Tencent

High Performance LLM Inference Operator Library

The High Performance LLM Inference Operator Library is an open-source project developed by Tencent, designed to optimize the inference performance of large language models (LLMs). It provides a set of operators and tools that enhance the efficiency and scalability of LLM deployments, making it easier for developers to integrate and utilize LLMs in various applications.

Hy4

Tencent Hy4 preview is a high-performance, open-source large language model designed for real-world productivity and complex reasoning tasks. It represents the latest iteration in the Tencent Hunyuan (Hy) series, focusing on enhanced agent capabilities and seamless integration into professional workflows.

CL-bench

CL-bench is a benchmark designed to evaluate language models' ability to learn from complex, context-dependent tasks. It comprises 500 complex contexts, 1,899 tasks, and 31,607 verification rubrics, all crafted by experienced domain experts.

BrowserSkill

BrowserSkill is an open-source tool that enables AI agents to interact with a user's real, logged-in Chromium-based browser. It provides a CLI and browser extension that allow agents to perform tasks like reading pages, filling forms, and debugging websites while maintaining the user's existing session state.

WeKnora

WeKnora is an open-source, LLM-powered knowledge framework designed for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. It transforms raw documents into a queryable RAG system, an autonomous agent, and a self-maintaining, interlinked Wiki.

Hy3

Hy3 is a powerful 295B-parameter Mixture-of-Experts (MoE) large language model developed by Tencent. It features 21B active parameters per token, a 256K context window, and is designed to deliver high-performance reasoning, agentic workflows, and long-context processing at lower compute costs.

HY-1.8B-2Bit

HY-1.8B-2Bit is a 2-bit quantized large language model developed by Tencent's AngelSlim project. It utilizes Quantization-Aware Training (QAT) on the Hunyuan-1.8B-Instruct backbone, achieving high performance with significantly reduced model size.

AngelSpec

AngelSpec is a unified, torch-native training framework designed for speculative decoding, supporting both autoregressive Multi-Token Prediction (MTP) and block-parallel drafting architectures. It enables independent scaling of inference and training through a disaggregated architecture, facilitating high-performance model deployment.

TeamAI CLI

TeamAI CLI is a Git-native management tool designed to make teams 'AI native' by synchronizing skills, rules, MCP configurations, and knowledge bases across various AI coding agents. It enables teams to maintain a shared harness in a Git repository, ensuring consistent AI behavior and collective learning through automated workflows.

HY-MT1.5

HY-MT1.5 is a multilingual machine translation model developed by Tencent, available in 1.8B and 7B parameter versions. It supports translation across 33 languages and 5 ethnic and dialect variations, optimized for both on-device and cloud deployment.

Youtu-VL-4B-Instruct-GGUF

Youtu-VL-4B-Instruct-GGUF is a lightweight yet robust Vision-Language Model (VLM) developed by Tencent. Built upon the Youtu-LLM with 4 billion parameters, it introduces the Vision-Language Unified Autoregressive Supervision (VLUAS) paradigm, enhancing visual perception and multimodal understanding. This model excels in both vision-centric and general multimodal tasks without the need for task-specific modules.

Cube Sandbox by Tencent

Cube Sandbox is an open-source high-performance sandbox runtime for AI agents built on RustVMM and KVM. It achieves sub-60ms cold starts, under 5MB memory per instance, hardware-level kernel isolation, and supports thousands of concurrent sandboxes per node. 100% E2B SDK compatible with zero code changes to migrate.

UI-Mate

UI-Mate-27B is an open-weight foundation GUI agent designed for long-horizon desktop automation across various operating systems. It observes live screen states to reason and execute structured keyboard and mouse actions, supporting in-context demonstrations to improve task accuracy.

TencentDB Agent Memory

TencentDB Agent Memory is a fully local, open-source long-term memory system for AI agents built by Tencent. Using a 4-tier progressive pipeline with symbolic short-term memory (Mermaid canvas) and layered long-term memory (L0→L3 persona hierarchy), it cuts token usage by 61% and improves agent task success by 51% when integrated with OpenClaw — with zero external API dependencies.

WorkBuddy Bench

WorkBuddy Bench is a multi-domain evaluation suite designed to test coding agents on realistic, complex tasks across software engineering, web development, office workflows, and security. It features 260 contamination-resistant tasks reverse-engineered from real-world commits and business scenarios to ensure agents are evaluated on genuine problem-solving capabilities rather than memorized data.