXNG + a local LLM for private, cited web search. Full Perplexica/Morphic deploy walkthrough, Ollama, latency tradeoffs.
Local Coding Agents Need Less Context
Local coding agents don't fail because your 27B model is too small. They fail because you let 200K tokens of garbage pile up in the context window. Cap it low.
LM Studio vs Jan vs GPT4All: Desktop LLM Clients
LM Studio, Jan, and GPT4All compared, the best desktop LLM clients for local AI chat on Mac, Windows, and Linux in 2026.
RAGAS: Evaluating RAG Without Vibes
Stop guessing if your RAG pipeline works. RAGAS gives you reproducible metrics: faithfulness, answer relevance, context precision and recall.
KV Cache Quantization: Free LLM Context, Almost
KV cache eats your VRAM at long context, not the weights. Q8/Q4 KV quantization in llama.cpp and vLLM cuts it 2-4x with almost no quality hit.