Levanto Labs (@levantolabs) header
Levanto Labs (@levantolabs) profile picture

We build Sage, the first decision model, and pioneered multimodality, grounding and reasoning. Benchmark-leading. Ready to deploy in startups and enterprise.

Planet Earth
Joined October 2025
Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)Photo by Levanto Labs (@levantolabs)
Software can now understand human language and act on it, in real time. Introducing Sage2 - Extract: natural language in, structured data out. 166x cheaper than Opus 5.5, beats @Cloudflare's Clairic - Decide: the first decision model with streaming. 3x faster, because it reads the context as it grows. Sage2 is a new primitive for developers. Get 20M tokens free 👇 Also available on @near_ai and, for agents, via @mpp with @Stripe cards and @Tempo stables.
143
131
65
1,062
680,400
Levanto Labs retweeted
Week 1 of Normies Arena is in the books. 748 Normies walked into a world played only by AI agents. Nobody steered them. Every move came from Sage. In 5 days: • 3.96M live decisions by Sage @levantolabs • 355k duels between Normies • 224k deaths, each followed by a new life • 134k monsters slain • 356 monuments raised • 10,000 viewers on X across 4 live streams Seus, a level 150 Zombie, finished #1 with 1.67M PX, the first Normie ever past a million. And level doesn't decide everything: 7 level-1 Normies made the top 75. The prize: 200 #PIXEL (about $4,170) sponsored by the Normies team, shared by the top 75. #1–50 get 3 #PIXEL each, #51–75 get 2. Prizes land on the Normie's own balance once results are approved. Round 1 results are approved and paid on chain. 200 #PIXEL to the top 75 Normies, in one transaction: etherscan.io/tx/0x3ec0bd48c0… Full results, all 748 Normies ranked by PX (results hash 0x90cc955dfadfd5acbfe3f31945d6c4e56ccc2296ea5849fb965f39c819e23352): arena.normies.art/api/world/… Winners: the prize is on your Normie's balance. Withdraw any time from the Enter page, or let it pay for future weeks. Full recap of first game: arena.normies.art/world/stat… Round 2 starts Monday 20:00 CET. It's free, and 895 Normies are already in. The Normies play. Humans watch. arena.normies.art
19
25
11
76
4,147
Levanto Labs retweeted
I have started testing @levantolabs SAGE2 decision model and so far been pretty impressed with the outcome layering My first intent here is to use their API key within my claude builder to debug, re-test and potentially improve algorithms that are currently embedded in Blocktronics Ultimate plan to to create the best-in-industry algorithms around smart-money, signals and predictive analyses, with no leaks and gaps
2
1
11
700
Levanto Labs retweeted
Normies Arena Gameplay Guide with all details. Read here, see the game engine, learn more about how it works. web3 gaming, this time agents are playing fully autonomously.
10
27
13
81
4,296
Levanto Labs retweeted
⚔️ NORMIES ARENA IS LIVE ⚔️ xitter.cf/i/broadcasts/2QnYXMJWW…
2
17
2
45
1,622
We are launching Examples to give you (and your agents) new ideas for how to blend Sage2's primitives. Explore by use case and test your skills on levanto.ai/examples.
3
4
2
16
976
Levanto Labs retweeted
Better games need humans.🫂 Players find the bugs. Sage scores every report in seconds. Your AI fixes them. Players verify the fix and get paid in USDG. Built on Robinhood Chain. Waitlist open 👇 buggypay.com/?x=buggypay#joi…
2
6
1
12
469
Levanto Labs retweeted
gm! Normies Arena Week 1 registration opens Saturday, November 14th! What should you know about Normies Arena: It's a fully autonomous agent game, powered by @levantolabs Sage decision making model. live streaming 24/7. Follow our twitch account: twitch.tv/normiesart Only Normies NFTs can enter the Arena as long as they are registered as an agent. You can do it in this page: normies.art/lab/agentic On Saturday, you should go to Arena website (will be posted officially) and get your Normie(s) into the Arena. It's open until Monday and entering Arena is only possible on Saturday-Sunday. When the final list of players are there, system will select 200 Normies to start the game. If there are more than 200 Normies in the list, remaining agents will enter the Arena automatically whenever playing agents die. If you agent dies in the Arena, it goes to cooldown for 8 hours. YOU NEVER LOSE YOUR NFT. Your agent dies inside the game and waits for 8 hours to re-enter. Game finalizes on every Saturday, highest XP earning agents earn #PIXEL from the reward pool. First 2 week will be free to enter for all holders after 2 weeks, it's one #PIXEL per Normie to play the game for one week. Skin purchase will be open in the first week. While you decide which Normies you want to enter the Arena, you can create a skin for them. Normally all Normies have same visual, appearance in the game (types gives player a different look) You can give your Normie a custom skin that is easy to recognize. For the fist two weeks, since there is no entry fee; i will put 200 #PIXEL to prize pool for each week from my own wallet. Only way to play the game and win prizes is to hold at least 1 Normies NFT.
33
38
13
152
4,951
The aeon team has millions of github stars on their security contributions. Glad Sage2 can help with the next million!
Replying to @aeonframework
@aaronjmars on how Sage 2 by @levantolabs helps Aeon route bug bounties autonomously, flipping as the policy streams in. xitter.cf/aaronjmars/status/2117…
1
1
7
505
Levanto Labs retweeted
How do you make use of the 20m free tokens you got from creating an account on @levantolabs? We've added this to the onboarding flow so it's a little easier to see. All newly created accounts get assigned a ''Free'' tier which comes with 20m input tokens per month.
3
2
10
583
Can Sage2 extract all the food mentioned in Chapter 1 of the Hobbit? Watch @bigironchris demo a live extraction. This is a tutorial for understanding how to create fields and values for accurate Extractions on documents. What would you like us to test in the next Sage2 demo?
Software can now understand human language and act on it, in real time. Introducing Sage2 - Extract: natural language in, structured data out. 166x cheaper than Opus 5.5, beats @Cloudflare's Clairic - Decide: the first decision model with streaming. 3x faster, because it reads the context as it grows. Sage2 is a new primitive for developers. Get 20M tokens free 👇 Also available on @near_ai and, for agents, via @mpp with @Stripe cards and @Tempo stables.
5
2
2
18
1,469
Levanto Labs retweeted
Software can now understand human language and act on it, in real time. Introducing Sage2 - Extract: natural language in, structured data out. 166x cheaper than Opus 5.5, beats @Cloudflare's Clairic - Decide: the first decision model with streaming. 3x faster, because it reads the context as it grows. Sage2 is a new primitive for developers. Get 20M tokens free 👇 Also available on @near_ai and, for agents, via @mpp with @Stripe cards and @Tempo stables.
143
131
65
1,062
680,400
Our thesis is to expand runtime models deeper into software until all if statements are replaced.
1
1
30
3,583
Sign-ups in the next 24 hours get 20M free tokens: levanto.ai/model Want to give it a try? This is our playground: playground.levanto.ai Learn how to set up MPP with Sage2 for your agents here: levanto.ai/mpp
17
3
87
13,208
Extraction models are new. We couldn’t find a benchmark, so we made one. On our Extract Bench, Sage2 was the most accurate. Sage2 ranked first both in accuracy (77.8) and identifying non-answers (72.2) beating @cloudflare’s Clairic scored (75.3, 59). It’s open-source, we invite improvements: github.com/levantolabs/extra…
3
2
54
6,955
Extraction models are new. We couldn’t find a benchmark, so we made one. On our Extraction model benchmark, Sage2 was the most accurate. Sage2 ranked first both in accuracy (77.8) and identifying non-answers (72.2) beating @cloudflare’s Clairic scored (75.3, 59) It’s open-source, we invite improvements github.com/levantolabs/extra…
21
Levanto Labs retweeted
Built a recruiter email screening tool using Sage by @levantolabs Scams are becoming more nuanced due to AI, and I ran into a few ones where I really had to keep my head right to spot the signs. I often had to check directly background on LinkedIn taking up more time than its worth. I created a nice simple setup: 1. Gmail connected to a Codex session to filter emails 2. Sage Codex Plugin - custom built, no plaintext API delivered to Codex 3. Sage decides if email is A) Scam B) Needs review C) High value 4. Codex then delivers me results in chat, and drafts email when more info is needed, then sends it. Training -> Two online databases for scam and valid recruiter emails (About 2k total used), LinkedIn profile data Codex fine-tuned Sage, created a prompt and question that validated setup. Simple setup, saves about 30-60 minutes per week for more important things to do. Link to prototype repo with installation guide: github.com/Barnadrot/sage-le…
2
1
3
5
861
Levanto Labs retweeted
Autopolis is LIVE. 🏙️ Powered by Sage (@levantolabs) 👉growblocks.xyz/autopolis
2
3
8
655
Sage is a decision model by @levantolabs hosted confidentially by @near_ai I expect more and more model builders to choose to host confidentially to ensure their customers' data is protected.
Sage is now live on NEAR AI's confidential infrastucture. Intel TDX and NVIDIA confidential computing, plus cryptographic attestation, give teams a verifiable boundary for classifying and deciding on sensitive enterprise data.
28
22
229
17,426
Levanto Labs retweeted
Decision models are moving into enterprise workflows. That company data must stay private. Now it can. Introducing the first private decision model, inside a TEE. Sage is now live on @near_ai’s confidential infrastructure. Private decisions, at machine speed.
6
12
7
61
23,150