Latest AI Resources

EverMemOS is an open source long-term memory operating system launched by the Shanda team led by Chen Tianqiao, designed for AI intelligences to solve the problem of memory breakage caused by the fixed context window of large language models. The system is based on the human brain memory mechanism, using a four-layer architecture (agent layer, memory layer, index layer...

Audio2Face is NVIDIA's open source AI tool capable of transforming audio input into realistic 3D facial animation. By analyzing speech features in the audio, such as phonemes and intonation, it generates precise lip synchronization and subtle emotional expressions to give vivid human expressions to virtual characters.

XTuner V1 is a new generation of large model training engine open-sourced by Shanghai Artificial Intelligence Laboratory (SAL), designed for ultra-large scale sparse Mixed Expert (MoE) model training. Developed based on PyTorch FSDP, it achieves high performance through multi-dimensional optimization of memory, communication and load ...

移动云 MobileClaw 是中国移动推出的桌面级AI办公智能体，央企首个深度兼容OpenClaw生态的"自研小龙虾"，主打"本地优先、隐私至上"。采用一键安装开箱即用设计，适配Windows/ma...

JJT（超级J的AI PPT）是360推出的全链路AI演示文稿创作工具，让用户以极简操作产出设计师级别的PPT。用户只需输入主题或粘贴数据，AI即可自动生成结构完整、视觉专业的演示文稿

SenseNova-MARS 是商汤开源的首个支持动态视觉推理与图文搜索深度融合的智能体视觉语言模型（Agentic VLM），提供 8B 和 32B 双版本。模型能自主规划任务步骤、调用多种工具（如...

NocoBase is based on AI-driven open-source no-code development platform that supports the rapid construction of business systems, without programming to complete the application development through configuration. The project uses Apache-2.0 protocol , provides private deployment and flexible scalability , suitable for enterprise management , collaboration platforms and other fields ...

Xiaomi MiMo-V2-Pro 是小米推出的旗舰级MoE大模型，采用1万亿总参数、420亿激活参数的混合专家架构，支持最高100万token超长上下文。模型以代号"Hunter Alpha"匿名...

GLM-5-Turbo 是智谱 AI 发布的全球首款专为 OpenClaw（龙虾） 场景深度优化的基座模型，也是 GLM-5 系列的高速增强版本。模型从训练阶段就针对 Agent 任务的核心需求进行专...

MiniMax M3是稀宇科技发布的新一代人工智能大模型，采用自研稀疏注意力机制（MSA），支持100万tokens超长上下文和原生多模态功能（图像/视频输入及桌面操作）。编程能力在SWE-Bench...

Androidify is Google's open source project to help developers learn how to build AI-driven apps on Android. The project uses Google's latest technologies such as Jetpack Compose, Gemini API (via Fire...

Qwen3-Next is a new generation of hybrid architecture big model open source by Ali Tongyi, combining Gated DeltaNet and Gated Attention technology, good at dealing with long text, fast inference and saving computing resources.

SenseAudio 是商汤科技推出的AI语音开放平台，面向开发者与企业提供一站式语音AI解决方案。平台集成语音识别（ASR）、语音合成（TTS）、音色克隆等核心能力，语音识别覆盖20+语言并支持说话...

ROCK (Reinforcement Open Construction Kit) is Alibaba's open source sandbox for training environment of intelligences, which solves the problem that intelligences can't be scaled up for training in real environments.ROCK provides a highly stable sandbox management service...

Fun-CineForge 是阿里通义实验室开源的首个支持影视级多场景配音的多模态大模型，基于 CosyVoice3 打造。通过"数据+模型"一体化设计，创新性地解决音画同步、情感表达、音色一致与时间...

GPT-Realtime-2 是 OpenAI 发布商用的旗舰级实时语音模型，也是首款具备 GPT-5 级推理能力的端到端语音代理模型，上下文窗口扩展至 128K，支持图像输入、五级可调推理强度与并行...

MiniMax M2.7 是 MiniMax 推出的旗舰级 Agent 推理大模型，主打"模型自我进化"能力。模型通过构建 Agent Harness 体系，深度参与自身训练与优化流程，在部分研发场景...

WorldMirror 1.1 (WorldMirror) is an open source 3D reconstruction of large models released by Tencent's WorldMirror team, which is an upgraded version of the WorldMirror series. It supports multi-view images, videos, and multi-modal a priori inputs such as camera position, internal reference, depth map, etc. It breaks through the traditional 3D reconstruction that only relies on...

ClipSketch AI is open source video to hand-drawn split-screen tool designed for short video creators. It can convert videos from B station, Little Red Book and other platforms into hand-drawn style storyboards with one click, support marking key frames, automatic generation of sub-scenes and social copy, and can integrate user-defined roles.

Wall-OSS-0.5 是自变量机器人（X Square Robot）推出的开源视觉-语言-动作（VLA）大模型，拥有 40 亿参数，基于 30 亿参数的 VLM 骨干网络构建。采用"梯度桥接协同训...

NemoClaw 是 NVIDIA 推出的开源企业级 AI Agent 安全增强平台。作为 OpenClaw 的"安全插件"和运行时沙箱层，通过 OpenShell 为自主 AI 代理添加企业级的隐私...

Step 3.7 Flash是阶跃星辰（StepFun）开源的新一代AI模型，专为生产级智能代理（Agent）设计。在速度、成本与复杂任务处理能力间取得平衡，支持编程、搜索和多模态工作流，并针对本地部...

DreamOmni2 is a multimodal AI image editing and generation model open-sourced by Jiajia's team at HKUST. Can handle both text and image commands, supports multiple reference images, providing creators with more flexible ways of creation. The model is trained using a three-stage data synthesis process , joint training generation/editing...

Gemini 3.5 Flash 是 Google I/O 大会发布的全新 AI 模型，是 Gemini 3.5 家族的首个成员。打破了"Flash 系列牺牲性能换速度"的传统定位，在保持每秒约 28...

TalkCody is a free and open source AI programming assistant desktop application , built on Rust + Tauri 2 , support for Windows, macOS and Linux three platforms , with native performance , fast startup and low resource consumption advantages . Supports more than 50 mainstream A...

TranslateGemma是谷歌推出的基于Gemma 3的开源机器翻译模型系列，专为提升翻译质量而设计。通过两阶段微调（监督微调和强化学习）优化翻译效果，提供4B、12B、27B三种参数规模，支持5...

KoalaQA is an open source intelligent after-sales service system developed by the Chaitin team. Based on the AI model, it provides AI customer service, AI search and knowledge base management functions to help enterprises quickly build an intelligent Q&A platform. The system supports 24/7 real-time response ...

TypeNo 是 marswaveai 团队开源的中文语音输入工具，专为 macOS 打造。用户只需轻点 Control 键即可录音，松手后语音会在本地实时转为文字并自动填入当前应用。

MAI-Image-2 是微软推出的第二代自研图像生成模型，模型在权威评测平台 LMArena 中跃升至全球第三位，仅次于谷歌和 OpenAI，标志着微软在图像生成领域实现从"追赶者"到"第一梯队"的...

Paper2Video is an open-source presentation video project for automatic generation of academic papers by Show Lab at National University of Singapore. Using the PaperTalker multi-intelligence framework, papers are transformed into full presentation videos containing slides, subtitles, voiceover and speaker avatar...

Steps Deep Research is an efficient AI research tool launched by Steps Star, which can autonomously complete research on complex issues and generate professional reports in a short period of time. The tool is designed for finance, consulting, healthcare, law and other fields, and excels in industry reviews with its in-depth search and information integration capabilities.

Seedance 2.0 Mini 是字节跳动 Seedance 视频模型系列的最新轻量版本，在火山方舟体验中心及 Dreamina 平台上线，计划近期开放 API 服务。

Gemini Spark是谷歌在2026年I/O大会上发布的个人AI智能体，是24/7全天候运行的AI代理，运行在谷歌云专属虚拟机上，无需用户设备（如电脑、手机）保持开启状态，即可持续执行任务。

Qwen3.5-Max-Preview 是阿里通义千问团队推出的旗舰大模型预览版，在 LM Arena 国际大模型竞技场以1464分跻身全球前五、国内第一，标志着国产大模型首次进入全球第一梯队。

Omnilingual ASR is a multilingual speech recognition framework introduced by Meta, covering 1600+ languages, with 78% language character error rate lower than 10%. its 7 billion parameter wav2vec 2.0 encoder combined with CTC and Transformer decoder, support...

BitCPM-CANN 是面壁智能联合清华大学、OpenBMB 开源社区发布并开源的中国首个完全基于国产算力平台（华为昇腾）实现端到端训练的三值（1.58-bit）大模型系列。系列包含 0.5B、1B...

Hy-Memory是腾讯混元推出的记忆插件，专为 Openclaw 等长期协作型 Agent 设计。通过 6层记忆框架 × System1/System2 双系统 × 演化链 三层核心架构，解决 Ag...

GigaBrain-0 is the first end-to-end Vision-Language-Action (VLA) embodied base model in China that uses world model generation data to realize real machine generalization, and it is jointly released as open source by GigaVision and Hubei Humanoid Robot Innovation Center. It adopts the hybrid Transformer architecture, integrating ...

OmniVinci is an open-source, fully modal large-scale language model developed by NVIDIA that solves the problem of modal fragmentation in multimodal models through architectural innovation and data optimization. Alignment of visual and audio embeddings is enhanced by OmniAlignNet, which utilizes temporally embedded group capture...

DiffusionGemma 是 Google DeepMind 发布的实验性开源文本生成模型，采用离散文本扩散架构替代传统自回归方式。基于 Gemma 4 的 MoE 骨干（26B 总参数，激活 3...

InfinityStar is a unified spatio-temporal autoregressive framework open-sourced by ByteDance, designed for high-resolution image and video generation. Using a discrete autoregressive approach, it can simultaneously handle text-to-image, text-to-video, and image-to-video tasks in a single model. The framework is benchmarked in VBench ...

LLaVA-OneVision-1.5 is an open-source multimodal model by the EvolvingLMMS-Lab team, using 8B parameter scale, through a compact three-phase training process (language-image alignment, conceptual equalization and knowledge injection, and instruction fine-tuning) on 128 A800...

DeepSeek-V3.2-Exp is a DeepSeek open source experimental AI model that significantly improves the efficiency of long text processing by introducing the DeepSeek Sparse Attention (DSA) mechanism. The model is based on DeepSeek...

小精龙是学而思基于OpenClaw架构打造的原生学生端精准学智能体，以"大脑映射、私有财产、学习伴侣"为核心定位。首次将长期记忆、动态学情诊断、教育专属Skill链与情感陪伴系统整合为统一的学生专属A...

LLaSO is an open source speech model launched by Beijing Depth Logic Intelligence Technology Co. Ltd, which solves the problems of data dispersion and insufficient task coverage in the field of large-scale speech language modeling by integrating speech and text data and providing alignment datasets, command fine-tuning datasets and evaluation benchmarks.

Qwen3.7-Plus 是阿里巴巴通义千问团队推出的多模态智能体基座模型，在 Qwen3.7 强大文本能力基础上全面升级视觉-语言理解能力，同时完整保留编码、工具调用与生产力工作流等智能体特性。

DPAI Arena (Developer Productivity AI Arena) is an open benchmarking platform created by JetBrains to measure the effectiveness of AI-assisted development tools in real-world software engineering tasks. Through a transparent evaluation stream...

StepAudio 2.5 Realtime 是阶跃星辰发布的新一代实时语音大模型，目前已全量上线开放平台。模型主打"活人感"对话体验，通过副语言感知、千万级人设自定义与双商进阶的对话能力，实现从文本...

RoboCOIN is the world's first large-scale dual-arm robot real machine dataset open-sourced by Beijing Zhiyuan Artificial Intelligence Research Institute in conjunction with a number of enterprises and colleges and universities, which contains 15 types of robot platforms, 180,000 real operation trajectories, and 421 types of task scenarios. The most important feature is the use of hierarchical annotation system to disassemble the task ...

Qwen-VLA 是阿里通义实验室发布的统一视觉-语言-动作（VLA）具身基础模型。以 Qwen3.5-4B 为视觉语言主干，搭配 1.15B 参数的 DiT（Diffusion Transforme...

gws 是 Google Workspace 团队推出的命令行工具，采用 Rust 构建。工具支持运行时动态生成命令，通过读取 Google Discovery Service 实时适配所有 Work...

Frappe Builder is open source low-code website builder, developed by Frappe, the core feature is to provide a Figma-like visual editor that supports drag-and-drop components to build websites quickly. Part of the Frappe ecology (Frappeverse)...

SceneGen is an open source method for generating 3D scenes from a single image at Shanghai Jiao Tong University. From a single scene image and a target resource mask, a complete scene containing multiple 3D resources is efficiently generated, including the geometric structure of the resources, texture and relative spatial location.

TuyaClaw 是涂鸦智能（Tuya Smart）推出的 AI 助理，基于 OpenClaw 架构搭建，是全球首个同时打通数字世界与物理世界的 AI Agent。与市面上仅能在屏幕内执行任务的"龙虾...

Veo 3.1 Lite是Google DeepMind发布的低成本AI视频生成模型，定位为Veo系列中最实惠的版本，专为大规模视频生成场景设计。模型支持文本和图像生成视频，输出720p和1080p分...

Vidi2 is a second-generation multimodal video understanding and generation big model open-sourced by ByteDance, focusing on video content understanding, analysis and creation. It supports joint input of text, video, and audio modalities, and can simultaneously understand picture content, sound information, and natural language commands to achieve cross-modal interaction and push...

SAM 3D is a 3D reconstruction model based on the SAM series from Meta, including two branches, SAM 3D Objects and SAM 3D Body. SAM 3D Objects can generate interactive 3D object models from a single photo, supporting...

Wan-Dancer 是阿里巴巴通义实验室万相（Wan）团队推出的音乐驱动舞蹈视频生成大模型，开源版本 Wan-Dancer-14B 拥有140亿参数，采用 Apache 2.0 协议免费商用。用户只...

PixVerse R2 是爱诗科技（AISphere）推出的实时全模态世界模型，延续年初 R1"全球首个实时世界模型"的路线，主打"边生成、边交互、边演化"，推动 AI 视频从"看"走向"玩"。

nanochat is an open source project released by AI legend and former Tesla AI Director Andrej Karpathy that allows individuals to quickly train a small ChatGPT-like language model at a very low cost and simplicity. The entire project uses only about 800...

2025年7月，蛙蛙写作正式发布2.0版本，这是该产品自2024年上线以来幅度最大的一次产品重构。此次升级不仅在底层技术能力上实现了对主流大模型的深度整合，更在产品交互架构上做出了突破性的创新——引入...

MiMo-Embodied is the world's first cross-embodied base model that successfully integrates Embodied AI and autonomous driving open-sourced by Xiaomi Group. It solves the knowledge migration problem between Embodied AI and autonomous driving, and realizes the unified modeling of tasks in the two fields.

HiDream-O1-Image-Pro 是智象未来（HiDream-ai）发布的旗舰级闭源图像大模型，采用新一代原生全模态架构 Unified Transformer（UiT），参数规模超过2000...

MOSS-Speech is an open source speech-to-speech (Speech-to-Speech) big model by Prof. Qiu Xipeng's team at Fudan University. It breaks through the traditional speech processing, without the need for text guidance, and directly understands and generates speech, which can capture non-text elements such as intonation and emotion, making...

FireRed-OCR 是小红书 Super Intelligence 团队开源的端到端文档解析模型，基于 Qwen3-VL-2B 架构打造，仅用 2B 参数就在 OmniDocBench v1.5 ...

Mureka V9是昆仑万维旗下天工AI在中关村论坛上发布的AI音乐模型，是Mureka系列的最新迭代版本，通过技术创新重塑数字音乐创作生态。基于Musicot（Music Chain-of-Thou...

Wan2.7-Image 是阿里巴巴通义实验室发布的图像生成与编辑统一模型，定位为"全场景视觉创作旗舰"。模型直击AI生图领域"标准脸"审美疲劳和"色彩盲盒"痛点，采用生成与理解统一的底层架构，具备文...

MAI-Thinking-1 是微软AI发布的首款自研高级推理模型。模型采用35B活跃参数、约1T总参数的稀疏混合专家（MoE）架构，拥有256K超长上下文窗口。完全基于干净且拥有商业许可的企业级数据...

EdgeClaw 是面壁智能联合清华大学等机构开源的端云协同 AI 智能体框架，主打安全可控与本地部署。首创三层数据安全协议（S1/S2/S3），通过规则检测器与本地 LLM 语义检测器实时分类请求敏...

HunyuanVideo 1.5 is a Tencent hybrid big model team open source lightweight video generation model , based on the Diffusion Transformer (DiT) architecture , the number of parameters is 8.3B. support for generating 5-10 seconds of high-definition video , sub...

企业知识库管理员：需要统一检索文档、会议录音、培训视频、产品图片等多模态资料的企业用户 RAG 应用开发者：为多模态内容提供语义检索能力，提升生成质量的 AI 应用开发者 法律/医疗行业从业者：如 E...

Fara-7B is a Microsoft open source release of a 7-billion-parameter-scale computer-operated agent (CUA) model based on the Qwen 2.5-VL-7B architecture. By visually parsing web page screenshots and performing clicks, inputs, and other actions on the screen, without relying on additional accessibility trees or multiple large models...

Pascal Editor 是基于浏览器的3D建筑设计与可视化工具，专为建筑师、设计师和开发者打造，支持在网页端直接进行楼层规划、空间布局和建筑场景探索。采用现代Web技术栈（React Three ...

Step-Audio-EditX is an open source audio editing grand model, developed by the Step-Star team, focusing on fine-grained manipulation of audio content through artificial intelligence technology. The model can dynamically adjust the mood of the audio, speaking style (such as petulant, old man accent, etc.) and paralinguistic elements (such as laughter, sigh...

LazyCraft is an open source AI Agent application development and management platform built by Shangtang based on the open source framework LazyLLM, which provides one-stop AI application development solutions for enterprises and developers. It helps developers to quickly build and release large model applications with low threshold and low cost...

MiMo-V2-TTS是小米推出的自研语音合成大模型，与MiMo-V2-Pro、MiMo-V2-Omni共同构成小米面向"Agent时代"的三大基础模型矩阵。模型基于自研Audio Tokenizer...

Depth Anything 3 (DA3) is a 3D visual reconstruction model developed and open-sourced by the Byte Jump Seed team. Through a single Transformer architecture to realize the spatial geometry of any viewpoint reconstruction, only need to predict the depth map and ray map can restore the three-dimensional scene, compared to...

Astron Agent is an open source enterprise-grade intelligent workflow development platform of KDDI , focusing on helping enterprises quickly build a landable AI agent application . Using Java + Spring Boot technology stack , support for lightweight private deployment (minimum 2-core 4G configuration) , built-in ...

NewBie-image-Exp0.1 is the first experimental anime text-born graph model open-sourced by the NewBieAI-Lab team, using the Next-DiT architecture with 3.5B parameters, optimized for the secondary style. The model is optimized for the secondary style by a dual text encoder (GEMMA3-4B...

阿里云百炼CLI（Bailian CLI）是阿里云Model Studio官方开源的命令行工具，通过一行命令即可让任意AI Agent自动调用阿里云百炼平台的150+款模型和10+款应用能力，涵盖文本...

Petri is an open source AI security auditing framework developed by Anthropic that systematically assesses the security and behavioral alignment of AI models. By simulating a real-world scenario where an automated auditor engages in multiple rounds of conversations with a target model, followed by a judge agent that acts on the model's...

SenseNova-SI is an open source spatial intelligence grand model released by ShangTech, focusing on improving AI's ability in spatial understanding and reasoning. The model excels in six core dimensions, including spatial measurement, reconstruction, relationship judgment, perspective transformation, deformation analysis, and spatial reasoning, significantly outperforming other...

Composer 2 是 AI 编程平台 Cursor 推出的专有代码大模型，主打"长周期智能体编程"。模型支持 20 万 Token 上下文窗口，能自主处理包含数百个操作的复杂开发任务，在 Term...

PrismAudio 是阿里通义实验室推出的视频生成音频框架，专注于为视频自动匹配严丝合缝的环境音效。框架创新性地引入"分解式思维链"（CoT）机制，让模型在生成音频前先分析视频内容、声音时序、音质特...

Bee is a full-stack open-source multimodal big model solution jointly launched by Tencent Mixed Element team and Tsinghua University to narrow the performance gap between open-source and closed-source models by improving data quality. The project contains three core achievements: 15 million scale high-quality two-layer CoT dataset Honey-Data...

SmartResume is Alibaba open source intelligent resume parsing and optimization tool , can efficiently extract structured information from PDF, images or Office documents , such as basic information , education and work experience . By integrating OCR technology and PDF metadata...

Vidu Claw（代号"V龙"）是生数科技旗下 Vidu AI 平台推出的 AI 创意智能体，定位为"你的第一个 AI 创意员工"。基于 Vidu 视频大模型构建，能自动完成从创意理解、脚本撰写、分...

LongCat-Audio-Codec is an open source speech codec solution from the LongCat team of Meituan. The program is designed for Speech Large Language Model (Speech LLM), through the semantic and acoustic dual Token parallel extraction mechanism , taking into account the semantic and acoustic features of speech ...

Open CoDesign是 OpenCoworkAI 团队开发的开源桌面端 AI 设计工具，采用 MIT 协议，定位为 Claude Design 的开源替代品，同时覆盖 v0 by Vercel...

GPT-5.4是OpenAI推出的旗舰AI模型，专为复杂专业场景设计。模型突破性融合推理、编程、原生计算机操控与深度搜索四大能力，在OSWorld测试中首次超越人类操作水平，知识工作任务表现达专家级标...

ChatTutor is an open source AI teaching aid focused on visual and interactive learning of STEM subjects. Through the multi-intelligent body architecture to achieve dialogical Q&A and dynamic drawing function, can draw math graphs, physics circuits or mind maps on the whiteboard in real time, to help users intuitively understand the abstract generalization ...

Supertonic is open source, high-performance text-to-speech (TTS) system focused on rapid speech generation on local devices. Using ONNX Runtime technology, it can run on devices such as cell phones, computers and even Raspberry Pi, supports 23 languages and speech clones, and requires no network...

Glow is open source command line tool for elegantly rendering Markdown files in the terminal. The tool supports highlighting code blocks , mathematical formulas and other complex elements , providing a wealth of features such as custom styles , paging display , mouse support and so on.

SkillOpt 是微软研究院开源的 Agent 技能自进化框架，核心创新在于将自然语言编写的技能文档视为可训练的外部参数，无需修改底层大模型权重。系统通过"执行-反思-编辑-验证"闭环运作：冻结的目...

Gemini 3.5 Live Translate 是 Google 发布的最新实时语音翻译模型，支持 70 余种语言和 2,000 多组语言对，覆盖全球绝大多数语种。采用流式实时翻译技术，输出仅落后...

FIBO is the world's first open source text generation image model with native JSON support developed by Bria AI. Based on the DiT (Diffusion Transformer) architecture with 8B parameters, it adopts the Flow Matching training method...

GLM-5V-Turbo是智谱发布首个原生多模态Coding基座模型，专为视觉编程打造。模型从预训练阶段深度融合视觉与文本能力，能直接理解设计稿、网页截图、K线图表等视觉信息并生成可运行代码，实现"所...

Octask 是深圳光魔科技推出的新一代 AI 原生内容工作室平台，由谷歌与腾讯背景团队打造，获得百度 A 轮投资。核心创新在于将 AI 工具"员工化"，通过像素风格的沉浸式虚拟工作室，让创作者以"老...

Xiaomi MiMo-V2.6是小米开源的全模态大模型系列，含Pro和Flash两个版本，通过大规模Agentic强化学习训练，不到6天完成约75万条任务轨迹，强化了代码、软件工程、视觉和网络安全等...