#python #agent #agentic_ai #agentic_framework #agentic_workflow #ai #ai_agents #ai_companion #ai_roleplay #benchmark #framework #llm #mcp #memory #open_source #python #sandbox

MemU lets AI systems take in conversations, documents, and media, turn them into structured memories, and store them in a clear three-layer file system. It offers both fast embedding search and deeper LLM-based retrieval, works with many data types, and supports cloud or self-hosted setups with simple APIs. This helps you build AI agents that truly remember past interactions, retrieve the right context when needed, and improve over time, making your applications more accurate, personal, and efficient.

https://github.com/NevaMind-AI/memU

#javascript #agent #agentic #agentic_ai #ai #ai_agents #automation #cursor #design #figma #generative_ai #llm #llms #mcp #model_context_protocol

Cursor Talk to Figma MCP lets Cursor AI read and edit your Figma designs directly, using tools like `get_selection` for info, `set_text_content` for bulk text changes, `create_rectangle` for shapes, and `set_instance_overrides` for components. Setup is quick: install Bun, run `bun setup` and `bun socket`, add the Figma plugin. This saves you hours by skipping context switches, automating repetitive tasks like text replacement or override propagation, speeding up design-to-code workflows, and keeping everything in sync for faster, precise builds.

https://github.com/grab/cursor-talk-to-figma-mcp

#python #agent #ai #aippt #editable_pptx #langgraph #paper2slides #ppt_generator

Paper2Any turns paper PDFs, images, or text into editable diagrams, technical roadmaps, experiment plots, PPT slides, and more with one click. Key tools include Paper2Figure for scientific visuals, Paper2PPT for custom decks with table extraction, PDF2PPT for layout-perfect conversions, and AI beautification. Install via GitHub on Python 3.11+, Linux preferred; try online demo or scripts. You save hours recreating figures or slides for research, talks, or reports, getting pro-quality, customizable outputs fast.

https://github.com/OpenDCAI/Paper2Any

#typescript #agent #agents #ai #assistant #assistant_chat_bots #generative_ui #js #react #reactjs #ui #ui_components

Tambo AI is a free React SDK that lets AI generate and control your app's UI from natural language chats, like showing charts or updating notes without clicks. Register components with simple Zod schemas, wrap in TamboProvider, and use hooks for streaming chats. It beats manual wiring with MCP tools, self-hosting, and templates. You save hours prototyping adaptive apps that fit every user—newbies see basics, pros get advanced views—cutting support needs and boosting speed.

https://github.com/tambo-ai/tambo

#python #agent_skills #ai_agents #antigravity #automation #claude #claude_code #codex #composio #cursor #gemini_cli #mcp #rube #saas #skill #workflow_automation

Claude Skills are customizable workflows that boost productivity on Claude.ai, Claude Code, and API by handling tasks like document editing, code development, data analysis, app automation (emails, Slack, GitHub via Composio's 500+ integrations), and more. Install the connect-apps plugin, add your free Composio API key, and restart to enable real actions across 1000+ apps. This saves time, automates repetitive work, and lets you focus on high-value tasks for faster, consistent results everywhere you use Claude.

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

#typescript #agent #agentic #agentic_framework #agentic_workflow #ai #ai_agents #bytedance #deep_research #harness #langchain #langgraph #langmanus #llm #multi_agent #nodejs #podcast #python #superagent #typescript

DeerFlow 2.0 is an open-source super agent harness that orchestrates multiple sub-agents, memory systems, and sandboxed execution environments to accomplish complex tasks. Built on LangGraph and LangChain, it combines research, coding, and content creation capabilities with extensible skills and tools. The platform features isolated Docker containers for safe execution, long-term memory that learns your preferences, and the ability to spawn sub-agents that work in parallel on different task angles. You benefit from dramatically reduced research and automation time—tasks that typically take hours complete in minutes—while maintaining full transparency and control over agent decisions through human-in-the-loop collaboration. Whether you need deep research reports, data analysis, slide decks, or custom workflows, DeerFlow handles multi-step complexity without requiring extensive coding knowledge.

https://github.com/bytedance/deer-flow

#typescript #agent #agent_development #ai_agent #claude #claude_code #educational #llm #python #teaching #tutorial

Claude Code is an AI agent framework that uses a simple loop: send messages to Claude, check if it needs tools, execute those tools, and repeat. The benefit is that you can build powerful autonomous agents by layering one feature at a time—from basic tool use to multi-agent teams—without rewriting the core loop. This modular approach lets you start simple with bash commands and scale to complex workflows with planning, skill loading, background tasks, and team coordination, making it easier to automate development work and delegate entire projects to AI agents.

https://github.com/shareAI-lab/learn-claude-code

#python #agent #android #app #automation #copilot #gui #mllm #mobile #mobile_agents #multimodal #multimodal_agent #multimodal_large_language_models

Mobile-Agent-v3.5 is Alibaba's top GUI agent family using GUI-Owl 1.5 models (2B to 235B sizes) for automating desktop, mobile, and browser tasks like stock checks, bookings, or document creation with planning, reflection, and memory. Try free online demos on ModelScope or Bailian, or use limited-time APIs—no setup needed. It leads 20+ benchmarks for real-world use. You benefit by saving time on repetitive tasks, boosting productivity, and handling complex operations hands-free across devices.

https://github.com/X-PLUG/MobileAgent

#python #agent_skills #ai_scientist #bioinformatics #chemoinformatics #claude #claude_skills #claudecode #clinical_research #computational_biology #data_analysis #drug_discovery #genomics #materials_science #metabolomics #proteomics #scientific_computing #scientific_visualization

Claude Scientific Skills offers 148+ ready-to-use tools for AI agents like Cursor or Claude Code, covering biology, chemistry, drug discovery, clinical research, ML, and 250+ databases (PubMed, ChEMBL, etc.). Easy setup: clone the GitHub repo and copy folders to your skills directory for automatic use in complex workflows like single-cell analysis or virtual screening. You save days on setup, get reliable code, and run multi-step science faster on your desktop.

https://github.com/K-Dense-AI/claude-scientific-skills

#python #agent #chatbot #large_language_models #llm #llm_agent #mcp #multi_agent #multi_modal #react_agent

AgentScope is a simple, production-ready framework to build AI agents fast. Install with `pip install agentscope` (Python 3.10+), then create ReAct agents with tools, memory, voice, human steering, multi-agent workflows, and finetuning in 5 minutes. It supports realtime voice, A2A protocols, RL training, and easy deployment locally, in cloud, or Kubernetes. You benefit by quickly making robust, scalable agents for tasks like games, research, or chats without complex coding, saving time and enabling real-world apps.

https://github.com/agentscope-ai/agentscope

#python #agent #ai_agents #memory #memoryscope #rag #reme

ReMe is a memory toolkit for AI agents with file-based (Markdown files for easy editing) and vector-based systems to fix limited context and stateless chats. It auto-summarizes talks, saves key facts like preferences, and recalls them next time using hybrid search. Install via `pip install reme-ai`, set API keys, and use ReMeCli or Python code for smart agents. You benefit by building persistent, learning agents that remember your needs, work faster on repeat tasks, and feel more natural without starting over.

https://github.com/agentscope-ai/ReMe

#python #agent #llm #llm_agent #llm_reasoning #machine_learning_systems #mlsys #reinforcement_learning #rl

AReaL is a free, open-source system for fast asynchronous reinforcement learning to train large AI models in math, coding, search, and agents. It decouples generation and training for up to 2.77x speedup, stable performance, and easy setup on single or 1000+ GPUs with algorithms like GRPO/PPO. Install via git/pip, run examples like GSM8K math instantly. You benefit by building top AI agents affordably and quickly, reproducing results with shared data/models, saving time/money vs. slow synchronous tools.

https://github.com/inclusionAI/AReaL