LLM
33 items
26 posts, 7 tools
Self-healing browser automation harness that lets LLMs complete any browser task. 5,000+ stars in under a week.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.