WormGPT
Open in Telegram
📈 Analytical overview of Telegram channel WormGPT
Channel WormGPT (@wormgpt) in the English language segment is an active participant. Currently, the community unites 16 626 subscribers, ranking 7 619 in the Technologies & Applications category and 1 020 in the International region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 16 626 subscribers.
According to the latest data from 26 August, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by 385 over the last 30 days and by -3 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 15.11%. Within the first 24 hours after publication, content typically collects 2.97% reactions from the total number of subscribers.
- Post reach: On average, each post receives 2 511 views. Within the first day, a publication typically gains 494 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 3.
- Thematic interests: Content is focused on key topics such as wormgpt, api, load, opencode, alternative.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“freedom”
Thanks to the high frequency of updates (latest data received on 27 August, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Technologies & Applications category.
16 626
Subscribers
-324 hours
+567 days
+38530 days
Posts Archive
16 626
Repost from cyberneurova
The Cyberneurova CLI works perfectly well and is better than our desktop app, but this will change as we are focusing on making the desktop app much better. Also, the Android mobile app is taking longer than expected because we are working on cool features like full agentic support and remote control. The building process has been slow since the new architecture requires proper building.
https://cyberneurova.ai
16 626
Repost from cyberneurova
Qwen 3.8 Max is now live.
Also, GLM 5.2 has been bumped to 250k ctx during overload. The GLM model will be assisted by Qwen 3.8 27B for simple tasks and switch to long, complex tasks.
https://cyberneurova.ai
16 626
Repost from cyberneurova
Api access has been fixed. We also had to scrap free API access, as we noticed that a lot of users were overloading it, and we had to end free API access. We are still monitoring the fixed issues. Additionally, we are switching to using the DeepSeek harness for our CLI tool, as the harness is better at running a lot of agentic workflows, so we are switching to it. Lastly, we will be introducing bot mode to our platform. This will allow users to interact with different agents in a chat flow manner, group chat, etc.
https://cyberneurova.ai
16 626
Repost from cyberneurova
+1
Get the latest IOS app bug fixes and features added
https://apps.apple.com/ke/app/cyberneurova/id6776460478
16 626
Repost from cyberneurova
You can run the quantized version of Qwen3.8; the model size is 10GB, and it outperforms most models in day-to-day tasks as well as advanced tasks.
https://x.com/cyberneurova/status/2088713510469386518?s=46
16 626
Repost from cyberneurova
Cyberneurova cli now supports Qwen 3.8
npm install -g cyberneurova-cli16 626
Repost from cyberneurova
Qwen 3.8 2t model is now available for paid users starting from premium - pro max ,
I’m working on the 27 b model that will serve from free users to also pro max
https://cyberneurova.ai
16 626
Repost from cyberneurova
cyberneurova-Qwen3.8-27B — GGUF
An uncensored, neutral 27B assistant. It answers directly, with no disclaimers or caveats — the tone is entirely yours, set by your own system prompt.
- 262K context, reasoning, tool-calling, multilingual
- Sees images (just add mmproj-F16.gguf)
- 92% pass@1 on an executable coding benchmark
- Runs locally on llama.cpp, Ollama, LM Studio, or Jan
from q2_k 10gb in size to q8 20gb
Pick a quant — Q4_K_M (~17 GB) is the sweet spot, up to Q8_0 for max quality:
https://huggingface.co/cyberneurova/cyberneurova-Qwen3.8-27B-GGUF
16 626
Repost from cyberneurova
+1
You can refer your friends to earn tokens
https://cyberneurova.ai/referrals
16 626
Repost from cyberneurova
For credibility, and as we wait for the Android app to be approved, we have open-sourced our mobile application. This comes with the introduction of agents running directly on your mobile phone without relying on any third-party servers. Check the repo and feel free to contribute to make the app better.
https://github.com/CyberNeurova/cyberneurova-mobile-oss
16 626
Repost from cyberneurova
For the mean time IOS app has been available on App Store for a week now
https://apps.apple.com/ke/app/cyberneurova/id6776460478
16 626
Repost from cyberneurova
The Android app restructure is complete; the agentic work is fully done on your Android device. The app has been published and is waiting for review 🍌
https://cyberneurova.ai
