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
dragonked2/alphacode

ALPHACODE FREE AI AGENT

Free MIT coding agent alphacode works without an API key: built‑in free model or connect Claude, GPT, Gemini, DeepSeek, Ollama and 50+ more LLMs. Swarm mode, 40+ tools, b

★ 618 · Rust
AbdelStark/awesome-typesafe-jev

JEV TYPESAFE CATALOG

Collection of 400+ resources for structured LLM output: SDKs, agent tools, demos, and independent Jev and TypeSafe evaluations. Helps choose the best solution for typed A

★ 617 · CSS
RobotecAI/rai

RAI: Agent for Robots

RAI is a framework for physical AI robots on ROS 2 and Python, supporting voice interaction, scenarios, and logs.

★ 616 · Python
microsoft/multilspy

MULTILSPY — PYTHON LSP CLIENT

multilspy is a Python LSP-client library that simplifies interaction with language servers for IDEs and code analysis.

★ 615 · Python
AltimateAI/altimate-code

ALTIMATE-CODE AI FOR DATA

Open-source agentic engine for dbt, SQL, and cloud storage: 100+ tools, support for 10 warehouses, AI‑powered.

★ 612 · TypeScript
DocAILab/XRAG

XRAG: EVALUATION OF RAG MODULES

XRAG evaluates core components of RAG systems: indexing, retrieval, and generation. Using standard datasets it compares different module implementations, revealing their

★ 612 · Python
benmaster82/Kwipu

LOCAL GRAPH RAG FOR NOTES

Kwipu — local Graph RAG engine for Markdown notes. Extracts entity-relation triples from wikilinks and YAML, retrieves answers via hybrid search (vector + BM25 + temporal

★ 612 · Python
Nikita-Filonov/ai-review

AI CODE REVIEW ON GITHUB

AI-powered code review for GitHub, GitLab, and other platforms, supporting models OpenAI, Claude, Gemini, and others.

★ 609 · Python
adaline/gateway

GATEWAY: UNIFIED SDK FOR LLM

Gateway is a local production‑grade Super SDK that unifies over 200 LLMs into a single interface. Use any model without complex setup.

★ 609 · TypeScript
Prism-Shadow/awesome-rsi

OPEN CATALOG OF RSI PAPERS

Index of 527+ papers on recursive AI self-improvement. Covers autoresearch, Claude Code, Codex, and GPT. Convenient search by topics and authors.

★ 608 · JavaScript
ericrisco/rsc-harness

RSC-HARNESS MEMORY AND REFLEXES

rsc-harness — meta-harness giving the AI agent memory and safe access to the DB without risk of breaking the repo. Supports Claude Code, Codex and 15+ tools, written in J

★ 607 · JavaScript
aryn-ai/sycamore

SYCAMORE: AI DATA SEARCH

Sycamore — an LLM-based platform for searching and analyzing unstructured data. Allows quick extraction of insights from texts, documents, and logs.

★ 606 · Python
V1ki/dsh-plugin-subscriptions

DSH-PLUGIN-SUBSCRIPTIONS - BYPASS API KEYS

The plugin provides access to ChatGPT, Claude, and Grok via OAuth in the DeepSeek Harness web UI, without requiring API keys.

★ 606 · TypeScript
Fabric-Project/Fabric

FABRIC CREATIVE 3D CODING

Fabric is a Node‑based environment for creative coding, 3D graphics and image processing, inspired by Quartz Composer. In Swift it uses Metal for fast rendering and suppo

★ 606 · Swift
yuxiaopeng/Github-Ranking-AI

GITHUB-RANKING-AI - TOP AI REPOSITORIES

Daily ranking of the most starred AI repositories on GitHub. Automatically updated based on star count.

★ 605 · Python
aldefy/compose-skill

COMPOSE SKILL AI CODING

AI agent with precise hints for Jetpack Compose from real AndroidX code. Works with Claude Code, Codex, Gemini, Cursor, and other IDEs.

★ 604 · Shell
qybaihe/mu

MU: SMART AGENT FOR CODING

mu (μ) — coding agent, which first evaluates the task with a small fast judge, then passes the complex work to the large model. Built on Pi and AionUi, written in TypeScr

★ 604 · TypeScript
kydlikebtc/awesome-jev

JEV: 884 VERIFIED EXAMPLES

Collection of 884 verified Jev examples — TypeSafe AI's decision model. Indexed by decisions made, not sources. CI re-validates all links weekly. Bilingual EN/中文, JSON sc

★ 602 · Python
MMMU-Benchmark/MMMU

MMMU: Multimodal Benchmark

Code evaluation for MMMU benchmark measuring multidisciplinary multimodal understanding and reasoning for expert AGI.

★ 601 · Python
MIV-XJTU/JanusVLN

JANUSVLN: NAVIGATION REVOLUTION

Official JanusVLN implementation from ICLR2026: dual implicit memory separates semantics and space for vision-language navigation.

★ 600 · Python
avidevelops/claude-architect-exam-prep

CLAUDE ARCHITECT EXAM PREP - PREPARATION

claude-architect-exam-prep — a set of materials for preparing for the solutions architect exam with Claude AI: questions, tests, and assignments.

★ 599
karanb192/awesome-claude-skills

TOP-50 CLAUDE SKILLS

More than 50 verified skills for Claude: TDD, debugging, git workflows, and document processing. Boost productivity with the community.

★ 599
wanghao-SunSky/cs329z-chinese

Stanford AI Agents Course (Chinese)

Chinese translation of Stanford CS329Z Engineering AI Agents course with 19 lectures and 4 hands-on projects covering LLMs, RAG, tool calling, memory, multi-agent systems

★ 599 · HTML
normal-computing-oss/fuji-web

FUJI AI AGENT IN BROWSER

Fuji is an AI agent that works in the browser's side panel and performs online tasks with a single command. It understands natural language, interacts with pages, and use

★ 597 · TypeScript
QuintinShaw/pi-dynamic-workflows

DYNAMIC WORKFLOWS FOR PI

Claude Code‑like dynamic workflows for Pi: model routing, isolated git‑worktree, resume journal, cost tracking, and interactive TUI.

★ 596 · TypeScript
l0ng-ai/papr

RSS READER FOR AI AGENTS

Fast native RSS reader on Rust with CLI for AI agents — read, search, and sort feeds right from the terminal.

★ 593 · Rust
gokayfem/ComfyUI_VLM_nodes

ComfyUI_VLM_nodes — Powerful Multimodal AI

A set of custom nodes for ComfyUI: from working with VLM and LLM to music generation and creative prompts.

★ 593 · Python
MindWorkAI/AI-Studio

AI-STUDIO — FREE DESKTOP FOR LLM

Cross-platform app for working with local and cloud LLM from different providers. 502 stars on GitHub.

★ 591 · C#
do-md/domd

DOMD – Lightweight WYSIWYG Editor

A 20KB Markdown-native WYSIWYG editor for React, designed for streaming AI workflows, large files, and agent-based processes.

★ 591 · TypeScript
sunrainyg/RandOpt

RandOpt: Task Experts Optimization

Code for ICML 2026: diverse task experts are densest around pretrained weights.

★ 590 · Python
llmmanorg/llmman

RUN ANY AGENT ON ANY MODEL

llmman lets you run any AI‑agent on any model stored as an OCI image. It supports Claude Code, Codex, llama.cpp, MLX and other popular LLM frameworks.

★ 590 · Rust
keyuchen21/agentic-engineering-handbook

OFFICIAL GUIDE TO AI AGENTS

A complete learning roadmap for building agentic systems based on OpenAI, Claude, MCP, Harness, and Evals. It includes practical Python examples and recommendations for d

★ 589 · Python
ibrahimqureshae/mdflux

MDFLUX - CONVERT PDF TO MARKDOWN

A local Svelte app turns scanned PDFs and folders into clean Markdown, saving tokens and working offline.

★ 586 · Svelte
umutxyp/Seo-Promt-Master

SEO-PROMPT-MASTER - AUTOMATE SEO WITH AI

Turn full Google SEO documentation into a ready-to-use AI prompt that instantly audits pages and suggests step-by-step fixes.

★ 585
CopilotKit/aimock

Mocking LLM and MCP

Mocking LLM API, MCP, A2A, AG-UI, vector databases and search in a single package on a single port, with zero dependencies.

★ 584 · TypeScript
ooples/token-optimizer-mcp

TOKEN OPTIMIZER: -95% TOKENS

Reduces token usage in Claude Code by 95%+ through caching, compression, and smart tool selection.

★ 582 · TypeScript
microsoft/DebugMCP

DEBUGMCP - FOR VS CODE AGENT

Give your VS Code agent a real debugger with breakpoints, step-by-step execution, and variable inspection.

★ 582 · TypeScript
PunithVT/ai-avatar-system

AI-AVATAR-SYSTEM - CREATE A REAL AVATAR

Upload a photo, clone your voice, and chat with a digital human in real time with lip‑sync.

★ 581 · Python
mozilla/bugbug

BUGBUG — PLATFORM FOR ML IN SE

bugbug — a platform for easy launching of ML projects in software engineering. It automates training, testing, and deployment of models.

★ 581 · Python
dbt-labs/dbt-mcp

DBT-MCP: Simplify DBT

An MCP server for integrating dbt with any AI agents and workflows. It allows running dbt models through a unified interface.

★ 578 · Python
worldbench/awesome-ai-auto-research

AI RESEARCHES ITSELF

🔥 Large-scale review of AI Auto-Research — how AI automates scientific research. 386 stars on GitHub!

★ 578 · HTML
frontman-ai/frontman

FRONTMAN: AI AGENT IN CODE

Frontman is an AI agent embedded directly in your framework or browser that helps you write, debug, and optimize ReScript code.

★ 576 · ReScript
NVIDIA-NeMo/Automodel

AUTOMODEL — DISTRIBUTED LLM/VLM TRAINING

Native PyTorch library for distributed LLM/VLM training with out-of-the-box Hugging Face support. ⭐ 576 stars on GitHub.

★ 576 · Python
eltociear/awesome-AI-driven-development

AWESOME-AI-DRIVEN-DEVELOPMENT — 417 STARS!

A curated collection of the best tools for AI development. An indispensable resource for those who want to write code faster, smarter, and more efficiently.

★ 576
awwaiid/ghostwriter

REMARKABLE2 BECOMES VISION-LLM INTERFACE

Project ghostwriter turns reMarkable2 into handwritten interface for vision-LLMs: ChatGPT, Claude, Gemini. Write by hand on E Ink — model sees, understands, replies. Writ

★ 573 · Rust
swarmclawai/swarmclaw

SWARMCLAW: SELF-HEADED AI AGENTS

Open-source self-hosted runtime for autonomous agent swarms: memory, MCP tools, schedules, and 23+ LLM providers.

★ 572 · TypeScript
zhongyu09/openchatbi

OpenChatBI: AI Chat for Data

OpenChatBI — an LLM‑powered chatbot that turns natural language queries into SQL and visualizes data.

★ 571 · Python
wecode-ai/Wegent

WEGENT: AI OS FOR AGENTS

Open AI-native OS for creating, organizing, and running teams of intelligent agents in Python.

★ 569 · Python
framerslab/agentos

AGENTOS - AI Agent Framework

TypeScript framework for building AI agents with cognitive memory, dynamic tool generation, and multi-agent orchestration.

★ 568 · TypeScript
mx-space/core

AI-CMS FOR BLOGGERS

AI core for personal blogs with auto‑summary, translation, moderation and AI writing. 538 ⭐ on GitHub.

★ 567 · TypeScript
towardsai/ragbook-notebooks

NOTES ON LLMS FOR PRODUCTION

Repository with Jupyter notebooks from the book «Building LLMs for Production» by Towards AI. Examples of agents, RAG pipelines, integrations with LangChain and LlamaInde

★ 567 · Jupyter Notebook
autonomous-ai/lampOS

LAMPOS — OS FOR PHYSICAL AI

lampOS — an open-source operating system built to run physical AI on embedded devices. Written in Python, it supports working with LLMs, agent frameworks, and robotics.

★ 567 · Python
NeptuneHub/AudioMuse-AI-NV-plugin

AUDIOMUSE-AI: SMART MUSIC PLUGIN

A plugin for Navidrome that analyzes audio in real time and automatically queues similar tracks. 328 stars on GitHub.

★ 566 · Go
tzachbon/smart-ralph

SMART RALPH: SPEC-DRIVEN DEVELOPMENT

A plugin for Claude Code that combines Ralph Wiggum's cycle with the specification workflow and smart code compaction.

★ 566 · Shell
vakra-dev/reader

INFRASTRUCTURE FOR AI AGENTS

Open web toolkit for AI: scraping, crawling, clean Markdown, and browser sessions ready for your agents.

★ 565 · TypeScript
BUPT-GAMMA/MASFactory

MASFactory Vibration Multi-Agent

MASFactory is a Python framework for orchestrating multi-agent systems using a graph-centric approach and vibrational modeling.

★ 564 · Python
ratel-ai/ratel

RATEL SMART MEMORY FOR AGENTS

Ratel is a Rust framework for AI‑agent context engineering: it cuts token usage by ~80% and provides in‑process BM25 plus semantic search without a vector DB.

★ 563 · Rust
adithya-s-k/FineEnvs

FINENVS: RL-ENVIRONMENTS OF THE NEXT GENERATION

FineEnvs — Python library for creating and scaling reinforcement learning environments with LLM capabilities. It simplifies LLM-agent integration, supports training via G

★ 563 · Python
codexstar69/bug-hunter

BUG HUNTER AI AGENT

An autonomous agent searches for vulnerabilities and bugs in the code, then fixes them in a safe branch.

★ 562 · JavaScript
jjang-ai/vmlx

VMLX - NEXT-GEN MLX MODELS

Ultra-fast compressed MLX models with two-level cache, hybrid scheduler, and continuous batching.

★ 561 · Python

New projects on this topic in Telegram

Telegram →
LLM — page 20 | REDDYX AI