Subnets / SN49
Nepher Robotics SN49
Nepher Robotics (subnet 49) is a Bittensor subnet held by 1,299 unique coldkeys. Its liquidity pool holds 4.0k τ, with the alpha token trading at 0.0054 τ. Roughly 24% of tracked holders are in profit — most bought in above today's price. Seller exhaustion is elevated: 88% of recent sellers have emptied their wallets, thinning the supply overhang. Full insider flow, whale tracking and the complete proprietary factor set for Nepher Robotics are available to SubnetStats subscribers.
ALPHA PRICE
0.0054 τ
IN TAO
HOLDERS
1,299
UNIQUE COLDKEYS
POOL DEPTH
4.0k τ
TAO IN POOL
7D MOMENTUM
-3.7%
ALPHA vs TAO
Project activity
Go2 Tournament Phase 2 is now in the submission stage! 🐕
The key difference from Phase 1? Rough terrain.
Phase 1 used a perfectly flat surface. While the winners performed well, their policies struggled with uneven terrain.
The current Phase 2 leader has overcome this limitati
Robots need millions of demonstrations. Collecting them by hand doesn't scale.
On Nepher tournament platform, miners compete to train the best robot policies, and every winning submission ships with full code. We plan to turn those winners into a synthetic data engine. 🤖
Here's
One year of SN49! 🎉🤖
Robotics doesn’t advance through demos alone. It advances through real challenges, measurable progress, and the ability to bring intelligence into the physical world.
That’s what we’ve been building at Nepher over the past year.
A year of building, testing
The Franka Tabletop RL Challenge, Phase 1, is now live on SN49. 🚀
Miners build the brain that teaches a Franka arm to grasp, carry, place, stack and pack objects on a cluttered table, creating high-quality practice data for next-gen AI models.
The robot can see the objects arou
27 people trained policies for one job: get a Unitree Go2 through a maze it has never seen, using LiDAR only.
The winner scored 0.9272 on held-out mazes.
Phase 1 had a smooth, clean floor. Phase 2 is live now on rugged, uneven terrain.
#Robotics @opentensor @bittensor @NVIDIAR
Watch the winning run of Unitree Go2 LiDAR Maze Phase 1 🏆
No cameras. No map. Just a 360° LiDAR scan, scored on mazes the policy has never seen.
76 submissions · 27 participants
Winning score: 0.9272
Trained in Isaac Lab, competed on Bittensor SN49 🤖
https://t.co/TtGyVtcIV7 h
Highlights from GTC Berlin 2026 🚀
This time we were there as attendees. Next GTC, we won’t just be watching.
Proud to be building the next generation of robotics AI at Nepher.
#NVIDIAGTC #PhysicalAI #Robotics https://t.co/sfMjfRvyJ6
Cool
The future of robotics is being built now. 🤖
A moment from NVIDIA GTC Berlin with Jensen Huang — and a future we at Nepher Robotics are working to make real.
We’ll be at @NVIDIAGTC Berlin this week (Oct 20–22).
If you’re around and want to connect on partnerships, benchmarks, or talent - let’s meet up.
https://t.co/8c706wVG0y
Humanoid Run Jump Phase 3 is officially in the books, with a winning score of 0.8245.
Across three phases, miners have continued to push the same Unitree G1 humanoid to perform better on the same task:
• Phase 1: 0.6750
• Phase 2: 0.7735
• Phase 3: 0.8245
Every phase used the
Excited to join the European robotics community at @NVIDIAGTC Berlin next week (Oct 20–22)!
We're Nepher Robotics — the platform that turns NVIDIA Omniverse + Isaac Lab into production-ready robot policies, from simulation to real hardware in days, not months.
Open tournaments.
https://t.co/E1LL92lERh
🚀 Training & evaluating VLA (Vision-Language-Action) and WAM (World Action Models) just got a major upgrade with @nvidiaomniverse’s Isaac Sim + Isaac Lab.
While MuJoCo remains solid for contact-rich physics and quick academic baselines, Isaac Sim delivers clear edges for modern
A new robot just joined SN49: the Unitree Go2.
The Unitree Go2 LiDAR Maze Navigation tournament is now live. Miners train a policy that guides the Go2 through enclosed mazes using nothing but a 360° LiDAR scan. There are no cameras and no map, so the robot has to read the walls
In July, a circle that looked perfect in simulation fell apart the moment it ran on our real SO-ARM101.
Today that same arm writes NEPHER and traces our logo, first in simulation and then on real hardware, following the same path stroke for stroke.
It's a big step up from the $
Humanoid Run Jump Phase 3 came down to a margin of 0.0018.
That's how close first and second place finished in the first tournament under our new 70/20/10 reward split. Under winner-takes-all, second place would have walked away with nothing. This time, the top three all get pai
Last month, Nepher Verified became a selectable certification for robot manufacturers, listed alongside CE, UL, ISO, TÜV, FCC and FDA.
Our CEO and co-founder, Mahdi Eghbali (@eghbali_mahdii), PhD, explains what that means for robotics.
When a robot maker says their hardware or
Thanks for the solid conversation @ShizzyUnchained 🔥
Really appreciate you covering Nepher Robotics (SN49) and breaking down how miners train real robotic policies on Bittensor. Physical AI is heating up.
Glad we got to sit down and talk through it.
Watch the full breakdown her
We’re joining @ShizzyUnchained live today at 1 PM ET.
@altinloshi6 and @eghbali_mahdii will break down what we’re building on SN49: Sim2Real robotics, open policy training on Bittensor, and taking trained policies from NVIDIA Isaac Sim into real-world hardware.
If you want to u
Humanoid Run Jump Phase 2 is officially in the books.
97 miners sent in 316 submissions, all training the same Unitree G1 to run, jump and stay stable. The winning policy scored 0.7735, hit a 95.3% success rate across 192 evaluation episodes with a mean completion time of 21.7 s
We're changing how Nepher tournaments pay miners.
Until now, most tournaments were winner-takes-all. Starting with Humanoid Run Jump Phase 3, every tournament on SN49 rewards the top three:
• 1st place: 70%
• 2nd place: 20%
• 3rd place: 10%
This split is here to stay. Strong w
𝗧𝗵𝗲 𝗡𝗲𝗽𝗵𝗲𝗿 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝘄𝗵𝗶𝘁𝗲 𝗽𝗮𝗽𝗲𝗿 𝗶𝘀 𝗹𝗶𝘃𝗲.
AI has mastered language, code and images, but it still can't reliably control a robot in the physical world. That gap is where Physical AI lives, and it's the problem Nepher was built to solve.
The paper lays out how we turn NVIDIA's si
About 97 miners competed to train the best policy for a robot navigating with no camera or map, using only a 360° LiDAR sensor.
Using Bittensor’s distributed network, miners submitted policies tested on unseen environments, resulting in:
> 337 submissions.
> 90 hidden mazes.
T
We’re pleased to announce that Nepher Verified is now officially available as a selectable certification type on a major robotics product-listing platform.
It now appears alongside options such as CE, UL, ISO, TÜV, FCC, and FDA.
Manufacturers can now attach Nepher Verified to t
SELLERS DRAINED
88%
28D SELLERS EMPTIED OUT
CAPITULATION
+0.37
BOUNCE COMPOSITE (z)
HEAT 7D
0.45×
VOLUME ÷ POOL DEPTH
HOLDERS IN PROFIT
24%
TRACKED WALLETS · ENTRY BELOW PRICE
WHAT'S CARRYING THE PRICE · 30D—emission rank #40 · below the bar (rank 32)
30D RETURN
-36.8%
ALPHA vs TAO
WITHOUT CHAIN BUYS
-38.5%
SAME 30 DAYS, PROTOCOL BID REMOVED
CHAIN SHARE OF BUYING
100%
CHAIN BUYS vs TRADERS' NET
CHAIN BUYS / DAY
0 τ
PROTOCOL BUYING ITS ALPHA
See who's buying and selling Nepher Robotics — every trade classified miner / validator / owner / outsider, plus holder cost basis and the full 23-factor screener.
OPEN THE INSIDER TAPE →