#python #apple_silicon #florence2 #idefics #llava #llm #local_ai #mlx #molmo #paligemma #pixtral #vision_framework #vision_language_model #vision_transformer

MLX-VLM lets you run, chat with, and fine-tune Vision Language Models (VLMs) plus audio/video models on your Mac using MLX—install easily with `pip install -U mlx-vlm`. Use CLI for quick text/image/audio generation (e.g., `mlx_vlm.generate --model ... --image photo.jpg`), Gradio UI for chats, Python scripts, or a FastAPI server with OpenAI-compatible endpoints supporting multi-images/videos. Features like TurboQuant cut KV cache memory by 76%, and LoRA/QLoRA fine-tuning works on consumer hardware. You benefit by experimenting with powerful multimodal AI locally—fast, memory-efficient, no cloud costs, perfect for Mac users tweaking models affordably.

https://github.com/Blaizzy/mlx-vlm

#python #ai_agent #automation #autonomous_agent #browser_automation #claude #computer_control #desktop_automation #gemini #lightweight #llm_agent #memory_system #python #self_evolving #skill_tree #task_automation

GenericAgent is a simple 3K-line AI agent framework that controls your computer—browser, files, mouse, screen, and phone—with just 9 tools and a 100-line loop. It learns from tasks like ordering food, checking stocks, or sending messages, saving them as reusable skills that grow into your unique skill tree over time. Install easily with git clone, pip, and an API key, then launch. This saves you hours on repetitive work, automates personal tasks, and builds smarter help tailored just for you.

https://github.com/lsdefine/GenericAgent

#typescript #analytics #autogen #evaluation #langchain #large_language_models #llama_index #llm #llm_evaluation #llm_observability #llmops #monitoring #observability #open_source #openai #playground #prompt_engineering #prompt_management #self_hosted #ycombinator

Langfuse is a free, open-source platform to build, monitor, evaluate, and debug AI apps using large language models (LLMs). It offers tracing for app logic, prompt management, evaluations, datasets, a playground, and easy integrations like OpenAI, LangChain, and LlamaIndex. Deploy it on Langfuse Cloud (free tier) or self-host with Docker in minutes. This helps you quickly spot issues, improve prompts without slowing apps, test reliably, and speed up development—saving time and boosting AI performance.

https://github.com/langfuse/langfuse

#python #awesome #awesome_lists #awesome_resources #codex #codex_cli #codex_skills #coding_agent_skills #coding_agents #gpt_5_1_codex #gpt_5_codex #llm #skills

Awesome Codex Skills offers a curated list of practical skills to automate workflows in Codex CLI and API, like code reviews, meeting summaries, GitHub PR fixes, Notion organization, email drafting, and data analysis across 1000+ apps via Composio. Install easily with a Python script or manually by copying folders to ~/.codex/skills, then restart Codex—it auto-triggers skills matching your task description. This saves you hours on repetitive dev, productivity, and comms tasks, letting Codex take real actions like posting to Slack or creating issues for faster, smarter work.

https://github.com/ComposioHQ/awesome-codex-skills

#rust #ai #claude #cli #coding_agent #llm #mcp #openai #rust #terminal #tui

jcode is a fast, low-RAM coding agent for Linux, macOS, and Windows that boosts your skills with multi-session workflows, smart memory recall, swarm collaboration, side panels for diagrams/files, and logins for models like Claude or OpenAI. Install easily via `curl -fsSL https://raw.githubusercontent.com/1jehuang/jcode/master/scripts/install.sh | bash`, then run `jcode`. It uses far less memory (27MB vs. 300MB+ for rivals) and starts in 14ms, letting you handle many agents smoothly without slowdowns or high costs—perfect for efficient, scalable coding.

https://github.com/1jehuang/jcode

#python #agent #ai #aigc #gemini #llm #quant #quantitative_trading #rag #stock

This AI-powered stock analysis system uses large models to automatically analyze your chosen A-shares, HK, or US stocks daily, delivering a decision dashboard with core conclusions, scores, buy/sell points, risk alerts, and checklists via WeChat, Telegram, email, or more. Deploy it free in 5 minutes via GitHub Actions—no server needed—or run locally/Docker. You save hours of manual research, get multi-dimensional insights (technicals, news, funds), backtesting, and interactive Agent queries for smarter, automated trading decisions.

https://github.com/ZhuLinsen/daily_stock_analysis

#rust #cli #deepseek #llm #rust #terminal #tui

DeepSeek TUI is a terminal-based coding agent that runs entirely in your command line, giving you direct access to AI-powered code assistance without needing separate software installations. It uses DeepSeek's advanced V4 model with massive 1-million-token memory, allowing it to understand and work with large codebases. The tool reads and edits your files, runs commands, searches the web, and manages version control—all through a fast keyboard interface. You benefit from real-time visibility into the AI's reasoning process, automatic cost tracking, and three interaction modes ranging from read-only planning to fully automated execution, making complex coding tasks faster and more transparent.

https://github.com/Hmbown/DeepSeek-TUI

#javascript #ai_agents #ai_gateway #anthropic #chatgpt #claude #claude_code #cline #codex #copilot #cursor #deepseek #free_ai #gemini #gemini_cli #llm #llm_gateway #openai #openai_proxy #qwen #token_saver

# 9Router//localhost:20128/v1`. You get unlimited coding with zero cost, no downtime, and intelligent fallback routing—perfect for developers who want maximum value from AI without subscription limits or surprise bills.

https://github.com/decolua/9router

#javascript #agent #ai #coding #course #deepseek #gemini #genai #gpt #llm #low_code #mcp #nextjs #no_code #openai #programming #tutorial #vibe_coding #vibecoding #vscode #workflow

# Easy-Vibe: Learn to Build Apps by Speaking

Easy-Vibe is a learning platform that teaches you to create real applications using AI by simply describing what you want. It offers beginner-friendly guides, step-by-step visual tutorials, and interactive coding simulations that make learning feel like having a private tutor. The platform covers everything from your first project to advanced full-stack development, with animated explanations of AI principles and game-like learning for complex topics like data retrieval systems. You benefit by gaining practical skills to turn ideas into working products quickly, whether you're a complete beginner, student, or developer wanting to master AI-assisted coding in the modern era.

https://github.com/datawhalechina/easy-vibe

#python #apple_silicon #inference_server #llm #macos #mlx #openai_api

# oMLX: Run AI Models Faster on Your Mac

oMLX is a tool that lets you run large language models directly on your Mac with Apple Silicon chips. It uses smart memory management—keeping frequently used models in RAM and storing less-used ones on your SSD—so everything runs smoothly without slowdowns. You control everything from a simple menu bar app or web dashboard. It works with many popular AI models and connects easily to coding tools like Claude Code. The benefit is you get powerful AI capabilities locally on your Mac without needing cloud services, saving money and keeping your data private while enjoying fast, responsive performance.

https://github.com/jundot/omlx