Top Open Source AI Dev Influencers in July 2025

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

自建Claude-code镜像服务，同时支持Gemini-cli、Codex-cli中转，支持多账户切换、自定义API密钥、Claude API、OPENAI兼容格式、能有效规避封号，OAuth集成可快捷添加账号池。

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai

This repo powers my blog experiment where ChatGPT manages a real-money micro-cap stock portfolio.

MemOS (Preview) | Intelligence Begins with Memory

MemU is an open-source memory framework for AI companions

A GitHub Action invoking the Gemini CLI.

Communicate with an LLM provider using a single interface

Building Kontext Model with Online RL for Unified Multimodal Model

🚀 MassGen: An Open-source Multi-Agent Scaling System Inspired by Grok Heavy and Gemini Deep Think. Join the discord channel: https://discord.com/invite/VVrT2rQaz5

Download Sorare Fantasy Football Trainer Hack 2025 – Ultimate Cheat Tool for Player Stats, Lineup Optimizer & NFT Strategy

ChatGPT Bot - AI-powered conversation tool

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Everything you need to know about LLM inference

siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

💻一款简洁实用轻量级的本地AI对话客户端，采用Tauri2.0和Next.js编写 A simple, practical, and lightweight local AI chat client, written in Tauri 2.0 & Next.js.

Efficient audio understanding with general audio captions

An AI Powered README Generator for Python Projects to Automate Your Documentation. AI驱动的项目文档生成神器

An Open-Source Multimodal AIGC Solution based on ComfyUI + MCP + LLM https://pixelle.ai

Run Surfer-H agents powered by Holo1 using the Surfer-H-CLI. Includes example tasks, scripts, and configurations.

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Physics of Language Models, Part 4

Deploy any AI model, agents, database, RAG, and pipeline locally in minutes

基于CNB平台的云端Stable-Diffusion Lora训练调度器，使用comfyui打标，调用秋叶训练器训练，实现可视化一键训练，适合小白。也对接高级参数，可以自由调配

Secure MCP runtime for fully autonomous agents as a desktop application

A framework for Ruby Gems to expose LLM context.

Qwen-TTS offers a robust voice synthesis service using FastAPI, supporting bilingual and dialect options. Explore seamless audio generation on GitHub! 🚀🌟

Scalable and extensible reinforcement learning for LM agents.

The Gemini CLI confirmed that the MCP server built with Google Apps Script (GAS), a low-code platform, offers immense possibilities. If you've created snippets for GAS, these could be revitalized and/or leveraged in new ways by using them as the MCP server. The Gemini CLI and other MCP clients will be useful in achieving this.

A high-performance, self-hosted Deno proxy that makes Fal.ai's powerful models (Flux, SDXL, etc.) compatible with the standard OpenAI image generation API. Use any OpenAI client seamlessly.

🧬 Generate visual charts using ECharts with AI MCP dynamically, used for chart generation and data analysis.

Desktop/web UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one interface, locally or remotely.

Revolutionary AI-powered 4K desktop wallpaper generator with DeepSeek-R1, FLUX-Dev, and 8K supersampling pipeline

Observee (YC S25) lets you build AI agents with 1000+ integrations using MCPs with managed OAuth, Security and Observability

A modern Android note-taking app powered by the Gemini API, built with Kotlin and Jetpack Compose.

Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks

An AI-powered chat application featuring a fluid, glass-morphism interface and persistent conversation history, built with React and Gemini.

cmux lets you run Claude Code, Codex CLI, Cursor CLI, Gemini CLI, Amp, Opencode, and other coding agent CLIs in parallel across multiple tasks

Multiturn VLM Bulk captioning using your api service

Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion (ICCV 2025 Highlight)

Awesome-AI-Meets-Biology is a collection of state-of-the-art, novel, exciting LLMs and agents on biomedical and bioinformatic fields.

让 GLM-4.5 完美适配 Agent TARS 系统的高性能适配器 - 解决 toolcall 兼容性，提供智能 fallback，极低成本享受顶级 AI Agent 体验

这是一个不基于任何框架实现的从0到1的VLM finetune（包括Pre-train和SFT）

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 70+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Discover the Best AI Models for Your PC

/slash is a mobile-first, AI-powered GitHub assistant built with Flutter. Connect your GitHub and AI keys, browse repos, review code, and open PRs—all from your phone

一个为ComfyUI设计的，适用于WAI-NSFW-illustrious-SDXL模型的角色和动作选择器

using vlm to ocr pdf with user friendly ui

Zero instrucment LLM and AI agent (e.g. claude code, gemini-cli) observability in eBPF

A powerful, portable, and feature-rich command-line client for the Google Gemini API, written in C. Supports interactive chat, scripting, file attachments, and session management with no external runtime dependencies.

A local-first database assistant powered by LangGraph and Ollama. Uses DeepSeek-R1:32B for intelligent data querying with ReAct reasoning pattern. Privacy-focused, offline-capable, and tool-driven database interactions.

AI Swarm Agent Launcher - A powerful CLI tool for launching and coordinating AI agents with specialized personas using git worktrees

MARVIS (Modality Adaptive Reasoning over VISualizations) is an 'everything predictor' powered by VLMs + embeddings

1Panel-第三方应用商店(运维监控、免费大模型API、Nas工具、容器管理)

🤖 AI-powered Gmail assistant that automatically analyzes emails and drafts responses using Google's Gemini AI

TradingAgents-MCPmode 是一个创新的多智能体交易分析系统，集成了 Model Context Protocol (MCP) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。

Real-time AI voice transcription in any active window

🤖 Intelligent integration between Claude Code and Google Gemini for large-scale code analysis

ClaraN — Privacy-first, fully local AI workspace with Ollama LLM chat, tool calling, agent builder, Stable Diffusion, and embedded n8n-style automation. No backend. No API keys. Just your stack, your machine.

llm-d helm charts and deployment examples

Chat Overleaf 谷歌插件，可自定义 LLM 供应商，提供 Overleaf 编辑器内划线问答以及获取文件内容作为当前上下文。

A layer selective fine tuning approach

A modern, experimental chat UI for Gemini and LLMs with local-first storage, context management, and multi-conversation support—all in your browser.

Community driven Sora modules

一个基于机器学习和人工智能的比特币期货智能交易系统，集成了量化模型、视觉语言模型(VLM)分析和社交媒体情报分析。

A modular, LLM-agnostic fullstack agent framework.

*Featured on Claude!* MCP server for accessing near real-time health data from Yale's PopHIVE platform, as well as additional HHS/CDC data

🔧 llamakit: Powerful AI devtools

Monitor and visualize your Claude Code API interactions with Claude Code Proxy. Easily set up a transparent proxy and live dashboard. 🛠️🚀

Dự án cá nhân để thử nghiệm các mô hình Stable Diffusion ngay trên máy cá nhân. Hỗ trợ tìm model từ Hugging Face, tinh chỉnh prompt, tăng tốc bằng GPU và tạo ảnh nhanh chóng.

Official Repo for Paper <MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query>

Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models

An intelligent assistant for FLUX.1 Kontext models in Stable Diffusion WebUI Forge. Analyzes context images and generates optimized prompts using dual AI models.

Run Mistral, LLaMA, and DeepSeek locally on Windows with zero setup — no Python required.

A modern fintech analysis platform powered by AI agents using Google's A2A (Agent-to-Agent) protocol for seamless communication and collaboration, with integrated blockchain systems.

Generador de prompts optimizados para arte con IA basado en Llama 3 + Cloudflare Workers.

A Misskey bot running on Linux or Windows that generates customizable content using DeepSeek or any LLM compatible with the OpenAI API

An (arguably the best) open-source AI image generation suite, specifically made and optimized for Intel ARC GPUs. Features a clean Gradio UI and support for all major Stable Diffusion models.

A control server for managing multiple Llama Server instances with a web-based dashboard.

A macOS Silicon wrapper & demo apps for developers of VLM/MLLM apps to simplify access to llama.cpp multimodal capabilities

Experimental LLM agent based on gemini-cli

The BAZAAR challenges LLMs to navigate the double-auction marketplace, where buyers and sellers must make strategic decisions with incomplete information. Each agent receives a private value and must decide how to quote based solely on the history of previous rounds. A realistic test of market intuition and strategic adaptation.

Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration

A secure, web-based chat interface that lets you talk to multiple AI models from different providers - all in one beautiful, easy-to-use application.

Stable Diffusion Model Manager

Gemini WebUI Lite - 自部署的 Gemini AI 代理服务 ｜ 一个简单易用的 Deno Deploy / Cloudflare Worker 程序，让您能够快速部署自己的 Gemini AI 代理服务。只需要一个域名和 Gemini API Key，即可免费为家人朋友提供 AI 问答服务。

START HERE: Modular DevOps lab with LLM-powered CI/CD automation.

Vim plugin to use Gemini APIs as a code assistant

AI-powered course advising system using local LLM and contextual student data.

FastBoz — Self-hosted AI Gateway for GPT, Claude & Gemini Run GPT‑4o‑mini, Claude, Gemini and more without API keys or cost. 🛠 One‑command Docker deploy | 🔒 Private & secure | 🌐 Ready for bots, apps & integrations

Notebooks and problem sets for Astrostatistics 2025—from GLMs and Bayesian tweaks to neural-network basics.

🚀 A framework for Context Engineering using Google Gemini. Move beyond simple prompting and learn to systematically provide context to your AI coding assistant for more reliable, consistent, and complex software development.