GitHub Trends

#python#agent#agents#ai#anthropic#claudecode#llm#llms#openai Open SWE is a free, open-source framework to build internal coding agents like those at Stripe, Ramp, and Coinbase. Trigger it via Slack, Linear, or GitHub (@openswe) to research codebases, plan tasks, code, test, review, and auto-open PRs in secure cloud sandboxes—running parallel jobs without your machine's resources. Customize models, tools, and workflows easily. You benefit by automating routine coding, slashing review cycles and production time by 30-50%, freeing you to focus on high-value work while ensuring safe, high-quality changes. https://github.com/langchain-ai/open-swe

#python#agent_memory#financial_forecasting#future_prediction#knowledge_graph#llms#multi_agent_simulation#public_opinion_analysis#python3#social_prediction#swarm_intelligence MiroFish is a simple AI tool that predicts anything by creating a digital world from your data like news, policies, or stories. Upload seed info and describe what you want to predict; it builds thousands of smart agents with personalities and memories to interact, simulate futures, and give you a detailed report plus chat access. You benefit by testing decisions risk-free—like policy impacts or story endings—making smart choices or fun ideas win through safe, accurate previews. https://github.com/666ghj/MiroFish

#rust#ai_gateway#ai_gateway_support#envoy#envoyproxy#gateway#generative_ai#llm_gateway#llm_inference#llm_proxy#llm_routing#llmops#llms#openai#prompt#proxy#proxy_server#routing Plano is an AI-native proxy server that handles key tasks for agentic apps like routing between agents, smart LLM model selection, safety guardrails, and automatic traces for observability. Define agents in simple YAML, write basic HTTP code in any language, and start Plano to run multi-agent systems without custom plumbing or framework lock-in. You benefit by building and shipping reliable agents to production much faster, focusing on core logic while gaining safety, low latency, and easy scaling. https://github.com/katanemo/plano

#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#large_language_models#llms#long_video_understanding#multi_modal_llms#rag#retrieval_augmented_generation Vimo is a desktop app that lets me chat with any video, from short clips to hundreds of hours, in simple natural language. I can drag and drop videos, ask questions, find exact moments, compare multiple videos, and export useful insights, all on macOS, Windows, or Linux. Powering this is the VideoRAG algorithm, which deeply understands visual, audio, and contextual information, giving accurate answers even for very long videos. This helps me save time, understand complex content faster, and turn large video libraries into searchable, usable knowledge. https://github.com/HKUDS/VideoRAG

#python#docker#fastapi#kbqa#kgqa#llms#neo4j#rag#vue Yuxi-Know (语析) is a free, open-source platform built with LangGraph, Vue.js, FastAPI, and LightRAG to create smart agents using RAG knowledge bases and knowledge graphs. The latest v0.4.0-beta (Dec 2025) adds file uploads, multimodal image support, mind maps from files, evaluation tools, dark mode, and better graph visuals. It helps you quickly build and deploy custom AI agents for Q&A, analysis, and searches without starting from scratch, saving time and effort on development. https://github.com/xerrors/Yuxi-Know

#typescript#agent#agentic#agentic_ai#agents#agents_sdk#ai#ai_agents#aiagentframework#genai#genai_chatbot#llm#llms#multi_agent#multi_agent_systems#multi_agents#multi_agents_collaboration Agent Development Kit (ADK) for TypeScript is an open-source toolkit to build, test, and deploy advanced AI agents with full control in code. Key features include rich tools like Google Search, custom functions, and multi-agent hierarchies for scalable apps, plus a dev UI for easy debugging. Install via npm install @google/adk. You benefit by creating flexible, versioned AI agents that integrate tightly with Google Cloud, run anywhere from laptop to cloud, and speed up development like regular software. https://github.com/google/adk-js

#python#agent_framework#data_analysis#deep_research#deep_search#llms#multi_agent_system#nlp#public_opinion_analysis#python3#sentiment_analysis You can use the "Weibo Public Opinion Analysis System" (called "微舆") to automatically analyze public opinion from over 30 major social media platforms and millions of comments. It uses AI agents working together to monitor, search, analyze text and videos, and generate detailed reports based on real-time data. The system supports easy setup, custom models, and integration with your own databases, helping you understand public sentiment, trends, and make better decisions. It offers continuous monitoring, deep multi-angle analysis, and flexible report generation, all accessible by simply asking questions like chatting. This saves you time and gives clear insights into public opinion dynamics. https://github.com/666ghj/BettaFish

#python#llms#mlx MLX LM is a Python tool that helps you run and fine-tune large language models (LLMs) efficiently on Apple Silicon Macs. It connects easily to thousands of models on Hugging Face, supports model quantization to save memory, and allows distributed training. You can generate text or chat with models via simple commands or Python code. It also offers features like prompt caching and memory optimization for handling long texts, making it faster and less resource-heavy. This means you can run powerful AI models locally on your Mac without needing expensive cloud services, saving cost and improving speed. https://github.com/ml-explore/mlx-lm

#python#agent#llms AutoAgent lets you create and use powerful AI agents easily by just using natural language—no coding needed. It supports many large language models (LLMs) like OpenAI and Anthropic, and performs as well as top research AI systems on benchmarks. You can build tools, agents, and workflows quickly, manage data efficiently with its built-in vector database, and interact flexibly through different modes. It’s lightweight, customizable, and cost-effective, making it a personal AI assistant that helps automate complex tasks simply and efficiently. This saves you time and technical effort while giving you advanced AI capabilities. https://github.com/HKUDS/AutoAgent

#python#agent#ai#ai_coding#claude#claude_code#language_server#llms#mcp_server#programming#vibe_coding Serena is a free, open-source toolkit that turns large language models (LLMs) into powerful coding agents able to work directly on your codebase with IDE-like precision. It uses semantic code analysis to understand code structure and symbols, enabling efficient code search and editing without reading entire files. Serena supports many programming languages and integrates flexibly with various LLMs and development environments via the Model Context Protocol (MCP). This means you can automate complex coding tasks, improve productivity, and reduce costs without subscriptions, making your coding workflow faster and smarter. https://github.com/oraios/serena

#typescript#agentic_ai#agentic_workflow#agents#ai#approval_process#escalation_policy#function_calling#human_as_tool#human_in_the_loop#humanlayer#llm#llms HumanLayer helps you safely use AI agents to automate important tasks by ensuring a human always reviews high-risk actions, like sending emails or changing private data. This is crucial because AI can make mistakes or create wrong outputs, and some tasks are too sensitive to trust AI alone. HumanLayer’s tools guarantee human oversight in these cases, so you get the benefits of AI automation without risking errors in critical work. This makes AI more reliable and useful for automating complex workflows while keeping control and safety in your hands. https://github.com/humanlayer/humanlayer