Skip to main content
Watch: Grok Bot Built My AI Video Arena While I Tested 8 Models

LLM

33 items

26 posts, 7 tools

Tool
Browser Harness

Self-healing browser automation harness that lets LLMs complete any browser task. 5,000+ stars in under a week.

Tool
Ollama

The easiest way to run LLMs locally. One command to pull and run any model. OpenAI-compatible API. 52M+ monthly downloads. Supports GGUF, Safetensors, and custom Modelfiles.

Tool
LM Studio

Desktop app for discovering, downloading, and running local LLMs. Clean chat UI, OpenAI-compatible API server, and automatic GPU detection. MLX engine optimized for Apple Silicon.

Tool
Jan

Open-source ChatGPT alternative that runs models fully offline. Desktop app with local models, cloud API connections, custom assistants, and MCP integration. Apache 2.0 licensed.

Tool
GPT4All

Private local AI chatbot by Nomic. MIT licensed with 77K+ GitHub stars. LocalDocs lets you chat with your own files. Runs on Windows, macOS, and Linux; latest release is v3.10.0 from February 2025.

Tool
LocalAI

Open-source OpenAI API replacement. Runs LLMs, vision, voice, image, and video models on any hardware, no GPU required. 60+ backends. Distributed mode for scaling.

Blog
Mercury 2: The LLM That Doesn't Generate Like an LLM

Mercury 2 from Inception Labs is a diffusion reasoning LLM that refines outputs in parallel at over 1,000 tokens per second. How it works and where it fits.

Blog
Claude Skills: A technical deep dive into Anthropic's new approach to AI context management

Claude Skills load instructions, scripts and resources progressively so context stays small. A technical deep dive into SKILL.md, the API and Claude Code use.

Blog
GPT-5: OpenAI's Most Capable Model

GPT-5 routes each query by complexity instead of making developers pick a reasoning mode. Its benchmarks, front-end coding gains and four API models explained.

Blog
Diffusion Language Models: How Mercury Changed the LLM Speed Game

Diffusion language models like Inception Labs' Mercury draft a whole response and refine it instead of going token by token. See why that makes them so fast.

Blog
Unstract: Open-Source AI Document Parsing at Scale

Unstract is an open-source, no-code platform that uses LLMs to extract structured JSON from PDFs, invoices and scans. How Prompt Studio and self-hosting work.

Blog
Microsoft PHI-4: A 14B Parameter Model That Rivals Models 5x Its Size

Microsoft PHI-4 is an MIT-licensed 14B model that matches Llama 3.3 70B on key benchmarks. See its specs, how to run it locally with Ollama, and when to use it.

Blog
Llama 3.3 70B: Meta's Cost-Effective Frontier Model

Llama 3.3 70B delivers 405B-class performance at a fraction of the cost. See the benchmarks, pricing versus GPT-4o, where to run it, and when to pick it.

PreviousPage 2 of 2
AI Development Stack

Get Smarter About AI Dev

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.

One email per weekReal code, not theoryFree forever