R_REDDYX.XYZ

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

AI Agents 1319MCP 1602Openai 691Claude 978Claude Code 1595Agent 547RAG 533AI Agent 690Anthropic 452Developer Tools 620Agents 400Codex 849Self Hosted 361Agentic AI 378
cyberkaida/reverse-engineering-assistant

AI Ghidra Assistant

MCP server that connects LLM to the Ghidra disassembler. Automatic binary analysis, function renaming, and neural network decompilation.

★ 962 · Java
dezoito/ollama-grid-search

Ollama Grid Search: Compare LLMs

A cross-platform app built with Rust and React for evaluating and comparing local LLMs via Ollama. Intuitive UI, live metrics, and results export.

★ 961 · TypeScript
WecoAI/awesome-autoresearch

AutoResearch use cases

Curated list of AutoResearch use cases featuring optimization traces and open-source implementations.

★ 960
yifanfeng97/Hyper-Extract

Hyper-Extract: Extract Knowledge from Text

Transforms unstructured text into knowledge using LLM. Graphs, hypergraphs, and spatio-temporal data — all with a single command.

★ 959 · Python
hexabot-ai/Hexabot

Hexabot v3 AI platform

Hexabot v3 combines workflows, actions, agents, and conversational channels in a single environment for automating AI tasks.

★ 952 · TypeScript
cdxiaodong/cain-agent

CAIN-AGENT AI Pentest Agent

A real AI engineer for authorized penetration testing. Supports AWS, Azure, GCP, Aliyun, Tencent, and Huawei via a built‑in cloud module.

★ 952 · Python
Pipelex/pipelex

PIPELEX - Declarative Language for AI

Pipelex is a declarative language for building composable AI workflows, convenient for both agents and humans.

★ 951 · Python
Andyyyy64/whichllm

Which local LLM to choose?

Find a local model with the best performance on your hardware based on real benchmarks, not parameter count. One command — instant launch.

★ 947 · Python
lightseekorg/tokenspeed

Ultra-fast engine

Ultra-fast LLM inference engine in Python with maximum performance. 943 stars on GitHub.

★ 943 · Python
foldl/chatllm.cpp

PURE C++ CHAT BOTS

Implementation of several models for real-time communication directly on your computer. Works on CPU and GPU.

★ 942 · C++
Renset/macai

MACAI: AI CHAT FOR macOS

A native macOS app that unifies chat with any AI providers in a single interface.

★ 942 · Swift
strands-agents/samples

STRANDS AGENT SAMPLES

Examples of agents created with the Strands Agents SDK in Python. Ready-made templates for quick start of AI agent development.

★ 940 · Python
MatthewZMD/aidermacs

AIDERMACS: AI PARTNER IN EMacs

The AiderMacs plugin integrates the Aider AI assistant into Emacs, providing instant code suggestions and refactoring directly in the buffer.

★ 936 · Emacs Lisp
usewhale/Whale

WHALE FAST AI AGENT

Whale is a terminal AI agent in Go for DeepSeek: 98% cache hits, 1M context, MCP tools, and dynamic workflows.

★ 935 · Go
sgaofen/humanizer-local-model

LOCAL AI DRAFT HUMANIZER

The project rephrases AI-generated drafts so they read like human-written text while preserving all facts. It runs fully locally, with no data sent to the cloud, and supp

★ 935 · Python
claw-eval/claw-eval

CLAW-EVAL - LLM Agent Evaluation

Claw-Eval is a suite of tests for evaluating LLM agents, with all tasks human-verified.

★ 934 · Python
onlyphantom/llm-python

LLM TUTORIALS IN PYTHON

Collection of notebooks for learning LLM: LangChain, LlamaIndex, OpenAI. Ready scripts for RAG, ChromaDB and Pinecone vector stores. 933 stars on GitHub.

★ 933 · Jupyter Notebook
NVIDIA-NeMo/Gym

GYM - Model Evaluation

Helps evaluate and improve LLMs through environments and agents with feedback and testing.

★ 932 · Python
mozilla-ai/otari

OTARI: GATEWAY FOR 40+ PROVIDERS

Self-hosted gateway compatible with OpenAI API, unifying over 40 LLM providers with virtual keys, budgets, and usage analytics.

★ 930 · Python
zamalali/DeepGit

DEEPGIT: GITHUB HUNTER

DeepGit — a Python agent for finding the best GitHub repositories by topic. It uses LangChain and LangGraph to perform deep code and documentation analysis. Returns a sor

★ 929 · Python
microsoft/mcp-gateway

MCP Gateway Proxy

Reverse proxy and management layer for MCP servers with routing and lifecycle in Kubernetes.

★ 920 · C#
metadist/synaplan

SINAPLAN SELF-HOSTED AI PLATFORM

Open-source self-hosted AI platform on PHP/Symfony: chat with any LLM model RAG over your documents embeddable chat widget and MCP — shows the cost per answer. Full Licen

★ 920 · PHP
777genius/agent-teams-ai

AI Agents Team

You are the CTO, your team is AI agents: they perform tasks autonomously, communicate, and check each other's work; you only monitor the board and give instructions.

★ 918 · TypeScript
patoles/agent-flow

Claude Code Agents Visualization

The project shows in real time how Claude Code agents think, branch, and interact with each other during task execution.

★ 911 · TypeScript
XHToken/Spark-X2.6

SPARK-X2.6: AGENTS ON DEVICE

Open Spark-x2.5 model series focused on agentic capabilities. Runs locally on device without cloud. 814 stars on GitHub.

★ 911
symgraph/IDAssist

IDASSIST: AI ASSISTANT FOR IDA PRO

IDAssist — a plugin for IDA Pro that uses large language models to automate reverse engineering. It generates comments, renames functions, and restores data structures di

★ 910 · Python
kessler/gemma-gem

Gemma 4 in browser

Google Gemma 4 runs directly in the browser via WebGPU — without cloud, API keys, or data transfer.

★ 909 · TypeScript
ENTERPILOT/GoModel

GOMODEL: AI-GATEWAY IN GO

Lightweight unified API gateway for OpenAI, Anthropic, Gemini, Groq, xAI and Ollama. Alternative to LiteLLM with monitoring, guardrails and cost tracking.

★ 909 · Go
lucasastorian/llmwiki

LLM Wiki with Claude

Open source implementation of LLM Wiki by Karpathy. Upload documents, connect Claude via MCP, and let it write your wiki!

★ 907 · Python
mosecorg/mosec

MOSEC - MAXIMUM ML PRODUCTIVITY

Fast framework for serving ML models with dynamic batching and CPU/GPU pipelines.

★ 904 · Python
fim-ai/fim-one

FIM AI One

Open platform-agent for global and Chinese companies: connect all systems through a unified core that supports any LLM and self‑hosting.

★ 903 · Python
instavm/coderunner

Coderunner Local Sandbox for AI

Coderunner is a local sandbox that lets you securely run and test AI agent code isolated from the main system.

★ 903 · Python
rome-os/rome

ROME - Agent OS Future

Rome is a TypeScript-based agent operating system that unites AI agents and development tools in a single environment.

★ 902 · TypeScript
NVIDIA/cuvs

CUVS - Accelerated Vector Search

cuvs is a library for fast vector search and clustering on GPU, using CUDA for maximum performance.

★ 897 · Cuda
vanloctech/youwee

YOUWEE: Download Video with AI

Beautiful cross-platform downloader for YouTube, TikTok, Instagram and 1800+ sites with AI video summarization and post-processing.

★ 892 · TypeScript
th1nhhdk/local_ai_ocr

LOCAL AI OCR

Offline OCR tool based on DeepSeek-OCR for recognizing text from images and PDF directly on your computer.

★ 890 · Python
agent-sh/computer-use-linux

computer-use-linux - LINUX DESKTOP CONTROL

Manage the Linux desktop via MCP, AT‑SPI, GNOME Shell, Wayland portals, and ydotool in Rust.

★ 889 · Rust
fainir/most-capable-agent-system-prompt

SYSTEM PROMPT FOR SELF-IMPROVING AI AGENTS

Paste this system prompt into Claude Code, Codex, or Cursor — the agent will build a self-improving autonomous agent system for any computer task.

★ 889
huggingface/llm-ls

LLM-LSP SERVER TO CODE COMPLETION

llm-ls — an LSP server in Rust that connects LLMs to any editor for code completion and generation. It supports local models via llama.cpp and remote APIs such as Hugging

★ 887 · Rust
taracodlabs/aiden

AIDEN Autonomous AI Agent

Aiden is an autonomous AI agent that controls the browser, terminal, and workflows via simple prompts. It retains memory and restores sessions.

★ 884 · TypeScript
eastriverlee/LLM.swift

LLM.SWIFT - LOCAL ACCESS TO LLM

Simple library for working with large language models locally on all Apple platforms.

★ 884 · C++
riponcm/projectmem

PROJECTMEM AI Agent Memory

Local memory for AI agents: records issues, attempts, and solutions, warning against repeating failed approaches. 100% local, with no cloud or telemetry.

★ 882 · Python
hyper-mcp-rs/hyper-mcp

HYPER-MCP: WASM EXTENSIONS

hyper-mcp is a fast and secure MCP server, extending capabilities via WASM plugins. Written in Rust, already 879★.

★ 879 · Rust
Blarc/ai-commits-intellij-plugin

AI COMMITS FOR INTELLIJ

The plugin generates meaningful commits using AI directly in IntelliJ and Android Studio, saving developers' time.

★ 872 · Kotlin
amitshekhariitbhu/ai-system-design

AI System Design: Learning

The repository contains step-by-step materials for designing AI systems based on LLM, RAG, and AI agents. It is suitable for developers and researchers.

★ 871 · Markdown
Intrect-io/OpenSwarm

OPEN AI TEAM

OpenSwarm — orchestrator of autonomous AI‑team based on Claude Code CLI. Control via Discord, sync tasks with Linear and use cognitive memory for context.

★ 870 · TypeScript
keli-wen/agy-staff

CONNECT ANTIGRAVITY TO CODE

The agy-staff project lets you hire Google's Antigravity CLI as a fast Gemini assistant for Claude Code and OpenAI Codex. Built in JavaScript, it already has 708 stars on

★ 870 · JavaScript
Purewhiter/mobilegym

MOBILEGYM: ANDROID AGENT TRAINING

MobileGym is a browser‑hosted Android emulator for research on mobile GUI agents. The platform provides verifiable evaluation and highly parallel online reinforcement‑lea

★ 866 · Python
sno-ai/sno-station-skills

SNO STATION SKILLS: CLICK FOR AGENTS

Sno Station Skills provides 31 skills that turn Claude Code and Codex into a coordinated team. It includes peer review between agents, handoff on quota exceed, a one-page

★ 864 · Shell
whitecircle/halo

HALO: FRAMEWORK FOR LLM TRAINING

Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, an

★ 862 · Python
hoophq/hoop

HOOP - Unified Protocol Gateway

Hoop is a universal gateway for MCP, LLM, databases, and containers with latency under 5 ms.

★ 859 · Go
editor-code-assistant/eca

ECA: AI Code Assistant

Editor Code Assistant — AI pair programming, editor‑agnostic. Works with any Clojure code editor.

★ 858 · Clojure
IncarnaMind/IncarnaMind

INCARNAMIND AI CHAT WITH DOCUMENTS

Free desktop app for macOS, Windows and Linux, allowing you to ask questions about your documents and get answers with exact page links. IncarnaMind verifies each citatio

★ 858 · TypeScript
ihor-sokoliuk/mcp-searxng

mcp-searxng - MCP Server for SearXNG

MCP server connecting SearXNG to the Model Context Protocol for fast web search in AI agents.

★ 857 · TypeScript
YeonwooSung/llm-architecture-from-scratch

IMPLEMENTING LLM ARCHITECTURES FROM SCRATCH

The project contains clean implementations of modern LLM architectures in PyTorch. Includes DeepSeek-R1, DeepSeek-V3, Gemma 3, Kimi K2, and Llama 4. Perfect for studying

★ 856 · Python
Dong90/oh-my-taiyiforge

CREATE OH-MY-TAIYIFORGE PROJECT

AI workflow automation plugin for intelligent code generation using Claude and Codex!

★ 855 · TypeScript
Helldez/BigMoeOnEdge

BIGMOEONEDGE - SUPER MOE ON PHONE

The project enables running 284 B Mixture‑of‑Experts models on a device with 12 GB of RAM, using only CPU and llama.cpp without loss of accuracy.

★ 855 · C++
wanshuiyin/HERO-Anti-OverDefense

PROTECTION AGAINST OVERDEFENSE OF AGENTS

HERO‑Anti‑OverDefense — a paste‑in contract that blocks four over‑defense patterns of agents. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf and Ge

★ 855 · Markdown
zj-unicom-ai/UniEmployee

AI Digital Employee Platform

A platform that encodes expert employee knowledge and workflows into configurable AI digital workers, ready for on‑demand deployment, approval, and monitoring.

★ 854 · Python
vixhal-baraiya/microgpt-c

MICROGPT-C: GPT IN PURE C

Minimalist GPT implementation in pure C without external dependencies. Train and run models in a single file.

★ 853 · C

New projects on this topic in Telegram

Telegram →
LLM — page 16 | REDDYX AI