Agents
AIEZZ tool tag
Browsing AI products tagged “Agents”, with 23 matching results.
Orchard – Microsoft Research’s Open-Source Agentic AI Modeling FrameworkAI AgentsOrchard – Microsoft Research’s open-source Agentic AI modeling framework. Centered on the Kubernetes-based Orchard Env environment service, the framework supports cross-domain sandbox reuse for data distillation, reinforcement learning rollouts, and evaluation, covering three major scenarios: software engineering, browser navigation, and personal assistants. It provides complete SFT + RL training recipes, along with 107K SWE trajectories and 3,070 GUI multimodal rollout data points, and enables end-to-end training directly in real harnesses such as Codex and OpenClaw. Designed for academic and industrial teams conducting Agent research and development, Orchard offers lower compute and hosting costs while helping smaller models approach frontier performance through cross-harness generalization.00
wigoloAI Agentswigolo is an open-source local search tool that connects to coding agents such as Claude Code and Cursor via MCP. No API key is required, enabling free local search, web fetching, site crawling, structured extraction, ...00
MemHarness – An Agent Memory Reconstruction Framework by Shanghai AI Lab and OthersAI AgentsMemHarness is an LLM Agent memory reconstruction framework released by Shanghai AI Lab in collaboration with Zhejiang University, Fudan University, Shanghai Jiao Tong University, and other universities. It inserts critique and reconstruction steps between retrieval and action, using the current context to retain, rewrite, or discard historical experiences. It uses GRPO for end-to-end training and requires no additional human annotations. The framework supports the complete workflow of memory retrieval, critique and reconstruction, action generation, experience write-back, and pruning, and provides a five-stage decision-making process. Its 7B-parameter model surpasses Gemini-2.5-Pro by 23.1% and 39.7% on ALFWorld and WebShop, respectively, achieving an average success rate of 85.9% in out-of-distribution scenarios. It is suitable for embodied household tasks, autonomous online shopping, intelligent customer service, code-assisted development, and other scenarios.10
LongCatAI Conversational ChatLongCat is an open-source large language model released by Meituan. It uses a mixture-of-experts architecture with 560 billion parameters, dynamically activating approximately 27 billion parameters at runtime for text understanding, complex reasoning, and conversational tasks. Users can provide long documents or ongoing conversations for the model to process, making it suitable for developers, enterprise users, and artificial intelligence researchers exploring document analysis, coding assistance, mathematical reasoning, and intelligent agent workflows. LongCat supports inputs of up to 128k characters and offers free usage options. Note that actual performance, response speed, and deployment costs still depend on the task type, operating environment, and specific method of use.138.5
ForgeStencil – ForgeStencil: FaceWall Intelligence’s Fully Automated Stencil Research and Deployment SystemAI AgentsForgeStencil – FaceWall Intelligence’s fully automated Stencil research and deployment system is jointly developed by FaceWall Intelligence and the OpenBMB community. It adopts a dual-agent closed-loop architecture consisting of a Kernel Agent and an App Agent. The system autonomously completes the entire process, from discovering optimization strategies and synthesizing high-performance CUDA Kernels to production-grade application integration and validation, with zero human intervention. Within one week, the system completed end-to-end optimization for more than 100 industrial and scientific computing software applications, achieving a median speedup of 1.41×. It covers 8 major industrial and 5 major scientific domains, including oil and gas exploration, electromagnetic simulation, and medical imaging, significantly reducing reliance on HPC experts and shortening development cycles.00
ClawTeamsAI AgentsClawTeams is an AI-powered e-commerce operations collaboration platform. Users send a one-line goal in IM tools such as Slack, Teams, and WeChat, and the AI Team Lead automatically breaks down the task and dispatches 30+ expert Agents to execute in parallel, ...00
PAST-BenchAI AgentsPAST-Bench is a benchmark introduced by Mengdi Wang's team at Princeton University to evaluate the recursive self-improvement capabilities of personal AI agents. By comparing task performance under conditions with and without memory, PAST-Bench deter...00
Grok BotAI AgentsGrok Bot is an AI Agent system launched by SpaceXAI. It can log into users’ accounts and operate websites and tools like a real person, completing actual work for users in the cloud 24/7. The system supports parallel collaboration among multiple Bots, recorded...00
EvoXAI AgentsEvoX is a self-evolving AI Agent launched by EvoMap. It uses a swarm model to split complex tasks among multiple Agents for parallel processing and aggregate the results, avoiding context contamination. Agents can inherit experience from across the network to achieve self-evolution,具...00
MindMemOS – Huawei Noah's Ark Lab's Open-Source AI Agent Memory Operating SystemAI AgentsMindMemOS – Huawei Noah's Ark Lab's open-source AI agent memory operating system, designed to provide agents requiring long-term memory management with an open, reusable memory layer. It uses a three-dimensional entity–attribute–time structure to decouple memory from individual agents and turn it into an independent, cross-framework asset. Through mechanisms such as Dreaming for offline organization, Feedback for correction, and Skill Evolution for automated improvement, it continuously optimizes memory. The system provides dual-mode memory writing (MindVanilla and MindSchema) and multi-path Compact Search retrieval, supporting Docker local deployment, cloud APIs, a Python SDK, CLI, and other integration methods. With over 94% structured recall accuracy and a 10% improvement in question-answering accuracy after memory compression, it helps developers share information across sessions and improve task efficiency in scenarios such as personalized assistants, multi-agent collaboration, and complex office automation.00
Nemotron 3.5 LightningAI AgentsNemotron 3.5 Lightning is NVIDIA's open-source 30B-parameter MoE model, optimized for multi-agent systems. Compared with similar models, it delivers 4× faster output and accelerates agent task completion by 30%, while...00
Gemini 3.5 FlashAI Intelligent AssistantsGemini 3.5 Flash is an AI assistant for developers, product designers, content and operations teams, and researchers. According to the provided materials, Google introduced it at I/O 2026. It continues the Flash series’ low-latency positioning and is designed for complex reasoning, long-context analysis, and advancing multi-step tasks. Users can input text, images, video, audio, or PDFs, then combine function calling, structured output, search, and code execution for information organization, code generation, debugging, prototype development, and workflow assistance. It is suited to processing long documents, code snippets, and information across multiple files, and can also support enterprise automation and cross-team collaboration. Actual results still depend on input quality, task complexity, and tool configuration, so important content requires human review.068.6
Kitesurf – Cloudflare’s Lightweight Cloud Browser for AI AgentsAI AgentsKitesurf is a lightweight cloud browser for AI Agents developed by Cloudflare. Built in Rust and running in Workers V8 isolates, it removes human-oriented features such as tabs and extensions, focusing instead on DOM parsing, JavaScript execution, and data extraction. It is compatible with both CDP and MCP, allowing Puppeteer and Playwright to connect without rewrites. Compared with Chromium, it uses over 3 times less CPU and 4.7 to 7 times less memory, making it suitable for high-concurrency, stateless AI Agent tasks. Developers can use the Quick Actions API to capture screenshots, extract HTML, or generate PDFs with a single request, or try it online in the Playground.00
E-Bench – An Agent Evaluation Benchmark by Tencent Hunyuan and OthersAI Model EvaluationE-Bench is a benchmark for evaluating multi-step tool use, developed by the Tencent Hunyuan team in collaboration with Tsinghua AIR and Southeast University. It builds fully synthetic virtual environments based on Honor of Kings, QQ Music, and Tencent Meeting, containing 323 state-change tasks and more than 76,000 data records. Through dual asymmetry in information and tools, it evaluates whether models can proactively gather information and orchestrate multi-step tool calls. Deterministic database state-diff scoring ensures stable and reproducible results. The benchmark is intended for AI agent researchers and model developers, helping identify cost-effective models and advance the establishment of general-purpose agent evaluation standards.00
Boundless AllAI AgentsBoundless All – Alibaba Cloud’s multi-role Agent collaboration workspace for enterprises and individual entrepreneurs. By automatically bringing together digital employees such as PMO, development, and testing into collaborative groups, it enables complex projects to be advanced and delivered through coordinated handoffs. The platform provides ready-to-use scenario templates, flexible integration of local Agents, and automatic accumulation and reuse of assets, supporting a dual-mode switch from single-turn conversations to multi-Agent group chats. Its built-in coordination Agent keeps multi-role collaboration aligned, while the entire process remains transparent and traceable, helping users transform execution processes into reusable team assets and SOPs.00
Qwen-CUA – A Native Computer Use Agent from Alibaba Qwen and OthersAI AgentsQwen-CUA – a native Computer Use Agent developed by Alibaba Qwen and others – is built on a 397B-A17B mixture-of-experts architecture. It perceives interface states solely through screenshots, without relying on the DOM tree or accessibility metadata, and directly outputs keyboard and mouse events to control browsers, desktops, and professional software. It scores 86.2 on the OSWorld-Verified benchmark, while the larger Qwen-CUA-Max reaches 87.6, placing it among the leading open-source CUA systems. With end-to-end vision-action training, it offers cross-platform versatility and high stability. Its technical report and demo are open source, supporting use cases such as automated testing, RPA, accessibility assistance, and control of scientific software.00
Muse Code – Meta’s Terminal Coding AI AgentAI ProgrammingMuse Code – Meta’s Terminal Coding AI Agent is a terminal coding AI agent developed by Meta and powered by the Muse Spark 1.2 model. It can handle complete software engineering tasks in large codebases, including planning changes, writing code, and verifying results. Its background agent continuously accumulates context throughout a session, supports splitting large tasks into multiple sub-agents for parallel execution, and provides auditable local event logs that enable recovery from the point of interruption after a crash. It is suitable for developers and teams seeking efficient, traceable, and secure software engineering automation, especially for large-codebase refactoring, game feature development, kernel performance optimization, and compliant development in sensitive industries.00
Today AIAI AgentsToday AI is a personal AI agent operating system launched by Qi Junyuan, the former founder of Teambition. The product connects to computers, local files, text messages, calendars, and various cloud services, continuously building long-term user memory to achieve a transition from passive response to proactive action...00
Muse Glimmer – Meta's Open-Source 30B-Parameter Large Language ModelAI AgentsMuse Glimmer is Meta's open-source 30-billion-parameter large language model, deeply optimized for always-on local Agent workflows. With 4-bit quantization, the model runs smoothly on a single GPU with 24 GB of VRAM or Apple Silicon (M4/M5 Max) with 32 GB of unified memory, with nearly zero performance degradation. Integrated DFlash speculative decoding delivers up to 3.1× faster performance on high-end hardware such as the RTX 5090. The model supports multimodal tasks including real-time conversation, tool calling, code generation, and multi-step reasoning. It is suitable for individual developers, small and medium-sized businesses, and privacy-sensitive industries such as healthcare and finance, providing efficient local AI capabilities with a low VRAM requirement while keeping all data on the device.00
Warp Agent CLI – Warp’s Standalone Command-Line Coding ToolAI AgentsWarp Agent CLI is Warp’s standalone command-line coding tool, running in any environment including Ghostty, iTerm 2, VS Code, and system terminals. Built on Warp’s terminal infrastructure, it includes a native multiplexer for managing pty connections and preserving Agent context across directories and SSH sessions. It can drive full-screen interactive applications such as sqlite and python, supports the MCP protocol, and automatically orchestrates local and cloud sub-Agent tasks, including delegation to Claude Code or Codex.00
WorldClaw – A 3D World Generation Framework from Tencent Hunyuan Team3D DesignWorldClaw is an Agent-driven open-world 3D generation framework developed by the Tencent Hunyuan team. With a single natural-language description, the system automatically plans terrain, regions, buildings, objects, and spatial relationships. Using a coarse-to-fine generation strategy, it builds complete 3D scenes in Blender that can be freely explored and edited object by object. The framework is powered by multiple collaborating models, including Claude Opus, GPT-Image-2, SAM3, and Hunyuan3D. It also features visual Agent-based self-checking and repair, automatically correcting contact issues such as floating objects and mesh intersections.00
Gemini 3.7 FlashAI ProgrammingGemini 3.7 Flash is the next-generation flagship AI model from Google DeepMind. Designed specifically for coding and agent workflows, it delivers major gains across software engineering, web development, and enterprise automation benchmarks...00
Omega – Tencent’s AI-Native Data Analysis PlatformAI Data AnalysisOmega – Tencent’s AI-Native Data Analysis Platform is an AI-native data analysis platform launched by Tencent. Its internal beta version is called “Marmos (marmos).” Powered by an Agent, the tool enables a complete analysis workflow, allowing users to generate interactive, iterative, and regularly refreshed data dashboards with natural language, truly embedding AI into business workflows. Core features include one-click AI dashboard generation, natural-language iterative editing, intelligent filter linkage, semantic model integration, monitoring alerts and scheduled delivery, a multi-style visualization engine, and version management and collaboration. It is suitable for scenarios such as e-commerce operations, content monitoring, financial reporting, product governance, and marketing attribution, helping enterprises achieve end-to-end intelligence from data understanding to decision-making and action.00All tools with this tag are shown.