AI & ML interests

Asynchronous Telemedicine AI Pipelines, Ambient Emotion IoT AI, Open Source for Smart Communities, AGI and ML Pipelines, Behavior Cognitive and Memory AI, Clinical Medical and Nursing AI, Genomics AI, GAN Gaming GAIL AR VR XR and Simulation AI, Graph Ontology KR KE AI, Languages and NLP AI, Quantum Compute GPU TPU NPU AI, Vision Image Document and Audio/Video AI

NymboΒ 
posted an update 15 days ago
view post
Post
1582
Two new tools added to the Nymbo/Tools MCP server, File_System and Shell_Exec. You can theoretically do basically anything with these two tools, and it should enable support for many Claude Skills.

GPT-5-Codex proves that for many cases, shell commands really are all you need, and Claude Skills seem to lean into this. The thing is, nothing about the design of Claude Skills actually restricts them to proprietary models!

# File_System

There's a new directory inside the repo called Filesystem, that's the agent's "root". It can perform the following actions : list, read, write, append, mkdir, move, copy, delete, info, help. It's able to keep this all within the scope of one tool call by making the Action field required and all other fields optional. Using a filesystem shouldn't require 15 different tools.

Files created in the public HF space live in the space's running container, and gets cleared when the space is restarted. When running the server locally, files are actually stored on disk.

# Shell_Exec

What good is a filesystem if you can't execute commands in that filesystem? This tool automatically detects if the server is running on Windows or Linux, and suggests using the appropriate shell (PowerShell/Bash). Both of these new tools require that the agent uses relative paths, rather than absolute paths. I could be convinced to back pedal on this.

# Closing Thoughts

The File_System and Shell_Exec tools aren't super polished yet, I'll continue to improve the agent's instructions and UX of using the new tools. Most of my testing was done with gpt-oss-20b and if it messes up, it gets the gist after one failed tool call. It should work perfectly fine for the GPU poor.
  • 1 reply
Β·
NymboΒ 
posted an update 20 days ago
view post
Post
1755
I've made some improvements to my custom Deep_Research tool in the Nymbo/Tools MCP server. I've added a second LLM process and it still takes less than 1 minute to complete!

The original version of my Deep_Research tool would basically dump up to 50 fetched webpages onto the Researcher model (Qwen3-235B), with only a little bit of context shown from each page.

# New "Filterer" Process

The new process includes another LLM call before the researcher process. The Filterer (also Qwen3-235B) gets the query summary and the original 50 pages with low context, and decides which pages are most relevant to the research topic. The Filterer then outputs the URLs to the relevant pages, which are then re-fetched (with more context) and sent to the Researcher.

# Researcher Context

The Researcher now gets only the relevant webpages, then begins writing the report. When testing with 50 initial results, the researcher would often end up with 10-20 results of relevant context.

It still takes less than a minute to accomplish everything, thanks entirely to Cerebras inference. It now takes about 35-45 seconds to complete once the tool is run.

It's also worth noting that both the Filterer and Researcher now are provided the current time/date before they see the content, reducing hallucinations caused by knowledge cutoffs.
NymboΒ 
posted an update 30 days ago
view post
Post
623
I have a few Sora-2 invites - 15509N
  • 1 reply
Β·
NymboΒ 
posted an update about 2 months ago
view post
Post
1054
There's now a custom Deep_Research tool in my Nymbo/Tools MCP server! TL;DR: The agent using the tools writes a summary of your requests and up to five DuckDuckGo searches (up to 50 results). Each of the webpages found in the searches are then fetched and given to our researcher (Qwen3-235B-A22B-Thinking-2507). The researcher sees the summary, searched queries, and fetched links, then writes a thorough research report. The agent using the tool provides the user with a summary of the report and a link to download research_report.txt. The researcher's instructions are similar to some leaked Perplexity sys prompts.

# Deep_Research Tool

It accomplishes everything in under a minute so it doesn't hit MCP's 60 second timeout, mostly thanks to Cerebras. The only thing required to make this work is a HF_READ_TOKEN for inference.

The Deep_Research tool could certainly be improved. It still needs some sort of mechanism for sorting URLs based on importance (I've got some ideas but I don't want it to be the responsibility of the agent using the tool). I'll probably add a second researcher to filter out the bad sources before inferencing the big researcher. I'm hellbent on keeping this all within the scope of one tool call.

# More Fetch/Web Search Improvements

The Search_DuckDuckGo tool has been further enhanced. It now allows the agent to browse through all pages of results. The results also now include published date (if detected). It also now supports every DDG search types! Default DDG search is called text, but it can also now search by news, images, videos, and books.

The Fetch_Webpage tool now specifies how much of the page has been truncated, and cursor index, allowing it to pickup where it left off without re-consuming tokens. The model can now also choose to strip CSS selectors to remove excess noise, and there's a new URL Scraper mode that only returns URLs found on the full page.

More to come soon ~
NymboΒ 
posted an update about 2 months ago
view post
Post
1020
I have a few updates to my MCP server I wanna share: New Memory tool, improvements to web search & speech generation.

# Memory_Manager Tool

We now have a Memory_Manager tool. Ask ChatGPT to write all its memories verbatim, then tell gpt-oss-20b to save each one using the tool, then take them anywhere! It stores memories in a memories.json file in the repo, no external database required.

The Memory_Manager tool is currently hidden from the HF space because it's intended for local use. It's enabled by providing a HF_READ_TOKEN in the env secrets, although it doesn't actually use the key for anything. There's probably a cleaner way of ensuring memory is only used locally, I'll come back to this.

# Fetch & Websearch

The Fetch_Webpage tool has been simplified a lot. It now converts the page to Markdown and returns the page with three length settings (Brief, Standard, Full). This is a lot more reliable than the old custom extraction method.

The Search_DuckDuckGo tool has a few small improvements. The input is easier for small models to get right, and the output is more readable.

# Speech Generation

I've added the remaining voices for Kokoro-82M, it now supports all 54 voices with all accents/languages.

I also removed the 30 second cap by making sure it computes all chunks in sequence, not just the first. I've tested it on outputs that are ~10 minutes long. Do note that when used as an MCP server, the tool will timeout after 1 minute, nothing I can do about that for right now.

# Other Thoughts

Lots of MCP use cases involve manipulating media (image editing, ASR, etc.). I've avoided adding tools like this so far for two reasons:

1. Most of these solutions would require assigning it a ZeroGPU slot.
2. The current process of uploading files like images to a Gradio space is still a bit rough. It's doable but requires additional tools.

Both of these points make it a bit painful for local usage. I'm open to suggestions for other tools that rely on text.
NymboΒ 
posted an update 2 months ago
view post
Post
1008
I built a general use MCP space ~ Fetch webpages, DuckDuckGo search, Python code execution, Kokoro TTS, Image Gen, Video Gen.

# Tools

1. Fetch webpage
2. Web search via DuckDuckGo (very concise, low excess context)
3. Python code executor
4. Kokoro-82M speech generation
5. Image Generation (use any model from HF Inference Providers)
6. Video Generation (use any model from HF Inference Providers)

The first four tools can be used without any API keys whatsoever. DDG search is free and the code execution and speech gen is done on CPU. Having a HF_READ_TOKEN in the env variables will show all tools. If there isn't a key present, The Image/Video Gen tools are hidden.

Nymbo/Tools
  • 1 reply
Β·
NymboΒ 
posted an update 3 months ago
view post
Post
1030
Anyone using Jan-v1-4B for local MCP-based web search, I highly recommend you try out Intelligent-Internet/II-Search-4B

Very impressed with this lil guy and it deserves more downloads. It's based on the original version of Qwen3-4B but find that it questions reality way less often. Jan-v1 seems to think that everything it sees is synthetic data and constantly gaslights me
NymboΒ 
posted an update 4 months ago
view post
Post
2866
Anyone know how to reset Claude web's MCP config? I connected mine when the HF MCP first released with just the default example spaces added. I added lots of other MCP spaces but Claude.ai doesn't update the available tools... "Disconnecting" the HF integration does nothing, deleting it and adding it again does nothing.

Refreshing tools works fine in VS Code because I can manually restart it in mcp.json, but claude.ai has no such option. Anyone got any ideas?
Β·
NymboΒ 
posted an update 6 months ago
view post
Post
4112
Haven't seen this posted anywhere - Llama-3.3-8B-Instruct is available on the new Llama API. Is this a new model or did someone mislabel Llama-3.1-8B?
  • 1 reply
Β·
NymboΒ 
posted an update 6 months ago
view post
Post
2784
PSA for anyone using Nymbo/Nymbo_Theme or Nymbo/Nymbo_Theme_5 in a Gradio space ~

Both of these themes have been updated to fix some of the long-standing inconsistencies ever since the transition to Gradio v5. Textboxes are no longer bright green and in-line code is readable now! Both themes are now visually identical across versions.

If your space is already using one of these themes, you just need to restart your space to get the latest version. No code changes needed.
awacke1Β 
posted an update 7 months ago
view post
Post
2422
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.

https://huggingface.co/spaces/awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? β˜•
2. Camera Snap πŸ“·: Capture life’s chaosβ€”your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR πŸ”: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt β€œneon superhero me”
5. PDF πŸ“„: Double-page OCR Single-page sniping

Build Titans 🌱: Train tiny AI models. πŸ’ͺCharactersπŸ§‘β€πŸŽ¨: Craft quirky heroes.
πŸŽ₯

awacke1Β 
posted an update 8 months ago
awacke1Β 
posted an update 8 months ago
view post
Post
2507
πŸš€ Blast into the future with ZaxxonGalaxian – a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies. awacke1/ZaxxoGalaxian
awacke1Β 
posted an update 10 months ago
view post
Post
3223
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.

1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]


To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.

1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
awacke1Β 
posted an update 10 months ago
awacke1Β 
posted an update 12 months ago
view post
Post
1032
πŸ•ŠοΈHopeπŸ•ŠοΈ and βš–οΈJusticeβš–οΈ AI
🚲 Stolen bike in Denver FOUND - Sometimes hope & justice DO prevail.

🎬 So I Created an AI+Art+Music tribute:
-🧠 AI App that Evaluates GPT-4o vs Claude:
awacke1/RescuerOfStolenBikes
https://x.com/Aaron_Wacker/status/1857640877986033980?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1857640877986033980%7Ctwgr%5E203a5022b0eb4c41ee8c1dd9f158330216ac5be1%7Ctwcon%5Es1_c10&ref_url=https%3A%2F%2Fpublish.twitter.com%2F%3Furl%3Dhttps%3A%2F%2Ftwitter.com%2FAaron_Wacker%2Fstatus%2F1857640877986033980

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">QT your πŸ•ŠοΈHopeπŸ•ŠοΈ and βš–οΈJusticeβš–οΈ art🎨<br><br>🚲 Stolen bike in Denver FOUND! <br> - Sometimes hope &amp; justice DO prevail! <br><br>🎬 Created an AI+Art+Music tribute: <br> -🧠 AI App that Evaluates GPT-4o vs Claude: <a href="https://t.co/odrYdaeizZ">https://t.co/odrYdaeizZ</a><br> <a href="https://twitter.com/hashtag/GPT?src=hash&amp;ref_src=twsrc%5Etfw">#GPT</a> <a href="https://twitter.com/hashtag/Claude?src=hash&amp;ref_src=twsrc%5Etfw">#Claude</a> <a href="https://twitter.com/hashtag/Huggingface?src=hash&amp;ref_src=twsrc%5Etfw">#Huggingface</a> <a href="https://twitter.com/OpenAI?ref_src=twsrc%5Etfw">@OpenAI</a> <a href="https://twitter.com/AnthropicAI?ref_src=twsrc%5Etfw">@AnthropicAI</a> <a href="https://t.co/Q9wGNzLm5C">pic.twitter.com/Q9wGNzLm5C</a></p>&mdash; Aaron Wacker (@Aaron_Wacker) <a href="https://twitter.com/Aaron_Wacker/status/1857640877986033980?ref_src=twsrc%5Etfw">November 16, 2024</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>


#GPT #Claude #Huggingface
@OpenAI
@AnthropicAI
awacke1Β 
posted an update about 1 year ago
view post
Post
1985
Since 2022 I have been trying to understand how to support advancement of the two best python patterns for AI development which are:
1. Streamlit
2. Gradio

The reason I chose them in this order was the fact that the streamlit library had the timing drop on gradio by being available with near perfection about a year or two before training data tap of GPT.

Nowadays its important that if you want current code to be right on generation it requires understanding of consistency in code method names so no manual intervention is required with each try.

With GPT and Claude being my top two for best AI pair programming models, I gravitate towards streamlit since aside from common repeat errors on cache and experimental functions circa 2022 were not solidified.
Its consistency therefore lacks human correction needs. Old dataset error situations are minimal.

Now, I seek to make it consistent on gradio side. Why? Gradio lapped streamlit for blocks paradigm and API for free which are I feel are amazing features which change software engineering forever.

For a few months I thought BigCode would become the new best model due to its training corpus datasets, yet I never felt it got to market as the next best AI coder model.

I am curious on Gradio's future and how. If the two main models (GPT and Claude) pick up the last few years, I could then code with AI without manual intervention. As it stands today Gradio is better if you could get the best coding models to not repeatedly confuse old syntax as current syntax yet we do live in an imperfect world!

Is anyone using an AI pair programming model that rocks with Gradio's latest syntax? I would like to code with a model that knows how to not miss the advancements and syntax changes that gradio has had in the past few years. Trying grok2 as well.

My IDE coding love is HF. Its hands down faster (100x) than other cloud paradigms. Any tips on models best for gradio coding I can use?

--Aaron
Β·
awacke1Β 
posted an update about 1 year ago
view post
Post
727
Today I was able to solve a very difficult coding session with GPT-4o which ended up solving integrations on a very large scale. So I decided to look a bit more into how its reasoners work. Below is a fun markdown emoji outline about what I learned today and what I'm pursuing.

Hope you enjoy! Cheers, Aaron.

Also here are my favorite last 4 spaces I am working on:
1. GPT4O: awacke1/GPT-4o-omni-text-audio-image-video
2. Claude:
awacke1/AnthropicClaude3.5Sonnet-ACW
3. MSGraph M365: awacke1/MSGraphAPI
4. Azure Cosmos DB: Now with Research AI! awacke1/AzureCosmosDBUI

# πŸš€ OpenAI's O1 Models: A Quantum Leap in AI

## 1. πŸ€” From 🦜 to 🧠: O1's Evolution

- **Thinking AI**: O1 ponders before replying; GPT models just predict. πŸ’‘

## 2. πŸ“š AI Memory: πŸ’Ύ + 🧩 = 🧠

- **Embeddings & Tokens**: Words ➑️ vectors, building knowledge. πŸ“–

## 3. πŸ” Swift Knowledge Retrieval

- **Vector Search & Indexing**: O1 finds info fast, citing reliable sources. πŸ”ŽπŸ“–

## 4. 🌳 Logic Trees with Mermaid Models

- **Flowchart Reasoning**: O1 structures thoughts like diagrams. 🎨🌐

## 5. πŸ’» Coding Mastery

- **Multilingual & Current**: Speaks many code languages, always up-to-date. πŸ’»πŸ”„

## 6. πŸ† Breaking Records

- **92.3% MMLU Score**: O1 outperforms humans, setting new AI standards. πŸ…

## 7. πŸ’‘ Versatile Applications

- **Ultimate Assistant**: From fixing code to advancing research. πŸ› οΈπŸ”¬

## 8. 🏁 Racing Toward AGI

- **OpenAI Leads**: O1 brings us closer to true AI intelligence. πŸš€

## 9. πŸ€– O1's Reasoning Pillars

- **🧠 Chain of Thought**: Step-by-step logic.
- **🎲 MCTS**: Simulates options, picks best path.
- **πŸ” Reflection**: Self-improves autonomously.
- **πŸ‹οΈβ€β™‚οΈ Reinforcement Learning**: Gets smarter over time.

---

*Stay curious, keep coding!* πŸš€
awacke1Β 
posted an update about 1 year ago
view post
Post
605
I have finally completed a working full Azure and Microsoft MS Graph API implementation which can use all the interesting MS AI features in M365 products to manage CRUD patterns for the graph features across products.

This app shows initial implementation of security, authentication, scopes, and access to Outlook, Calendar, Tasks, Onedrive and other apps for CRUD pattern as AI agent service skills to integrate with your AI workflow.


Below are initial screens showing integration:

URL: awacke1/MSGraphAPI
Discussion: awacke1/MSGraphAPI#5

Best of AI on @Azure and @Microsoft on @HuggingFace :
microsoft
https://www.microsoft.com/en-us/research/
---
Aaron
awacke1Β 
posted an update about 1 year ago
view post
Post
1025
Updated my πŸ“ΊRTVπŸ–ΌοΈ - Real Time Video AI app this morning.
URL: awacke1/stable-video-diffusion

It uses Stable Diffusion to dynamically create videos from images in input directory or uploaded using A10 GPU on Huggingface.


Samples below.

I may transition this to Zero GPU if I can. During Christmas when I revised this I had my highest billing from HF yet due to GPU usage. It is still the best turn key GPU out and Image2Video is a killer app. Thanks HF for the possibilities!