The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction. LobeHub LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s largest human–agent co-evolving network. English · 简体中文 · …
Kimi Code CLI is your next CLI agent.Kimi Code CLI Kimi Code | Documentation | 文档 Kimi Code CLI is an AI agent that runs in the terminal, helping you complete software development tasks and terminal operations. It can read and edit code, execute shell commands, search and fetch web pages, and autonomously plan and adjust actions during execution. ImportantKimi Code CLI is currently in technical preview. Getting Started See Getting Started for how to install and start using Kimi Code CLI. …
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods Pi Monorepo Looking for the pi coding agent? See packages/coding-agent for installation and usage. Tools for building AI agents and managing LLM deployments. Packages Package Description @mariozechner/pi-ai Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.) @mariozechner/pi-agent-core Agent runtime with tool calling and state management @mariozechner/p…
An AI-powered data science team of agents to help you perform common data science tasks 10X faster. AI Data Science Team + AI Pipeline Studio AI Data Science Team AI Data Science Team is a Python library of specialized agents for common data science workflows, plus a flagship app: AI Pipeline Studio. The Studio turns your work into a visual, reproducible pipeline, while the AI team handles data loading, cleaning, visualization, and modeling. Status: Bet…
AirLLM 70B inference with single 4GB GPU Quickstart | Configurations | MacOS | Example notebooks | FAQ AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run 405B Llama3.1 on 8GB vram now. AI Agents Recommendation: Best AI Game Sprite Generator Best AI Facial Expression Editor Updates [2024/08/20] v2.11.0: Support Qwen2.5 [2024/08/18] v2.10.1 Support CP…
UltraRAG v3: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines Less Code, Lower Barrier, Faster Deployment | Documentation | Dataset | Paper Daily | 简体中文 | English | Latest News 🔥 [2026.01.23] 🎉 UltraRAG 3.0 Released: Say no to "black box" development—make every line of reasoning logic clearly visible 👉|📖 Blog| [2026.01.20] 🎉 AgentCPM-Report Model Released! DeepResearch is finally localized: 8B on-device writing agent AgentCPM-…
An autonomous agent for deep financial researchDexter 🤖 Dexter is an autonomous financial research agent that thinks, plans, and learns as it works. It performs analysis using task planning, self-reflection, and real-time market data. Think Claude Code, but built specifically for financial research. Overview Dexter takes complex financial questions and turns them into clear, step-by-step research plans. It runs those tasks using live market data, checks its own work, and refines the results un…
Download videos from almost any website worldwide VidBee VidBee is a modern, open-source video downloader that lets you download videos and audios from 1000+ websites worldwide. Built with Electron and powered by yt-dlp, VidBee offers a clean, intuitive interface with powerful features for all your downloading needs, including RSS auto-download automation that automatically subscribes to feeds and downloads new vide…
FlashMLA: Efficient Multi-head Latent Attention KernelsFlashMLA Introduction FlashMLA is DeepSeek's library of optimized attention kernels, powering the DeepSeek-V3 and DeepSeek-V3.2-Exp models. This repository contains the following implementations: Sparse Attention Kernels These kernels power DeepSeek Sparse Attention (DSA), as introduced in this paper. Token-level sparse attention for the prefill stage Token-level sparse attention for the decoding stage, with FP8 KV cache Dense Attenti…