Go
How to connect neural network vision to home cameras with Unblink
Unblink V2 brings vision-language models to home RTSP cameras, enabling semantic search and natural language queries instead of manual timeline scrubbing.
AI / ML
94 projectsMachine learning frameworks, data tooling, and the libraries powering modern AI applications.
JavaScript
Documind Turns Messy PDFs and Scans into Clean JSON
A Node.js library that extracts structured JSON from messy PDFs and scans using AI, supporting both cloud and local vision models.
TypeScript
Interactive Geopolitical Events Map Built with Next.js and Valyu API
A look at globalthreatmap—an interactive command center for monitoring geopolitics, military bases, and global incidents in real time built with Next.js and Valyu API.
JavaScript
How to Turn the Zotero Library into a Personal Search Engine Based on Local Neural Networks
Turn your Zotero library into a powerful local search engine with PapersGPT—a C++ indexing plugin that uses local AI models for fast, private document retrieval.
Vue
How to render streaming Markdown from neural networks without flickering and freezes
Standard Markdown renderers weren't built for live token streams. Markstream solves flickering, broken code blocks, and hanging formulas when rendering AI output.
HTML
How to Build a True Six-Axis Robot Manipulator on a 3D Printer
PAROL6 is a desktop six-axis robot arm that can be 3D printed at home. It features industrial-grade kinematics, ROS 2 support, and an active community building extensions.
Python
How to Turn a Mountain of Chaotic Documents into Rigorous Knowledge Graphs
Hyper-Extract converts messy documents into structured knowledge graphs and typed data using ready-made templates, eliminating the need for complex prompt engineering.
C-sharp
How to Connect Claude and Cursor Directly to Unity via MCP
Unity-MCP connects Unity with Claude and Cursor via the Model Context Protocol, giving AI assistants direct access to scenes, assets, and the Roslyn compiler.
TypeScript
How Magnitude Automates the Browser Through Vision Instead of Brittle Selectors
Magnitude uses visually grounded LLMs to automate browsers through direct computer vision, achieving 94% success on WebVoyager without relying on fragile selectors.
Rust
How to Stop Juggling Accounts in Cursor, Windsurf, and Copilot
Stop juggling multiple AI editor accounts. Cockpit Tools consolidates Cursor, Windsurf, Copilot and more into one dashboard with quota tracking and one-click switching.
TypeScript
How to get multiple AI agents to work together in one repository without losing context
Atlas is a local workspace and version control system for AI agents that ties their memory together and links every commit to the session where it originated.
Go
How to Tame the Neural Network Zoo with TokenHub
When teams start integrating neural networks, API key management descends into chaos. TokenHub—a private AI gateway written in Go—centralizes access to dozens of LLM providers with unified OpenAI-compatible endpoints, role-based access, smart routing, and cost tracking.
TypeScript
How to Connect Thousands of Ready-Made Parsers to Your LLM
Apify's MCP server lets AI agents tap into thousands of ready-made cloud scrapers through a unified tool-calling interface, eliminating the need to build custom scraping infrastructure.
Python
How to Tame a Dozen Coding Agents and Set Them Up to Work Together in Omnigent
Omnigent is an open-source Python meta-framework that orchestrates multiple AI coding agents under one roof with unified interfaces and security policies.
TypeScript
How holaOS works and why it's more convenient for working with multiple AI agents
holaOS combines multiple AI agents in one desktop environment with shared context, local memory, and interactive panels for seamless workflow.
Go
How to Stop Neural Networks from Writing Bad Go Code
Stop neural networks from generating bad Go code with cc-skills-golang — a curated set of Agent Skills for idiomatic Go development.
Go
How to Make AI Find Real Bugs in Pull Requests Instead of Generating Trivial Comments
PR-AF is an open-source tool for deep code auditing that builds dynamic agent graphs, extracts AST trees, and verifies each finding for falsifiability.
Jupyter
How to Prepare for AI and ML Interviews at Big Tech Without Chaos in Your Head
A developer turned his interview prep into a structured repository and landed offers at Meta, Google, Amazon, Apple, and Roku. Here's what's inside.
C
Autonomous AI Assistant on ESP32 Board for $5
MimiClaw runs a full AI agent loop on an ESP32-S3 microcontroller for just $5, with local memory, Telegram integration, and autonomous task scheduling.
Python
All Tools for Vector Search and LLM in One Python Library
txtai is an all-in-one Python library combining vector database, hybrid search with SQL, graph analytics, and LLM orchestration for RAG pipelines.
Python
SD.Next — A Replacement for Automatic1111 for Those Who Need More Than Standard WebUI
SD.Next is a fork of Automatic1111's WebUI that adds cross-platform support, efficient resource management, and built-in tools for image and video generation.
Python
Full SEO Audit Right in the Terminal with the Claude SEO Plugin
A CLI extension for Claude Code that automates SEO audits, generates actionable roadmaps, and validates technical issues directly in the terminal.
Python
How to Get Rid of the Container Zoo When Building AI Agents with SIE
Building AI agents with local LLMs? SIE (Superlinked Inference Engine) consolidates multiple inference servers into one, cutting GPU costs and simplifying your container setup.
Python
Why Vector Databases Won't Save Agents from Auditors and How Semantica Solves This
Vector databases and standard RAG can't answer auditor questions about AI decisions. Semantica adds deterministic graphs, rules, and audit trails.