Zenki shimitora retweeted
Live Web Data API from Teneo gives your Grok bot live web data in 3 steps.
Add livewebdata.com/mcp as the MCP server, paste in your key from livewebdata.com, and start using it.
The free test account is enough to try it.
How to set up Live Web Data API by @teneo_protocol for your Grok @bot (5 seconds):
1. Give it the MCP server: livewebdata.com/mcp
2. Give it your key from livewebdata.com/
3. Done. Start to use it with your free test account.
Zenki shimitora retweeted
What does it cost an AI agent to read X? We priced one crypto sentiment workload on the three main routes.
The workload: an hourly search on 20 cashtags, plus daily timelines and profiles for 100 accounts. That is 390,000 posts and 3,000 profiles in 30 days.
At each provider's published price on 18 November:
Official X API: 1,980 dollars.
xAI X Search: 1,980 dollars plus model tokens.
Teneo X Platform Agent: 420 USDC.
That is about a fifth of the cost of X's own API for the same posts.
Price is one line of the bill. The other is setup. The other two routes start with an account, prepaid credits and an API key someone has to store. That is fine for a team building one product. It is the step that fails when an agent needs data nobody set up for it in advance.
On Teneo, the agent pays for each request itself through x402, with no account or API key. It sees the price before the call runs.
The same payment also reaches the CoinMarketCap, Messari and Nansen agents on the network, so one session can read the posts about a token and the token's market data without a second account.
It is already where social data demand goes on Teneo: Agent Console shows 451,802 requests to the X Platform Agent, 89.5% of the requests to our four social data agents. Those counts are cumulative and may include test calls.
The full comparison, the caveats that move each number, and all ten X commands with prices:
teneo-protocol.ai/blog/how-t…
Building a crypto research or sentiment agent? Reply with the accounts and cashtags you watch and we will set you up with a free seven-day pilot.
Zenki shimitora retweeted
Live Web Data by Teneo Protocol is now listed on mcp.so and mcpservers.org.
Fetch any public page live, as local visitors see it, from the country you choose. Clean Markdown back. Hosted remote MCP, nothing to install.
More platforms to come.
mcp.so/servers/live-web-data
mcpservers.org/servers/live-…
I just got onboard @VOICECC Express! Its your LAST call! Ends in 4 days!
1
1
5
Zenki shimitora retweeted
The future of AI depends on access to real-time information.
That’s exactly what Teneo Live Web Data brings to AI agents.
Built for developers and AI-powered applications, it enables agents to:
Fetch live content from public websites
Extract clean Markdown, text, or HTML
Access localized web results through geo-targeting
Retrieve information using a simple API or remote MCP server
No more relying solely on outdated information.
AI agents need live data to make smarter decisions, and @teneo_protocol is helping make that possible.
The next generation of AI will be powered by real-time data.
Explore: mcp.so/servers/live-web-data
The ODDI allowlist is officially open!
Give this a repost to spread the word and
apply here: byoddi.com/#allowlist
If you're followed by ODDI - congratulations you're already on our GTD Early Supporters list! 🎉
We've spent the past year quietly building ODDI.
Now we’re putting the finishing touches on 4,444 collectible characters coming to Ethereum.
Blending the expression of 2D anime with the depth and texture of 3D, we've created our own 2.5D world where anime soul meets designer-toy spirit.
Every ODDI has its own personality. Some are cute, others a little scary. Some hide behind masks, while others are perfectly happy showing up in pyjamas.
PHASE 02 starts here. You’ve seen glimpses of the collection. Now it’s time to meet more of the cast.
Whether you’ve been with us since day one or you’re just clocking in for PHASE 02, we’re glad you found us.
Welcome to the world of ODDI 🌐
Stay ODD. Stay curious. 👾
Zenki shimitora retweeted
A crowd can label a stop sign. It can't label a chest X-ray.
The AI data worth most needs doctors, lawyers and engineers. Labeling vendors struggle to find them.
A token-incentivized network can ask its own contributors. Perceptron's upcoming data quests start there.
Zenki shimitora retweeted
Polyester Testnet now supports @0xPolygon network and ethereum:0x455e53cbb86018ac2b8092fdcd39d8444affc3f6 trading.
We are giving away $10,000 to our users to celebrate!
To enter:
• Like + repost this post
• Login to Polyester Testnet and trade any pair
• Reply with your Polyester username
Good luck!
Zenki shimitora retweeted
Local prices, live, from any country your agent needs.
One URL, one country code, and your agent sees what a visitor in that country sees: local prices, local currency, local offers.
How it works, with real examples, below.
livewebdata.com View article
Zenki shimitora retweeted
Welcome to the Giraffies Valley!
6666 Lil Giraffies are coming soon on Robinhood Chain.
🔹Raise giraffies.
🔹Grow the valley.
🔹Harvest $GIRAFF
Whitelist registration is now live (Freemint)
Join the Valley🦒
🔗 valley.loculus.xyz/lil
Zenki shimitora retweeted
Keep your Beacon running!
AI is only as good as the information it can reach. If it can't see what's on the web right now, its answers fall behind.
That's what @teneo_protocol fixes. People like me run an app called Beacon, and our devices help AI pull live info from the web.
10M+ requests went through the network in 4 days. That's about 30 every second, and it's the most it has ever handled. Watching it grow from the inside is wild.
Zenki shimitora retweeted
Today, we're launching the Live Web Data API by Teneo Protocol to the public.
One API that delivers public web pages live as clean Markdown or text, ready for AI agents and apps.
Zenki shimitora retweeted
We compared old copies of public web pages with what those pages say now. A third had lost at least 5% of their text within 30 days.
A RAG index is a copy, and a copy stops changing the day you make it.
We took a fixed list of pricing pages, documentation and official rates, and compared Internet Archive captures of different ages.
After 30 days, 16 of 48 pages had lost at least 5% of their text. After 180 days, 31 of 47 had. After 30 days, 9 of 48 had lost at least one price, percentage or version number.
Mistral's pricing page listed 10, 15 and 30 dollars a month in API credits on 7 October. By 12 October it listed 15 and 25.5. A copy indexed on 7 October still says 10 and 30, with a valid citation and no error.
The usual fix is a webhook, and that only works for sources you own. A page on someone else's website has no webhook for you. So you have to go and look.
27 of the 54 live pages we tested can be checked without a download, because they answer a conditional request with a 304. The rest have to be fetched and compared.
Teneo supplies that re-fetch: the page requested from the market you name, through a connection whose owner agreed to share it, paid per request.
It is a small hand-picked list, so treat it as a floor. The post covers how to spot changes on a site you do not own, how often to re-fetch each kind of page, and the free seven-day pilot for RAG teams:
teneo-protocol.ai/blog/how-t…
Building RAG on public pages?
Reply with the sources you trust least and the markets they serve.
🔥 THE $LWT COUNTDOWN HAS STARTED
ICO Round 1
📅 11 November
⏰ 13:00 UTC
The product is live.
The community is growing.
And the next phase of LF Wallet is about to begin. 💚
📖 Full announcement:
🔗 lfwallet.app/blog/lf-wallet-…
$LWT is coming.
Are you ready?
#LWT #LFWallet #ICO #BNBChain #Web3 #CryptoCommunity
Zenki shimitora retweeted
The Season 4 reveal is live.
Check the Teneo Hub to see if you won: hub.teneo.pro
While you are there, check that your wallet is connected and up to date.
Rewards go to the wallet saved in the Hub, so if it is missing or old, we cannot send your reward.
If you won, approve your wallet in the Hub, same as every season.
Zenki shimitora retweeted
If your AI agent gets out of its sandbox, what can it reach?
Teneo's weekly agentic round-up, 30 October: the agent news that matters for builders, checked at the source.
- OpenAI now trains its frontier models with no live internet access. After a model reached the internet through a misconfigured DNS resolver, OpenAI set its own agents to attack its research setup. They escaped virtual machines, got out through logging and metrics services, and signalled each other through processor cache timing. Research setup, not customer use.
- Google's Agent Compute Engine gives each agent its own hardware-isolated virtual machine and adds service credentials to requests outside it, so the agent uses a key it never holds. Preview "in the coming months"; not tested by us.
- Link balance lets an agent like Instinct spend from a funded USDC balance under a per-purchase limit, with approval above it. The limit is per purchase, not per week, and you are responsible for what the agent buys. US only.
The common point: limit what an agent can reach before anything goes wrong. Network, keys and money.
Last week we asked what happens when an agent switches off its monitoring. This week: how much it can break before anyone looks.
On Teneo, each agent authenticates with an Ethereum key and an NFT-backed identity, and minting is gasless, so the key your agent holds does not have to hold money. Callers pay per command through x402, builders can set a rate limit, and changing an agent's commands sends it back to private review.
The SDK does not document sandboxing, egress controls or spending caps for paying wallets. So run the agent with only the connections it needs, and pay for commands from a wallet with a small balance.
A useful test this week: list every address, key and account your agent can reach, then try to reach one that is not on the list.
Read this week's round-up here:
teneo-protocol.ai/blog/what-…
$LWT TGE IS COMPLETE. 💚
A major milestone for LF Wallet is officially behind us.
The token is live, the next chapter has started, and now the focus moves to growth, listings, utility, creators, and the wider LF Wallet ecosystem.
Explorer: bscscan.com/token/0x0c9Eaa61…
For More Visit Website: lfwallet.app
Zenki shimitora retweeted
If you train or fine-tune models on public web data, your list of open sources is getting shorter. We measured it.
On 25 September and 27 October we read robots.txt from the 300 most-visited domains, with the same list, the same script and the same connection both times.
151 of them publish a robots.txt. 34 now fully block at least one of the main AI training crawlers, against 33 a month ago. Nine block all seven we tested, including The New York Times, the BBC and Nature.
Sites treat training and search differently. 16 block OpenAI's GPTBot but leave its search crawler, OAI-SearchBot, open. OpenAI's own documentation says a site can do exactly that.
In one month, facebook.com moved from a partial rule to a full block. CNN went the other way.
A different connection changes where a request comes from. It does not change what a site has agreed to.
Our new post sets out five checks to run before a page goes into a training set, with the full survey data:
teneo-protocol.ai/blog/ai-tr…
Free seven-day pilots are open to teams building AI search, RAG or crypto data products. If you run a training pipeline, say so on the form: teneo-protocol.ai/partner





















