bitcoin
bitcoin

$61769.147764 USD

-2.81%

ethereum
ethereum

$1743.384989 USD

-3.33%

tether
tether

$0.999069 USD

0.02%

bnb
bnb

$571.804060 USD

-2.80%

usd-coin
usd-coin

$0.999854 USD

0.00%

xrp
xrp

$0.966271 USD

-1.46%

solana
solana

$72.584973 USD

-3.00%

tron
tron

$0.309764 USD

-0.92%

hyperliquid
hyperliquid

$65.747085 USD

-3.44%

zcash
zcash

$851.603224 USD

-9.10%

dogecoin
dogecoin

$0.057499 USD

-3.10%

monero
monero

$477.774191 USD

-4.85%

unus-sed-leo
unus-sed-leo

$9.211262 USD

-1.40%

chainlink
chainlink

$8.864427 USD

-3.12%

cardano
cardano

$0.149815 USD

-2.47%

Cryptocurrency News Video

Tongyi DeepResearch: Alibaba's Open-Source Deep Research Agent | OpenViST Listing

Nov 16, 2026 at 01:33 am OpenViST

Tongyi DeepResearch is Alibaba Tongyi Lab's open-source deep research agent: an agentic language model with 30.5 billion parameters, 3.3 billion active per token, built for long, multi-step web research. Listing: https://openvist.com/site/deepresearch/ Sources OpenViST listing: https://openvist.com/site/deepresearch/ Official repository: https://github.com/Alibaba-NLP/DeepResearch Tech blog: https://tongyi-agent.github.io/blog/introducing-tongyi-deep-research/ Model on OpenRouter: https://openrouter.ai/alibaba/tongyi-deepresearch-30b-a3b Chapters 0:00 Welcome to OpenViST 0:15 What it is 0:30 How it works 0:50 Find the listing The repository is public and licensed under Apache-2.0. It is developed by Tongyi Lab (Alibaba-NLP). Per the README, Tongyi DeepResearch is an agentic LLM with 30.5 billion total parameters and 3.3 billion activated per token, designed for long-horizon, deep information-seeking tasks. It supports ReAct inference and an IterResearch-based Heavy mode. Running it needs the model weights (MODEL_PATH in run_react_infer.sh) and API keys set in .env, including Serper for web search, Jina for page reading and an OpenAI-compatible API for summarization. The model is also available through OpenRouter, which runs without GPUs. The commands shown are taken from the Quick Start section of the official README; the recommended Python version is 3.10.0. The listing's practical guide is source-based: OpenViST has not run or independently tested this project. Follow OpenViST X: https://x.com/openvist GitHub: https://github.com/Open-ViST YouTube: https://www.youtube.com/@openvist
Video source:Youtube

Disclaimer:info@kdj.com

The information provided is not trading advice. kdj.com does not assume any responsibility for any investments made based on the information provided in this article. Cryptocurrencies are highly volatile and it is highly recommended that you invest with caution after thorough research!

If you believe that the content used on this website infringes your copyright, please contact us immediately (info@kdj.com) and we will delete it promptly.

Other videos published on Nov 20, 2026