AI tools for Agent

Atoms.dev is a multi‑agent product development platform that transforms plain‑language ideas into fully functional, production‑ready web and mobile applications, without requiri

SenseNova 6.8 Flash is SenseTime's multimodal agent model for office work and content creation. It supports tasks that span several steps or sessions and can deliver outputs suc

This Qwen3.5-0.8B checkpoint is the released result of a weight-space programming experiment. The authors tasked an external language model with modifying the smaller model's te

DeepSeek Harness is an open-source runtime for coding and general-purpose agents. It is available in public preview as a desktop application and as a developer-facing web runtim

Phonic-1 is a hosted speech-to-speech model for voice agents. It receives the caller's audio directly and responds in spoken audio, using cues such as pace and hesitation to sup

Tencent Hy4 is the final hosted release of Tencent's flagship model for long-running agent tasks. It adds visual understanding to the earlier preview's text capabilities and sup

LongCat-2.5 is Meituan's hosted multimodal model for extended agentic work. It combines image understanding with code generation for tasks such as working across complex project

ToolSpace is a research toolkit for turning tool-use traces into executable training and evaluation environments. It focuses on long-horizon agent tasks that require several sta

Ling-3.2-Flash is Ant Group's hosted multimodal model for reasoning over text, images and video. Its model overview describes applications in visual understanding, spatial inter

Ripple-65B is Ricursive Intelligence's open-weight language model for general-purpose reasoning and agentic coding. It is a dense 65-billion-parameter transformer derived from t

GPT-6 Cyber is OpenAI's restricted model for authorized security research and defense. It can assist with investigating vulnerabilities, reproducing findings in approved test en

OpenRoboKit is a suite of open-source libraries for robotics development. Its components cover motion optimization, transfer of motion across embodiments, manipulation and agent

RoboSkills is an open collection of lightweight agent workflows and tools for robotics. It packages five working approaches: automated research, agent-as-policy control, agentic

SenseNova-Loop-9B-Preview is an open multimodal language model for long-context and agentic workflows. It accepts text and images and generates text, supporting document interpr

AutoSwarm coordinates existing AI agents into a shared working team. Instead of requiring one assistant to provide every capability, it connects compatible local agent tools, sh

SceneBloom creates realistic indoor environments for training embodied agents. It translates room descriptions into varied furniture layouts and simulation-ready scenes, coverin

Gemini 4 Carbon is Google DeepMind's frontier model for sustained engineering, reasoning, and multimodal work. The initial rollout focuses on selected cyber defenders and truste

Nanbeige4.3-33B is an open-weight language model for coding and professional agent workflows. It is the flagship teacher model in the Nanbeige4.3 series, combining task-oriented

Apex-35B-V1.0 is Apex Intelligence's open-weight model for general assistance and research-oriented agent work. It supports coding, question answering, search, and computational

Clover-35B-A3B-Preview is DiffuSpace's open-weight diffusion language model. It targets text generation and agentic workloads with a 35-billion-parameter mixture-of-experts back

Spark-X2.6-1.7B is a compact open-weight language model designed for practical on-device AI. It supports coding, planning, tool use, reasoning, and multilingual tasks while keep