Stars
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…
Replace coding puzzles with real-work simulations.
AgentClaw turns one-sentence ideas into reusable Claw capabilities. Build less boilerplate with declarative workflows, computer browser code file control, MCP, Skills, memory, knowledge bases, trac…
Official Implementation of "PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations"
First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come …
Unified real-time search engine skill for AI agents.
Modular SenseNova skills for building AI-powered office assistants and productivity workflows
DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adjusting their mixing ratios.
Personal-Model First Self Evolving AI Agent 🐘
Text and code embeddings research from CodeFuse: C2LLM, D2LLM, E2LLM, F2LLM, ML-Embed
Agent trace and tool-use safety evaluation lab.
Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.
Engineering toolkit for building scalable AI systems, including model training pipelines, LLM optimization utilities, and data engineering tools.
[ICLRW 2026 Best Short Paper Award] Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
DeepBot is a system-level AI assistant built for both personal productivity and enterprise workflows — one-click setup, seamless experience, and native Feishu integration.
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
Agent-native knowledge engine with MCP tools for document indexing, wiki organization, fast retrieval and deep reading across PDF/DOCX/PPTX/Markdown
Failure-first AI regression testing CLI for turning AI failures into local regression assets and PR gates. 把真实 AI 失败快速变成可执行回归资产和防止再次犯错清单。
Quant trading agent: Get minute-level, MBB-grade investment insights powered by SEC and 10-K filings.
🤖🧠👾 Graph VLA with Control Barrier Function in Dual-Arm Robotics Manipulation
OpenClaw 安全巡检工具，一键执行系统安全扫描并生成通俗易懂的报告。 使用场景：用户说"安全巡检"、"安全检查"、"安全审计"、"巡检"、"security audit"、"检查安全"、"系统安全"等。 触发条件：任何与 OpenClaw 安全检测、审计、巡检相关的请求。