LLM: open-source projects on GitHub
2094 repositories on LLM, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
HUMANIZE - TURN IDEAS INTO CODE
The humanize project helps quickly turn automated ideas into working solutions using simple shell scripts.
★ 1,616 · ShellEMPRYO: AST Surgeon of Code
Empryo edits code through AST, not strings, providing a living genome for the project.
★ 1,615 · TypeScriptTinyML LLM for cheap boards
Running a language model with 1B parameters on a $10 device with 256 MB RAM in C.
★ 1,614 · CANYJEV 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
★ 1,609 · PythonEXTRACTTHINKER 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 analy
★ 1,605 · PythonLotus: Accelerating AI Processing
Optimized LLM data processing up to 1000× faster, with simple Pandas syntax. 1.6k ★, Python.
★ 1,604 · PythonAI - Building Future with Stripe
A platform for rapidly building AI products with Stripe integration, from prototype to monetization in minutes.
★ 1,600 · TypeScriptLLM FOR VULNERABILITY DETECTION
The most complete index of research on using LLM for detecting vulnerabilities in code — articles, datasets and benchmarks.
★ 1,598 · PythonLOCAL AI FOR MAC OFFLINE
Nativ runs open LLMs locally on Apple Silicon. No data ever leaves your Mac. Built on MLX and Swift.
★ 1,591 · SwiftNVIDIA GPU METRICS FOR PROMETHEUS
Exporter of NVIDIA GPU metrics to Prometheus in Go. Monitoring temperature, utilization, and memory via nvidia-smi.
★ 1,590 · GoVIBETHINKER: 1.5B Model
Tiny model with powerful logical reasoning — Diversity-Driven Optimization awakens the mind of a large LLM. 577 ★ already!
★ 1,589 · PythonUZU: Powerful Engine for AI Models
High-performance inference engine for AI models in Rust. Fast, reliable, efficient.
★ 1,586 · RustUCCL: GPU Communication at Max
A fast library for efficient data exchange between GPUs: collective operations, P2P, and inference acceleration.
★ 1,586 · C++LLM Inference on AWS Trainium
Open-source LLM inference engine for AWS Trainium featuring NKI megakernels, 1M-token context, and OpenAI-compatible API.
★ 1,585 · PythonOPENSERP — AI SEARCH API SELF-HOSTED
Self-hosted SERP API that renders Google, Bing, Yandex and other search engine results with page extraction.
★ 1,584 · GoTUYAOPEN – 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.
★ 1,579 · CBUILD YOUR AI COMPUTER
The project helps you build your personal AI computer with open-source code and support for autonomous agents.
★ 1,577SECOND 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-orga
★ 1,576 · HTMLVOICE 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
★ 1,571 · C++PIXELTABLE — DECLARATIVE AI BACKEND
Pixeltable is a declarative, incremental backend for multimodal AI applications, simplifying work with data and models.
★ 1,569 · PythonFULL 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.
★ 1,568 · PythonAWESOME LLM FOR RECOMMENDERS
Collection of 1500+ papers and resources on LLM in recommender systems. Constantly updated, covers training, inference, and evaluation quality.
★ 1,567OPENCONTRACTS — Document Intelligence
Open platform for working with documents, tailored for AI agents. 1359 stars on GitHub.
★ 1,548 · Python🔥 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! 🌟
★ 1,543 · JavaScriptLLM-WIKI: Knowledge for Agents
Creates knowledge bases for AI agents, combining parallel research and wiki generation.
★ 1,534 · ShellNEUROSPLOIT - AI PENTEST FRAMEWORK
NeuroSploit uses LLM to automate pentesting, generating exploits and analyzing vulnerabilities in real time.
★ 1,534 · PythonFAST MULTIMODAL LLM ON MOBILE
A C++ library enables running multimodal LLMs directly on smartphones with high speed and low power consumption.
★ 1,533 · C++Visual Intelligence for Home
ha-llmvision brings visual intelligence to your home, enabling real‑time object, face and activity recognition for smarter automation.
★ 1,531 · PythonAI Interview Cheat Sheet
A collection of questions and answers for preparing for an AI engineer interview. Covers topics in machine learning, deep learning, and system design.
★ 1,523 · MarkdownTOP-100 AI AGENT HARNESSES
A weekly updated list of 100+ top harnesses for AI agents with an MCP server and ready-to-use recommendation formats.
★ 1,523 · PythonCLAUDE-PRISM – OFFLINE SCIENTIFIC WRITING
A local workspace for scientific papers: LaTeX, Python, and 100+ Claude skills — all offline.
★ 1,515 · TypeScript80+ FREE AI SERVICES
A collection of 80+ free AI services for chat, images, video, voice, and API. Includes even paid LLM. ⭐ 1510
★ 1,510RCLI — Voice AI
Voice AI with RAG, no cloud: chat with Mac and request documents locally.
★ 1,507 · C++tt-metal - Metallic Operations Library
TT-NN operator library and low-level programming model for TT-Metalium kernels to accelerate AI workloads on proprietary hardware.
★ 1,505 · C++FLUENT-KOREAN: CLEAN KOREAN CODE
Output-style plugin for Claude Code that makes responses clear and natural in Korean. Provides smooth Korean without artifacts.
★ 1,505SOKUJI - REAL TIME TRANSLATION
Sokuji provides instant speech translation on-device and in the cloud with support for OpenAI, Gemini, and other providers.
★ 1,497 · TypeScriptMIRASCOPE - LLM WITHOUT FRAMEWORKS
Mirascope is a lightweight anti-framework for working with LLMs, enabling quick prompt creation and testing without unnecessary abstraction.
★ 1,493 · PythonRISUAI: CREATE YOUR STORIES
Risuai lets you easily create interactive role-playing plots with LLM using TypeScript.
★ 1,491 · TypeScriptGPU-Accelerated AI Video Analytics
A set of reference architectures for building GPU-accelerated vision agents and AI-based video analytics applications. ⭐ 1,486 stars, Python.
★ 1,486 · PythonAI Text Anti-Detector
Skill for auditing and reworking content to eliminate AI-generation traces. Works with Claude Code, OpenClaw, Hermes.
★ 1,483LENNY SKILLS: 86 PRODUCT SKILLS
A collection of 86 product management skills from the Lenny podcast, adapted for Claude Code and AI agents.
★ 1,483LUA N1AO AGENT: AI-PENTEST
An autonomous AI agent for system penetration, using a dual reasoning graph. Developed by Professor Lu Hui's team from Guangzhou.
★ 1,476 · PythonFAST LLM ON AMD
Run LLM on AMD Ryzen™ AI in minutes. Like Ollama, but deeply optimized for AMD chips! C++
★ 1,464 · C++MINUET AI.NVIM — SMART AUTOCOMPLETION
An AI plugin for Neovim that offers real-time code completion from popular LLMs: OpenAI, Gemini, Claude, and local models.
★ 1,462 · LuaKONNECT: AI PCB Design
The Konnect AI assistant integrates into KiCad as a single Rust binary, providing 171 tools for schematics, routing, and design verification.
★ 1,462 · RustAWESOME MUSE CONNECTORS
The project offers a source-backed catalog of Meta Muse integrations featuring community connector skills, with (details) on capabilities, authentication, and required pe
★ 1,462 · PythonAGENTLAS-OS: Agents Environment
Manage specialist agents via a hub, automatically creating orchestrators for tasks. Works locally and is compatible with any model.
★ 1,458 · PythonMY AI COMPANION ON PC
Create your AI assistant on the desktop: custom characters, voice dialogue in 1 second, long-term memory, and image recognition.
★ 1,455 · PythonOmnibox - Your Universal Hub
Omnibox collects, organizes, and lets you use and share any data in a single Python interface.
★ 1,442 · PythonRUN LLM LOCALLY IN REACT NATIVE
Run large language models directly on device without internet. Full Vercel AI SDK compatibility for familiar API.
★ 1,438 · TypeScriptBROWSERGYM WEB-AGENT TRAINING
BrowserGym is a Gym environment for automating web tasks, enabling training of AI agents to interact with real websites. It provides a standard reward and observation API
★ 1,437 · PythonMCP-SERVER-QDRANT - OFFICIAL SERVER
Python implementation of the official Qdrant Model Context Protocol server for fast embedding of vector databases.
★ 1,431 · PythonE2B-Cookbook - Unlock Possibilities
Examples of using E2B to launch sandboxes and integrate with AI agents. Simplifying code work in the cloud.
★ 1,425 · TypeScriptBROWSERWING - CONTROL THE BROWSER WITHOUT LIMITS
BrowserWing turns browser actions into MCP commands or Claude skills, enabling AI agents to control the browser quickly and without extra tokens.
★ 1,424 · GoDOCUMENTATION FOR AI AGENTS
Open-source MCP server for working with documentation — an alternative to Context7, Nia, and Ref.Tools. 1419 stars on GitHub.
★ 1,419 · TypeScriptKEY TO SCIENTIFIC SUCCESS
A Claude Code/Codex skill set for top journals: from idea to reviewer responses. Accelerate publication in minutes.
★ 1,418 · StataOLLAMA SHARP: EASY AI ACCESS
OllamaSharp is a simple .NET library for integrating with local Ollama models, enabling quick requests and responses.
★ 1,414 · C#CHATGPT-SCRAPER - INTELLIGENT SCRAPER
Get structured responses from ChatGPT scraping API in one line. Enable live search, HTML context, and automate tasks.
★ 1,411WebAI-to-API - TURN CHAT INTO API
The project lets you easily turn any web chat into a REST API, simplifying AI assistant integration.
★ 1,408 · PythonCOMMONLY: Social Network for AI Agents
A social platform where people and AI agents interact with each other. Connect any agent via HTTP.
★ 1,405 · TypeScriptNew projects on this topic in Telegram
Telegram →