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 1320MCP 1602Openai 691Claude 978Claude Code 1595Agent 547RAG 533AI Agent 691Anthropic 452Developer Tools 620Agents 400Codex 849Self Hosted 361Agentic AI 378
mindroom-ai/mindroom

AI AGENT FOR YOUR WORK

Mindroom — open-source AI agent that knows your work context and chats in a familiar chat interface. Supports any LLM, can be self‑hosted or hosted. Your data stays with

★ 370 · Python
freestylefly/wesight

WESIGHT: AI Agent Workspace

Open-source workspace for AI agents: instant launch of Claude Code, Codex, OpenClaw, and Hermes Agent with flexible LLM routing.

★ 369 · TypeScript
jmerelnyc/Photo-agents

AI photo agents

Autonomous self‑learning agents with visual memory for LLM agents that control the computer.

★ 368 · Python
cocofhu/grasp

MANAGE MULTIPLE PROJECTS

Grasp combines multiple projects and parallel AI‑agents into a single visual panel. You see dependencies, manage tasks, and speed up releases without switching context.

★ 368 · Go
niki914/zafiro

ZAFIRO – AI AGENT FOR ANDROID

Zafiro is an open‑source BYOK AI agent for Android with full phone control via native Shell and Python 3. It supports Skills, MCP and works via Shizuku (root optional), a

★ 368 · Kotlin
matrixhub-ai/matrixhub

MATRIXHUB: AI Hub – Open Source

Self-hosted platform for AI models with Hugging Face compatibility and vLLM/SGLang acceleration. Stars: 246 ⭐

★ 367 · Go
Entelligence-AI/agentplay

VIEW CODING AGENT SESSIONS

Agentplay visualizes Claude Code and Codex sessions as an interactive map and timeline. Helps understand agent logic, find errors, and optimize prompts. 295 stars on GitH

★ 367 · Python
schmitech/orbit

ORBIT SELF-HOSTED AI

Orbit — self-hosted platform for private RAG and multimodal AI applications in Python.

★ 364 · Python
alondmnt/joplin-plugin-jarvis

JOPLIN + AI ASSISTANT

A plugin for Joplin that unites powerful AI models (GPT, Claude, Gemini, Ollama, Hugging Face) in one smart assistant for notes.

★ 364 · TypeScript
shibing624/agentica

AGENTICA AI LONG-TASK AGENT

Python framework for AI agents working for hours: auto context assembly, cost budgets, and death-spiral protection.

★ 364 · Python
mlco2/ecologits

ECOLOGIT: ENERGY ASSESSMENT

EcoLogits measures energy consumption and carbon footprint when using generative AI models via API. It collects CO₂ emission metrics and offers recommendations to reduce

★ 364 · Python
gameworkerkim/vibe-investing

VIBE-INVESTING: AI TRADING BOT

AI analysis of NASDAQ, S&P500 and crypto: multi-agent backtesting, mNAV arbitrage and automated trading.

★ 363 · Python
louisfb01/ai-engineering-cheatsheets

AI Engineering Cheatsheets - Complete Guide

A set of ready-made cheat sheets for solving typical AI engineering tasks. Quick access to proven solutions.

★ 363
day50-dev/streamdown

STREAMING MARKDOWN RENDER IN TERMINAL

streamdown — a Python utility that streams Markdown rendering directly in the terminal. Supports live preview and works with LLM output. Stars: 358.

★ 363 · Python
lalipa2003-arch/JailbreakHub

HUB FOR LLM JAILBREAKING

JailbreakHub collects prompts and methods to bypass LLM safety. The project has 245★ and attack classification. Useful for vulnerability research.

★ 363 · Roff
liruiw/GenSim

GenSim: LLM Generates Simulations

GenSim uses large language models to automatically generate robot simulation tasks, accelerating research and development.

★ 362 · Python
sums001/Deepseek-API

DEEPSEEK API WITHOUT KEYS OR BILLING

Reverse engineered Deepseek chat into OpenAI-compatible API. Access V4 and R1 models via REST without API keys or billing. 326 stars on GitHub.

★ 362 · Python
upgini/upgini

UPGINI: Smart Data Search

Upgini is a library for data search and enrichment that adds features from hundreds of open and commercial sources into the ML pipeline.

★ 361 · Python
whitelonng/mancode

MANCODE: AI AGENT CODE

MANCODE — AI‑agent framework with five modes from practice to playoffs. It blocks over‑engineering, forcing lean, maintainable and effective codes.

★ 361 · TypeScript
clawdotnet/openclaw.net

OPENCLAW.NET: Self-hosted .NET Gateway

Self-hosted gateway and agent runtime on .NET with NativeAOT support for fast deployment of OpenClaw.

★ 360 · C#
starbaser/ccproxy

CCPROXY Mods for Claude Code

ccproxy allows intercepting any requests to Claude Code and modifying responses, as well as connecting your own models via /model.

★ 360 · Python
nshiab/simple-data-analysis

FAST DATA ANALYSIS IN TYPESCRIPT

TypeScript library powered by DuckDB for tabular, geospatial, vector, AI and Google Sheets data workflows, plus visualization. Supports Deno, Node.js and Bun, delivering

★ 360 · TypeScript
liu673/Awesome-LLM4Security

Awesome LLM4Security: Cybersecurity Resources

A curated collection of top cybersecurity resources and tools based on LLMs. Simplifies finding materials for defense and testing.

★ 359
llt22/talkio

TALKIO: Unified Multi-AI Chat

Talkio — a local multimodal chat that unites GPT, Claude, Gemini, and DeepSeek in one window. Tauri 2 + React 19 for fast and secure operation.

★ 359 · TypeScript
ARUNAGIRINATHAN-K/awesome-ai-agents-2026

AI AGENTS 2026: TOP 300

300+ ready-made AI agents, frameworks, and tools for code, voice, research, and enterprise. Comparisons, benchmarks, and in-depth reviews.

★ 358
jasonacox/TinyLLM

RUN LLM LOCALLY ON ANY HARDWARE

TinyLLM lets you run a local LLM and chatbot on consumer hardware. The JavaScript project uses llama-cpp-python for inference without GPU. 352 stars on GitHub.

★ 357 · JavaScript
ModelEngine-Group/unified-cache-management

ACCELERATE LLM WITH CACHE

The unified-cache-management project enables storing and reusing KV Cache to accelerate large language models.

★ 356 · Python
CyberSunil/LLMVault

LLMVault: OWASP LLM Training

Learn to protect AI systems: practical Prompt Injection, RAG, and agent vulnerabilities in one open training framework.

★ 356 · Python
Green-PT/honey-for-devs

HONEY: Fewer Tokens, More Results

Honey reduces AI agent token usage by 53% without quality loss, working with Claude Code, Cursor, Copilot and others.

★ 356 · JavaScript
qf-studio/navigator

NAVIGATOR: CONTEXT FOR CLAUDE CODE

Navigator extends Claude Code sessions to 20+ exchanges, preventing crashes during long dialogues. It implements incremental context storage and a simple plug‑in integrat

★ 356 · Python
djcopley/ShellOracle

SHELLORACLE: AI ASSISTANT TERMINAL

ShellOracle — terminal utility that generates shell commands from natural language using LLM. Supports Bash, Fish and Zsh, integrates with Gemini and other models. Speeds

★ 355 · Python
guoqingbao/xinfer

XINFER - FAST LLM INFERENCE

Xinfer — ultrafast LLM inference in pure Rust, without PyTorch and Python. Enables running models with minimal latency.

★ 354 · Rust
KlaatAI/klaatcode

KLAATCODE - AI AGENT FOR CODE

Open-source AI agent for the terminal with smart model routing — selects the best AI model for the task, cutting costs tenfold.

★ 353 · TypeScript
voska/hass-mcp

HASS-MCP: Control Home with AI

The hass-mcp MCP server lets Claude and other LLMs control and query Home Assistant data through a simple API.

★ 353 · Python
FalkorDB/code-graph

CODEGRAPH: ONLINE CODE GRAPH

The code-graph demo creates an interactive code graph via GraphRAG-SDK and FalkorDB, allowing quick exploration of project dependencies and structure.

★ 353 · Python
automagik-si/genie

GENIE: CLI AGENT FOR PRS

Genie is a CLI agent that interviews you, plans work, launches parallel agents in isolated worktrees, and reviews code before you see it. Just describe the task — get a r

★ 353 · TypeScript
GoogleCloudPlatform/cymbal-air-toolbox-demo

CYMBAL AIR AGENT DEMO

Demo of the Cymbal Air AI agent: LangGraph, tools, RAG, and Google Cloud Databases accessed via MCP Toolbox.

★ 352 · Python
seochecks-ai/slopless

Textlint clean text rules

Deterministic textlint rules and CLI to detect boilerplate phrases and style errors in Markdown.

★ 351 · TypeScript
elbwalker/walkerOS

walkerOS - Simplify Code Tagging

walkerOS is an open‑source tag manager built with TypeScript that simplifies metadata management in projects.

★ 350 · TypeScript
Pal-AI-Lab/Cortico

Cortico: Agent Framework

Cortico is a TypeScript framework for creating persona bots that work with real-time streaming events. It provides a modular architecture, LLM integration, and a configur

★ 350 · TypeScript
SYuan03/Skill-Anything

SKILL‑ANYTHING: ONE COMMAND

Converts any source — PDF, video, web, audio or text — into an interactive learning package with quizzes, flashcards and spaced repetition. One command generates a 12‑sec

★ 350 · Python
strands-labs/ai-functions

AI-FUNCTIONS - Smart Functions for Agents

The ai-functions library provides Python functions controlled by AI agents, with post‑conditions at runtime for reliable agent workflows.

★ 349 · Python
agentclientprotocol/python-sdk

PYTHON-SDK - SIMPLE SDK FOR ACP

Python SDK for ACP clients and agents: easy integration, ready-to-use functions, and minimal configuration.

★ 349 · Python
Lap-Platform/LAP

LAP: Agent API Compass

LAP converts any API specifications into a compact agent‑native format, reducing size by 10× and providing ready‑to‑use skills for 1500+ APIs.

★ 349 · Python
LosaLosSantos/aurelio-finance

Aurelio Finance Manager

Track net worth, investments, ETFs, cash, and debts locally with an AI financial advisor.

★ 349 · Python
iAmCorey/kooky

KOOKY: AI CODING TERMINAL

A minimalist terminal with sidebar workspaces, horizontal and vertical split panels, one‑click agent launch, and live workspace state.

★ 348 · Swift
opencmit/alphora

ALPHORA: BUILDING AI AGENTS

A production Python platform for building composite AI agents, ready for scaling and integration.

★ 348 · Python
SirAllap/agentglass

AGENTGLASS - AI AGENT MANAGEMENT

Real-time dashboard for monitoring and managing AI agents across all providers and projects on your computer.

★ 348 · TypeScript
wanyichen06/LLMInternSkill

LLMINTERNSKILL – Turnkey Resume

A tool for polishing resumes, matching job openings, verifying evidence, and preparing for interviews using LLM.

★ 348 · Markdown
JordyZomer/lemmalog

LEMMALOG: DATALOG FOR AGENT MEMORY

Lemmalog — a Datalog engine for LLM agent memory. It supports stratified rules, provenance‑tracked facts, incremental derivation, and an MCP server that lets you use the

★ 348 · Rust
aa0101181514/tw-legal-rag

TW-LEGAL-RAG: Taiwan Case Search

Open‑source CLI for semantic search of Taiwan court decisions, packaging them for LLM and citation verification. Works only with retrieve; you choose the LLM yourself.

★ 347 · Python
DevDock-AI/claude-unlimited

UNLIMITED CLAUDE CODE CLI

A tool for seamless rotation of Claude and GPT subscriptions and API keys. Switch limits during a session via a local dashboard.

★ 346 · Python
mrwogu/promptscript

PROMPT SCRIPT: AI CODING

Standardize and audit AI prompts as code, easily deploying them in any coding assistant.

★ 344 · TypeScript
mlhher/late-cli

LATE-CLI: AI COMMAND IN TERMINAL

Run an AI development command on 5 GB VRAM: ephemeral sub‑agents, precise diffs, a single binary, any model, no config.

★ 342 · Go
Ammaar-Alam/minebench

MINEBENCH: AI BENCHMARK

Minecraft‑style voxel benchmark comparing AI models in arena and sandbox.

★ 342 · TypeScript
xiaYuTian11/maskit

Local LLM Privacy Gateway

Automatically masks sensitive data in LLM requests and streams restored responses. Works with any tool supporting custom Base URLs like Cursor, Claude Code, and Codex.

★ 342 · Python
zaxbysauce/opencode-swarm

OPENCODE SWARM: AGENT SWARM

An architecture‑centric agent swarm for OpenCode: hub‑spoke organization, SME consultation, code generation, and QA review.

★ 341 · TypeScript
mahimairaja/voiceai

VOYSAI: AGENT TEMPLATES

A collection of useful articles and links for creating voice AI agents. Quickly start with ready-made templates and resources.

★ 341
OnlyTerp/openclaw-optimization-guide

OPTIMIZE YOUR AI AGENT

Guide to accelerating the OpenClaw AI agent: speed, memory, context, model selection, and one-shot development.

★ 340 · JavaScript
berelevant-ai/slopless

SLOPLESS: STOP SLOP

Deterministic textlint rules and CLI that find excess slop in English Markdown and help write cleaner.

★ 340 · TypeScript

New projects on this topic in Telegram

Telegram →
LLM — page 26 | REDDYX AI