TabTin is a full-stack, open-source AI agent team collaboration platform. The platform truly integrates agents into team workflows; tasks can be initiated on desktops, viewed on mobile devices, executed by server agents, and can be handed over with complete context...
FreeToken is an open-source edge-side MoE (Model-Based Inference) system for large models, jointly developed by UC Berkeley, MIT, and other institutions. The system utilizes full-layer double buffering, bandwidth-adaptive hybrid scheduling, agent state reuse, and elastic memory hot-scaling/scaling, among other features...
CoinVE-200K is a large-scale combinatorial instruction video editing dataset open-sourced by Tencent Video's Intelligent Creation Team. It contains 200,000 pairs of 1080p video editing samples, each containing 2-5 atomic editing instructions, including addition, removal, modification, etc.
LLM-as-a-Verifier is a general-purpose verification framework jointly open-sourced by Stanford, UC Berkeley, and NVIDIA Research. The framework requires no additional training and generates continuously fine-grained verification by using the complete logits distribution of LLM-scored tokens...
SenseNova U1.5 Lite is a lightweight, native unified multimodal large model open-sourced by SenseTime, designed specifically for real-world visual creation workflows. The model natively supports 3-4k character ultra-long instructions and features high-quality visual generation...
DeepSeek-V4-Flash-Vision-Exp is an experimental multimodal visual understanding model from DeepSeek. While retaining the text input capabilities of DeepSeek-V4-Flash, it adds visual input, and a multimodal agent...
Cocode is an open-source distribution of DeepSeek Harness, providing both a desktop GUI and a terminal TUI. The tool integrates files, Git, terminal, browser, and agent into a single workspace, with sessions synchronized in real-time. Agen...
Qwen-UI-Agent is a GUI intelligent agent foundation model developed by Alibaba's Tongyi team. It enables users to interact with interfaces on mobile phones, computers, and web browsers much like a real person. The model was trained on 100+ real devices and 150+ applications, and supports GUI...
Lumos NexCore, launched by Lumos Robotics, is an embodied intelligence evolution engine positioned as a skills infrastructure for industry applications. Lumos NexCore integrates data assets, model training, evaluation and verification, skills management, and robot...
Qwen3.8-27B-DFlash2 is an open-source speculative decoding draft model from Inco AI, specifically designed for Qwen3.8-27B. The model has only 1.92B parameters and achieves this through block-level parallel prediction, a lightweight path selector, and dual-tap dynamic convolution...
HarnessEval is an evaluation system launched by MirroS in collaboration with institutions such as Tsinghua University, Peking University, Berkeley, MIT, and NVIDIA. HarnessEval agentizes the evaluation process: for each case, the system dynamically plans the evaluation path, starting from S...
Academic Research Skills is an open-source academic skills plugin developed by Cheng-I Wu for Claude Code, covering the entire process from topic selection and research, paper writing, peer review, to final revisions. The plugin includes 39+ features...
Nature Skills is an open-source research skills library for AI scholars worldwide, focusing on the entire workflow of publishing Nature/CNS papers. Nature Skills uses a routed SKILL.md architecture and includes 18 built-in skills covering paper writing,...
ToolJet is an open-source, low-code platform, often referred to as an open-source alternative to Retool. The platform offers 60+ draggable components and 80+ data source connections, supporting a built-in PostgreSQL database, visual workflows, and JS/Python...
MemoraX Code is a long-term memory system designed specifically for Coding Agents, solving the pain point of agents needing to 're-learn' projects for each new conversation. The tool achieves cross-Agent communication through local code repository memory and cloud-based long-term memory...
WeLM (WeChat Language Model) is a large language model developed by WeChat, which has been iterated to V4. The model is specifically designed for the WeChat ecosystem, with approximately 80B-130B parameters. It adopts a sparse MoE architecture, emphasizing low cost and high efficiency.
Many people have probably had the thought of writing a song. Perhaps it's a sudden surge of emotion in the dead of night, a few off-key lines floating through your mind; perhaps it's wanting to prepare a special gift for someone important, only to find that nothing quite feels right...
Origin is an AI-native code hosting platform launched by Cursor, designed specifically for the Agent era. The platform provides core functions such as Git repository management, PR review and merging, and two-way synchronization with GitHub, and pioneered stacked PRs and Agents...
Many people who use AI to create songs have probably experienced a similar sense of disappointment: the songs they generate have smooth melodies and clever lyrics, and they listen to them on repeat, finding them increasingly enjoyable. However, once uploaded to platforms like TikTok or music streaming services, the data is surprisingly poor...
MyContext is an open-source Agent context infrastructure developed by Alibaba Cloud's Qianwen Office team. Running in a local-first mode, it can process multi-source work data from platforms like DingTalk and Lark, including IM communications, documents, and meetings, into continuously updated...
Luna-TTS is a large-scale text-to-speech model independently developed by VUI Labs, a startup company affiliated with Shanghai Jiao Tong University. The model abandons the mainstream autoregressive approach and adopts a Masked Diffusion architecture, based on Qwen3-0.6...
Mureka V9.5 is a new generation AI music generation model launched by Kunlun Wanwei. Based on the MusiCoT music thought chain framework, the model emphasizes restrained and natural arrangements and realism: the vocal quality rate has increased to 61%, and the overall quality control rate reaches 9...
DeepSeek Harness Desktop is a community-developed, open-source desktop client based on DeepSeek Harness, supporting Windows and macOS. The tool encapsulates Harness's web UI, local services, and plugin system into a unified package...
HiDream-O1-World is a native, multimodal, interactive world model launched by HiDream.ai, built on its self-developed UiT architecture.