Coding & Dev AI Tools

A lightweight CLI that uses embeddings to spot fuzzy code clones without a heavy UI.

A zero‑dependency Bash wrapper that lets you hit LLM APIs from the terminal in a single line.

A zero‑cost, pure‑C implementation of GPT‑2 that lets you run large language models on a single GPU without a heavyweight framework.

Spaced‑repetition for developers that turns AI‑generated snippets into lasting knowledge.

A protocol that lets you ship consistent, version‑controlled prompts across any LLM without rewriting code.

A pluggable command‑line filter that compresses prompts and responses to save LLM tokens without losing context.

A standards‑first, open‑source schema that lets you orchestrate heterogeneous AI agents without vendor lock‑in.

Zot turns vague prompts into production‑ready code while staying lightweight and fully open‑source‑friendly.

A C++/CUDA engine that shaves milliseconds off inference while staying fully open‑source.

A free, plug‑and‑play harness that lets any team turn game telemetry into self‑driving AI in minutes.

A cloud‑first AI pair‑programmer that runs instantly in the browser without any local setup.

Turns drag‑and‑drop designs into native mobile apps without writing a single line of code.

A fully‑managed WordPress platform that builds, optimizes, and scales sites with AI, all in one dashboard.

RunThisLLM lets developers spin up, test and schedule any LLM in seconds, without writing boilerplate code.

Run, fine‑tune and chat with top open‑source LLMs on your own hardware without a subscription.

A Python‑centric ChatGPT UI that lets developers run, debug and fine‑tune code without leaving the browser.

A self‑hosted, schema‑aware LLM platform that lets you run large language models on your own data without vendor lock‑in.

A versatile prompt‑engineering lab that lets you test every OpenAI model in real time.

A single AI assistant that reads, annotates and suggests fixes for any GitHub repository in seconds.

A self‑hosted, plug‑and‑play front‑end for LLMs that lets teams own their data without paying per‑token fees.