New This Month

Frigate: Local AI Object Detection for Security Cameras (GitHub, Scanned)

A self-hosted camera recorder that spots people, cars and animals locally, built for Home Assistant.

Buzz: Transcribe Audio Offline With Whisper (GitHub, Scanned)

A desktop app that transcribes and translates audio and video offline with Whisper, no account needed.

TRELLIS.2: Turn One Image Into a 3D Model (GitHub, Scanned)

Microsoft's open 4B model that turns a single image into a detailed, textured 3D asset.

Stability Matrix: One-Click Installer for Stable Diffusion UIs (GitHub, Scanned)

Install, update and launch ComfyUI, Forge, InvokeAI and more from one app, with one shared model library.

Ultralytics YOLO: Object Detection in a Few Lines (GitHub, Scanned)

Detect, segment, track and estimate pose in images, video and webcams with pretrained YOLO models.

PaddleOCR: Turn Images and PDFs Into Structured Text (GitHub, Scanned)

Baidu's OCR toolkit that reads text in 100+ languages and turns documents into Markdown or JSON.

WebLLM: Run Language Models Inside the Browser (GitHub, Scanned)

An engine that runs open language models entirely in the browser on WebGPU, with an OpenAI-style API.

llamafile: An LLM in a Single Executable File (GitHub, Scanned)

Run a language model from one downloaded file on macOS, Windows, Linux or BSD, with nothing to install.

Page Assist: Chat With Local AI on Any Web Page (GitHub, Scanned)

A browser extension sidebar and web UI for local models like Ollama, including chat with the current page.

Read Frog: AI Bilingual Translation for Learning Languages (GitHub, Scanned)

A browser extension that translates pages side by side with AI and turns what you read into flashcards.

LLM: Prompt Any Model From Your Terminal (GitHub, Scanned)

Simon Willison's CLI for prompting hundreds of models, with every exchange logged to SQLite.

Prompt Optimizer: Rewrite and Test Prompts for Better AI Output (GitHub, Scanned)

Rewrites your prompts with an AI model, then lets you test and compare the results side by side.

promptfoo: Test and Red-Team Your LLM App (GitHub, Scanned)

Tests your prompts across models, scores the answers, and attacks your AI app to find weak spots.

Langfuse: See What Your LLM App Is Actually Doing (GitHub, Scanned)

Self-hostable tracing, prompt management and evaluations for apps built on language models.

LiteLLM: One API for 100+ Language Models (GitHub, Scanned)

Call 100+ model providers through one OpenAI-style API, with keys, budgets and logs.

Repomix: Pack a Whole Repo Into One File for AI (GitHub, Scanned)

Packs a codebase into one AI-friendly file with token counts, ready for Claude, ChatGPT or Gemini.

PR-Agent: Open-Source AI Code Review for Pull Requests (GitHub, Scanned)

An open-source AI reviewer that describes, reviews and suggests fixes on your pull requests.

Resume Matcher: Tailor Your Resume to Every Job With AI (GitHub, Scanned)

Tailors your resume and cover letter to each job description, scores the match, exports a PDF.

Copilot for Obsidian: AI Agents Inside Your Vault (GitHub, Scanned)

An Obsidian plugin that brings AI chat and agents like Claude Code and Codex to your notes.

Playwright MCP: Let an AI Agent Drive a Real Browser (GitHub, Scanned)

Microsoft's MCP server that lets AI agents browse, click and test real web pages through Playwright.

goose: An Open-Source AI Agent for Desktop and Terminal (GitHub, Scanned)

A general-purpose AI agent for desktop and terminal that runs commands, edits files and uses MCP tools.

ccusage: See What Your Claude Code Usage Really Costs (GitHub, Scanned)

Reads Claude Code, Codex and other agent logs locally and reports tokens and cost by day or session.

GPT Researcher: An Open Deep-Research Agent With Citations (GitHub, Scanned)

An open-source research agent that searches the web and your files and writes a cited report.

ConvertX: Self-Hosted File Converter for 1,000+ Formats (GitHub, Scanned)

A self-hosted web app that converts images, video, documents and e-books between 1,000+ formats.