Repository index
6792 AI, ML and Web3 projects · page 20 of 68
- SYMFORCE: SPEED AND ACCURACY
Symforce speeds up symbolic computations, generates efficient code, and solves nonlinear optimization problems for robotics.
- Claude Code Plugins
A collection of plugins for extending Claude Code: custom commands, agents, hooks, and MCP servers.
- LONG-TERM MEMORY FOR AI AGENTS
powercontext gives agents long-term memory and context handoff between sessions. Works with Claude Code and Codex. Python, 1.4k GitHub stars.
- KUBERNETES MCP SERVER FOR AI
Model Context Protocol server for Kubernetes and OpenShift, enabling integration of AI agents with clusters.
- Full LLM Course
The repository contains step‑by‑step training on working with large language models, from prompt engineering and RAG to AI agents, fine‑tuning, deployment, and interview preparation for top companies.
- OFFLINE AI ASSISTANT FOR SURVIVAL
Local AI assistant with survival, medical, and technical knowledge base. Works offline, shows sources and reasoning.
- Build Your AI Agent
Step-by-step guide to creating your own AI agent from scratch.
- Content system for growth
A workflow that turns every post into a calibrated experiment: assessment, blind forecast, retrospective, evolution—a system, not luck.
- PaperBanana: Scientific Visualization Generation
An open-source implementation and extension of Google Research PaperBanana for automating the creation of academic figures, diagrams, and scientific visualizations.
- Repowise — Codebase Intelligence
Auto-generated documentation, Git analytics, and dead code detection for AI engineering teams via MCP.
- UAGENTS — CREATE AGENTS FAST
A fast and lightweight Python framework for creating decentralized agents.
- DURABLE AGENTS WITH MEMORY
Project agents provides a durable process for each agent with preserved memory after restart. Implemented in TypeScript, it uses the actor‑model and durable execution.
- PAGE LM TRANSFORMS LEARNING
PageLM turns learning materials into interactive quizzes, flashcards, notes, and podcasts.
- Golang Skill Set for Agents
The project provides ready-made agentic skill modules in Go, enabling quick creation of intelligent agents with LLM support and task planning.
- CLAUDE-OSINT: RECON OPERATOR
Claude-OSINT turns Claude into a powerful external scout: 90+ modules, attack templates, and credential validators for red‑team.
- DEEIX-CHAT: AI Workspace for Business
DEEIX-Chat — enterprise AI workspace for model routing, multimodal chat, file work, tools, billing, and identity management.
- DORY: LOCAL ENVIRONMENT FOR APPLE SILICON
Dory provides a full-featured local development environment for Apple Silicon, combining Docker, Compose, Kubernetes and virtual machines. It includes policy‑bound agent sandboxes for secure code execution and AI agents.
- draw.io Diagram Generator
Generate diagrams from text using 6 templates and quality checking.
- RULEGO RULE SPEED
RuleGo is a lightweight, high-performance rule engine for Go that enables orchestration of embedded components.
- AGENT VISUAL ANALYTICS FRAMEWORK AVA
AVA — framework for visual analytics built for AI agents. Agents autonomously explore data, build charts, and find insights. 1600+ stars on GitHub.
- GRAPHICAL RAG AGENT FOR COMPLEX QUESTIONS
Controllable‑RAG-Agent is an advanced Retrieval‑Augmented Generation system for answering complex questions. It uses a graph‑based search algorithm and integrates with LangChain/LangGraph, allowing pipeline configuration and source control.
- TOP SOLUTIONS FOR LLM AGENTS
Curated list of top frameworks for building agents on large language models. 1.5K stars, Python.
- MCPJUNGLE MANAGE SERVERS
MCPJungle unifies all your MCP servers in a single interface, simplifying connection and management. Ideal for developers and DevOps.
- AIDE ML AI Code Agent
Find the perfect code and instantly generate it with AIDE – an agent that learns and creates suitable implementations.
- CORE: Personal AI Operating System
core — your personal AI operating system on TypeScript, uniting agents, tools, and automation in one environment.
- MEMORYOS — MEMORY FOR AI AGENTS
MemoryOS provides a memory operating system for personalized AI agents, learning from their interactions.
- LLM EVALUATION SURVEY
Official repository page for the survey paper on evaluation of large language models.
- HUMANIZE - TURN IDEAS INTO CODE
The humanize project helps quickly turn automated ideas into working solutions using simple shell scripts.
- PPTX Generation Skill
A Claude Code skill that creates correct PPTX presentations from a text prompt, following formatting rules and using 38 ready‑made SlideSpecs. Automatic verification of the result is built‑in.
- Paper Figure Gallery
A gallery of 3,516 Figure 1 teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI papers (2023-2026) with tier badges and FigureForge-powered retrieval-augmented drafting.
- EMPRYO: AST Surgeon of Code
Empryo edits code through AST, not strings, providing a living genome for the project.
- TinyML LLM for cheap boards
Running a language model with 1B parameters on a $10 device with 256 MB RAM in C.
- TRACK CLAUDE USAGE
Local dashboard for tracking tokens, cost, and Claude Code sessions. Progress bar for Pro and Max!
- MANAGE KUBERNETES VIA AI
MCP server for managing Kubernetes via AI agents. Automate deployment and monitoring of clusters using language models.
- WAKU — Native Solution for Agents
Waku is a native app that unifies all your AI coding agents in one environment. Fast, secure, and built on Rust.
- ANYJEV TURNS LLM INTO JEV-MODEL
AnyJev converts any LLM into a Jev‑style decision model, outputting typed decisions and real probabilities without requiring retraining. The project is actively developed and ready for integration into Python projects.
- OpenAdapt - Boundless AI Process
OpenAdapt — an open platform for generative process automation based on LLM, LAM, and VLM models. Python, 1.6k stars, AI-first approach to RPA.
- Middleware OpenWolf
More precise context and lower token consumption as open middleware for Claude Code.
- Agent Apprenticeship - Teaching AI
The project creates a living ecosystem where AI agents learn on real tasks through iterative cycles and exchange of training signals.
- EXTRACTTHINKER DOCUMENT INTELLIGENCE
ExtractThinker — an ORM‑style library for LLM integration, including LangChain and LlamaIndex, that streamlines parsing of PDF, DOCX and images, performs layout and analysis and OCR, and provides tools to build flexible document workflows.
- MotionMaxxing Video Enhancer
MotionMaxxing upgrades AI‑slop videos with designer‑level color grading, easing, and motion blur for a polished, film‑ready look.
- Lotus: Accelerating AI Processing
Optimized LLM data processing up to 1000× faster, with simple Pandas syntax. 1.6k ★, Python.
- PUPPYONE - AI CONTEXT DRIVER
A platform for managing AI-agent contexts, allowing easy data connection and improving their responses.
- Rapid Decision Model
A 0.8B‑parameter open‑source model that outputs calibrated probabilities for choosing between arbitrary options. It runs locally and uses swappable LoRA adapters for domain‑specific fine‑tuning.
- AI - Building Future with Stripe
A platform for rapidly building AI products with Stripe integration, from prototype to monetization in minutes.
- Type-Safe SQL Imports
Import .sql files directly into TypeScript with full type inference and zero code generation.
- LLM FOR VULNERABILITY DETECTION
The most complete index of research on using LLM for detecting vulnerabilities in code — articles, datasets and benchmarks.
- ONE BINARY — ALL APPLICATIONS
A single Go binary installs and runs self-hosted alternatives to paid SaaS. No Docker needed — terminal dashboard for you, simple commands for AI agents. Replace subscriptions with local services in minutes.
- CCX: Proxy for AI APIs
Lightweight proxy server for Claude, Codex, and Gemini API with request routing and management support.
- LOCAL AI FOR MAC OFFLINE
Nativ runs open LLMs locally on Apple Silicon. No data ever leaves your Mac. Built on MLX and Swift.
- NVIDIA GPU METRICS FOR PROMETHEUS
Exporter of NVIDIA GPU metrics to Prometheus in Go. Monitoring temperature, utilization, and memory via nvidia-smi.
- Type-Safe SQL Imports for TypeScript
Import .sql files directly into TypeScript with full type inference and zero code generation.
- VIBETHINKER: 1.5B Model
Tiny model with powerful logical reasoning — Diversity-Driven Optimization awakens the mind of a large LLM. 577 ★ already!
- OPENCLAW-TERMUX: AI ON YOUR PHONE
Launch the OpenClaw AI gateway on Android — a Flutter app with terminal, web panel, and one‑click install. Also available as a Termux package.
- UZU: Powerful Engine for AI Models
High-performance inference engine for AI models in Rust. Fast, reliable, efficient.
- AGMSG - CROSS-VENDOR MESSENGER FOR CLI-AGENTS
agmsg lets Claude Code, Gemini, Copilot, and Codex communicate in a single team via simple Bash and SQLite — without daemons or external frameworks.
- UCCL: GPU Communication at Max
A fast library for efficient data exchange between GPUs: collective operations, P2P, and inference acceleration.
- LLM Inference on AWS Trainium
Open-source LLM inference engine for AWS Trainium featuring NKI megakernels, 1M-token context, and OpenAI-compatible API.
- AGENTLY: SIMPLIFYING GEN-AI DEVELOPMENT
Agently — a Python framework for rapid creation of GenAI applications: simple code, event-driven flow, and easy model swapping.
- OPENSERP — AI SEARCH API SELF-HOSTED
Self-hosted SERP API that renders Google, Bing, Yandex and other search engine results with page extraction.
- AI-DEV-KIT FOR CODING AGENTS
Databricks Toolkit from Field Engineering — everything for working with AI agents in Python.
- ATTENTION-SPAN: HUMAN AGENT
The attention-span library makes Claude Code output more human and ADHD‑friendly, reducing token noise and increasing focus.
- Nano Banana Pro Prompts
AI skill for OpenClaw and Claude Code — recommendations from 10,000+ Gemini prompts for image generation. Smart search, remixes, examples.
- OFFICIAL SWIFT SDK FOR MCP
Official Swift SDK for Model Context Protocol servers and clients. Developed in collaboration with Apple. Simplifies AI agent integration with tools and data.
- PRETTY-MERMAID-SKILLS - MERMAID DIAGRAM GENERATION
Convert text into beautiful Mermaid SVG or ASCII diagrams directly in the terminal. 15 themes, 6 diagram types, batch CLI, no browser required.
- Academic Presentation Skill
A Claude skill that generates academic slides with mandatory action headings, a structured argument, and proper citations.
- TUYAOPEN – AI+IoT FRAMEWORK IN C
TuyaOpen is a framework for rapid integration of AI agents with IoT devices on T2/T3/T5AI and ESP32 platforms, written in C.
- MELDWORK: PLATFORM FOR AGENTS
Meldwork — local-first AI‑agent workspace for multi‑agent collaboration. It provides orchestration, scoped permissions, evidence‑aware runs and human‑in‑the‑loop decisions.
- BUILD YOUR AI COMPUTER
The project helps you build your personal AI computer with open-source code and support for autonomous agents.
- MCP-REBORN: MINECRAFT MODIFICATION
A tool for creating modified Minecraft clients and exploring its code. Supports versions 1.13–26.2.
- SECOND BRAIN OS: SELF-LEARNING.
second-brain-os is an AI-powered second brain that maintains itself. The project offers a thorough full guide, the starter vault, agent skills and scripts for a self-organizing knowledge base in Claude Code and Obsidian.
- GAWKBOT: AI-TEAM IN TERMINAL
The project lets you quickly spin up a personal office of AI agents working together on a shared context. Supports Claude Code, Codex, OpenClaw, OpenCode and any local LLMs.
- AI Video Replacement Workflow
Combines depth maps, SAM segmentation, face meshes, and audio to replace characters/objects in video using Seedance, with a local UI for input prep, mask review, and export.
- DUCKLE: POWERFUL LOCAL ETL STUDIO
Open-source local ETL/ELT studio with 360+ components, running at DuckDB speed and generating pipelines via on-device AI.
- AGENT - CODE ON AUTOPILOT
Agent is an open-source Rust agent that runs 24/7 on your machine and automatically keeps your applications in working order.
- AI INTERVIEW: FAST USER RESEARCH
A set of scripts for automated interviews and synthetic users generating high-quality data for research.
- VOICE ASSISTANT FOR MAC
Wally lets you control Mac by voice and search local documents offline without internet. It runs on Apple Silicon M1 using an on-device offline LLM via llama.cpp and RAG search. It supports KittenTTS and KokoroTTS for natural speech.
- PIXELTABLE — DECLARATIVE AI BACKEND
Pixeltable is a declarative, incremental backend for multimodal AI applications, simplifying work with data and models.
- FULL DESKTOP
E2B Desktop Sandbox — a virtual desktop for AI agents. Connect LLMs to an isolated OS with a graphical interface for secure desktop task automation.
- AWESOME LLM FOR RECOMMENDERS
Collection of 1500+ papers and resources on LLM in recommender systems. Constantly updated, covers training, inference, and evaluation quality.
- AKTOOLS: FINANCIAL DATA FOR AI
aktools provides HTTP API and MCP server for AKShare. Fetch financial data from any programming language or AI assistants like Claude and Cursor. 1500+ stars on GitHub.
- Headless 3D Engine for AI Agents
A Rust-based headless 3D and VFX engine designed for AI agents to simulate, render, and interact with virtual environments without a GUI.
- DEJA-VU - Encoded Agent Memory
A memory layer for the agent that searches, stores context, redacts secrets, shares logs, and synchronizes without dependencies.
- CLI-AGENT-ORCHESTRATOR - MULTI-AGENT ORCHESTRATION
The project orchestrates multiple AI agents (Claude Code, Kiro, Codex) in separate tmux sessions, simplifying collaborative code work.
- Kids Earn Screen Time via Quizzes
Android TV app where kids answer questions to unlock viewing time. Parents manage content locally via QR code and LAN—no accounts or servers needed.
- ELEVENLABS MCP OFFICIAL SERVER
Official MCP server for ElevenLabs, enabling fast integration of voice AI into Python applications.
- LAUNCH AI AGENTS WITHOUT BACKEND
golive-skill — open Agent Skill for AI agents to launch product to production: hosting, DB, domain, email, payments on your accounts. Zero‑dependency Node CLI runs detect → plan → approve → apply → verify, no GoLive, backend or telemetry.
- OPENCONTRACTS — Document Intelligence
Open platform for working with documents, tailored for AI agents. 1359 stars on GitHub.
- LTX-Desktop video generation
An open-source desktop application written in TypeScript for creating videos using LTX models.
- Portable AI on USB
Fully offline AI with Ollama, Llama 3, and AnythingLLM, running directly from a USB drive on Windows and Mac without leaving traces.
- IMAGE GENERATION IN DEEPSEEK HARNESS
dsh-image-gen — a plugin for DeepSeek Harness that generates images from text prompts directly in the chat. Written in TypeScript, it supports style and parameter configuration via simple commands and integrates with Gemini and other LLMs.
- AGENTFRAMEWORK OF YOUR DREAM
NagaAgent - a powerful framework for AI assistants. Multi-agent capability and smart tools in one package.
- RocketMQ on Rust: Speed and Reliability
RocketMQ on Rust — faster, safer, and with lower memory consumption. Support the project with a star!
- ON-DEMAND COMPUTERS FOR CODING AGENTS
A tool to lease temporary machines (cloud, local containers, or your own) to run agent tests and builds while the developer edits code locally. Synchronizes the working directory with uncommitted changes, streams output, and returns the exit code.
- 🔥 GPU REAL‑TIME DASHBOARD
GPU-hot — a web dashboard for monitoring NVIDIA GPU showing temperature, load, and memory in real time. Already over 1,500 stars on GitHub! 🌟
- DATA-API-BUILDER: QUICK REST & GRAPHQL
Create REST and GraphQL endpoints for Azure databases and local storages in minutes.
- RAGBUILDER: OPTIMIZE RAG FAST
Ragbuilder - toolkit for quickly building production‑ready RAG systems on your data. It indexes files, configures search and connects LLMs via a simple API. Written in Python, it has 1.5k stars on GitHub.
- 1500 ANIMATED ICONS FOR REACT
1 500 free animated icons for React, Vue, Angular and JavaScript. Every animation is crafted for smooth work in all frameworks.
- OVIS: Visual-Text Sync
A modern MLLM architecture for structural alignment of visual and text embeddings.
- CZ-GIT: LIGHTWEIGHT COMMITIZEN ADAPTER
cz-git is a lightweight and customizable Commitizen adapter with standard output, written in TypeScript to improve DX.