Machine Learning middleware
-
@dvcorg/cml
<p align="center"> <img src="https://static.iterative.ai/img/cml/title_strip_trim.png" width=400> </p>
-
@fal-ai/client
The fal.ai client for JavaScript and TypeScript
-
@huggingface/inference
Typescript client for the Hugging Face Inference Providers and Inference Endpoints
-
@langchain/anthropic
Anthropic integrations for LangChain.js
-
@langchain/classic
Old abstractions from LangChain.js
-
@langchain/core
Core LangChain.js abstractions and schemas
-
@langchain/openai
OpenAI integrations for LangChain.js
-
@mlc-ai/web-llm
Hardware accelerated language model chats on browsers
-
amazon-sorftime-research-MCP-skill
Analyze Amazon listings and categories using Sorftime MCP to deliver detailed competitor insights and automated product selection.
-
atlas
Atlas — self-hosted, source-configurable, multi-disciplinary engineering platform for gen-AI, ML, and data work. 30+ OSS Docker Compose services (Ollama, LiteLLM, Supabase, n8n, Airflow, Spark, Weaviate, Neo4j, JupyterHub, Ray, ComfyUI, …) pre-wired behind Kong. Interactive TUI wizard, configurable tracks, one-command launch.
-
atlas.llm
Local AI coding companion in a single Go binary. Bubbletea chat TUI with on-device inference via llamafile, plus one-shot --summarize and --dump modes for turning a repo into LLM-ready Markdown.
-
AtomMind
🧠 Develop specialized reasoning and computation in Math, Physics, Chemistry, and Biology with AtomMind, your lightweight scientific language model.
-
awesome-ai-handbook
A practical guide to AI: from running your first local model to building your own agents. 52 files covering LLMs, Ollama, RAG, prompt engineering, machine learning, AI agents, and local AI tools.
-
ax-studio
Local-first AI workspace for macOS and Windows with cloud providers, local inference, MCP tools, memory, and artifacts
-
be-a-guptaji
Hi, I’m Aryan Baadlas a Data Scientist & Web Developer who loves building data driven solutions and scalable applications. I work at the intersection of machine learning, AI, and web development, transforming raw data into actionable insights and real world products with modular, attractive and presentable designs which are easy to navigate.
-
better-rm
🛡️ Enhance file safety with better-rm, a secure alternative to the rm command that prevents accidental deletions by moving files to the trash.
-
builder-jobs-scraper
Hourly pipeline that discovers, fetches, and classifies engineering jobs from company ATS boards — publishes a curated index to builder-jobs.
-
captainslog-whisper
Convert your voice to text locally using Whisper without sending data to the cloud or requiring accounts.
-
CDM
Distill diffusion models into few-step generators using continuous-time distribution matching.
-
chatgpt
Node.js client for the official ChatGPT API.
-
cli
A Git-first CLI coding agent that turns ideas, issues, and tasks into real code changes.
-
cli-llm-chat
Welcome to the digital thunderdome, you keyboard-smashing lunatics! This ain't your grandma's chatbot – it's a CLI-powered, LLM-fueled beast! And guess what? It also supports Telegram integration right out of the box. Get ready to unleash the madness!
-
ComfyUI-Segformer_Ultra_Fast
🖼️ Run Segformer efficiently for rapid image and video segmentation with minimal setup. Streamline your workflow and enhance your projects quickly.
-
dgx-spark-llm-platform
Self-hosted multi-user LLM platform for the NVIDIA DGX Spark: OpenAI-compatible API (vLLM + LiteLLM), per-user keys & budgets, self-service portal with playground and an AI support assistant.
-
dots.ocr-fix-demo
🖼️ Upload images to experience accurate multilingual OCR results with the enhanced dots.ocr model and fix processor loading issues seamlessly.
-
dynet
Dynamic Neural Network Toolkit
-
eco-mesh-sdk
Mica Plugin 2026: Route AI Inference Through Green Energy MVM Nodes to Cut Token Costs by 60%
-
epochix
Visual storytelling for deep learning training runs.
Machine Learning Python -
fak
fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.
-
GEO-AI
Optimize websites for AI search engines with a universal TypeScript engine supporting Next.js, NestJS, WordPress, and Shopify integration.
-
gglib
Download, manage, and chat with LLMs, completely private and local.
-
ggml
Tensor library for machine learning
-
Grade
🌍 Generate realistic, dynamic environments for robotics research using Isaac Sim. Manage simulations, control robots, and customize workflows easily.
-
homely-vibes
Modular IoT home automation — Tesla Powerwall, Rachio/Flume, August locks, Samsung Frame, node monitoring, and VS Code tools
-
hyparquet
Parquet file parser for JavaScript
-
immich-ml
Machine learning service for Immich — handles facial recognition, image classification, and semantic search using ONNX models.
-
InstinctMJ
Provide a native mjlab environment for Project-Instinct to support reinforcement learning in humanoid whole-body control tasks.
-
kry
Tamper-evident, stranger-verifiable receipts for LLM cost-savings — anyone can recompute your caching/routing savings math offline, no trust in your dashboard required. Pure stdlib, zero-dependency.
-
langchain
Typescript bindings for langchain
-
leviathan
Discover and enumerate subdomains with a fast, multi-phase recon engine built from the ground up for syscall-level efficiency
-
llamaindex
<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>
-
llm-pricing
Track standardized pricing for 300+ LLM APIs in one JSON file for cost tools, comparisons, and billing dashboards
-
llm-systems-manager
LLM Systems Manager — real-time observability and control for LLM systems
-
maithili-news
Maithili-news-gnews is a project aimed at automating the fetching of news from the GNews API, translating it into the Maithili language, and then classifying it using a machine learning model. The classified news articles are then displayed on a website using Streamlit.
-
mcp-superset
Extend Apache Superset with Model Context Protocol to integrate and manage machine learning models efficiently within data dashboards.
-
mlguard
Perform pre-deployment checks for ML models to detect data drift, performance drops, and latency issues, preventing faulty deployments.
-
MLJobSearch2025
📊 Discover top AI companies and access 100+ ML interview questions to enhance your job search in machine learning for 2025.
-
nano-banana-cli
🖼️ Generate and edit images with ease using the Nanobanana CLI, powered by AI and Google's Gemini models for advanced image manipulation.
-
nano-banana-pro-prompts-recommend-skill
🖼️ Generate stunning images easily with intelligent prompts from a database of 6000+ curated options, tailored to your specific needs.
-
NanoBanana-PPT-Skills
🎨 Generate high-quality PPTs with AI, featuring smart transitions and interactive playback for seamless presentations and engaging visuals.
-
ncnn
High-performance neural network inference framework
-
Netron
Visualiser for neural network, deep learning, and machine learning models
-
Neural Network
An addon for Godot that provides functionality for working with neural networks.
Machine Learning Godot -
notion-md-crawler
A library to recursively retrieve and serialize Notion pages with customization for machine learning applications.
-
ollama-mesh
The control plane for self-hosted AI inference. Warm-state GPU routing, multi-runtime orchestration across Ollama, vLLM, llama.cpp, and TGI. Single Go binary. Apache-2.0.
-
ONNX Runtime
Cross-platform inference and training accelerator for machine-learning models.
-
OpenProcessor
Self-hosted visual AI processing engine for object detection, face recognition, CLIP embeddings, OCR, and vector search. Built on FastAPI, NVIDIA Triton Inference Server, and TensorRT.
-
ort
A safe Rust wrapper for ONNX Runtime 1.24 - Optimize and accelerate machine learning inference & training
Machine Learning Rust -
pdf2md
PDF2MD - Batch convert PDF papers to clean Markdown. Extracts titles, sections, and body text only; drops figures, formulas, headers/footers, and references. Powered by docling (local AI) with GPU acceleration.
Machine Learning Python -
pm-tools-templates
🚀 Next-generation AI-powered project management ecosystem with 80+ proven templates, predictive analytics, blockchain automation, and intelligent workflows. Transform from static templates to data-driven insights with ML forecasting, smart contracts, and real-time collaboration. Open-source foundation with SaaS monetization.
-
RecIS
🔍 Enable powerful recommendation systems with RecIS, a deep learning framework for large-scale computing, designed for optimal model training and performance.
-
saas-churn-prediction
🔍 Predict customer churn with a machine learning system that identifies at-risk clients and recommends tailored retention strategies for better ROI.
Machine Learning Python -
SnifTern.ai
🐙 SnifTern.ai is an AI-powered internship fraud detection platform built with Flask. It uses machine learning to identify fake postings and verify company legitimacy.
-
SPFgraph
Run LLMs locally in your terminal — .pt GPT-2 checkpoints + GGUF, live dashboard
-
squish
⚡️ The fastest way to run local LLMs on Apple Silicon — sub-second model loads, beats Ollama on throughput, tail latency, and full-response time. OpenAI/Ollama-compatible. No cloud, no API keys.
-
stripped-vocal-remover-windows
The easiest way to install the Stripped Vocal Remover on Windows. This auto-installer fixes dependency errors, bypasses Hugging Face logins, and provides a beginner-friendly local UI for audio separation.
-
tqnn-anyengine-api
🔹 Access the TQNN AnyEngine API to transform structured data into high-dimensional inference outputs across various modes like EEG, Finance, and more.
-
Transformers
State-of-the-art machine learning models for text, vision, and audio — pretrained and ready to use.
-
transformers_dart
🤖 Run state-of-the-art Machine Learning models in Dart with transformers_dart—cross-platform, serverless, and based on Hugging Face's transformers.
-
uzdabrawza
The Anal-Queen of AI Browser Automation 🏴☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.
-
vibe-tuning
Calibrate your Claude Code assistant to diagnose and fix recurring errors by saving permanent root cause patterns after every mistake.
-
zero-operators
Autonomous AI research team: write a plan.md, spawn agents, train, verify, and deliver a clean ML repo.
-
GLM-OCR-Demo
-
KindleVibe
-
shenxiangzhuang.github.io
-
vless-xhttp