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.
Just wanted to annouce 🏭SmolFactory : it's the quickest and best way to finetune SmolLM3 and GPT-OSS-20B on huggingface !
Basicaly it's an app you can run on huggingface by duplicating the space and running your training directly on huggingface GPUs .
It will help you basically select datasets and models, fine tune your model , make an experiment tracker you can use on your mobile phone , push all your model card and even automatically make a demo for you on huggingface so you can directly test it out when it's done !
Current transformer-based, self-supervised systems have driven massive gains, but important gaps remain on the path to AGI. Key missing pieces are continual, curiosity-driven learning; grounded multimodal perception; reliable, contextual long-term memory with forgetting; motivated (hot) executive control and dynamic attention; metacognition and coherent causal world-models; and robust fluid reasoning, planning and decision-making. Progress will require hybrid architectures (neuromorphic/Hebbian + gradients + symbolic modules), active-inference and intrinsic-motivation objectives, and new lifelong, embodied benchmarks to evaluate safety and competence.
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.
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
just submitted my plugin idea to the G-Assist Plugin Hackathon by @nvidia . Check it out, it's a great way to use a local SLA model on a windows machine to easily and locally get things done ! https://github.com/NVIDIA/G-Assist
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?
So every bio/med/chem meeting i go to i always the same questions "why are you sharing a gdrive link with me for this?" and "Do you have any plans to publish your model weights and datasets on huggingface?" and finally i got a good answer today which explains everything :
basically there is some kind of government censorship on this (usa, but i'm sure others too) and they are told they are not allowed as it is considered a "dataleak" which is illegal !!!!
this is terrible ! but the good news is that we can do something about it !
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.
Mining LLM Pretraining Data: Topics, Skills, and Cognitive Patterns
Summary The technical blog post details an analysis of pretraining data from various Large Language Models (LLMs) like GPT-2, Falcon, and Gemma2. Using text mining techniques including embeddings, clustering, and LLM-based annotation on datasets like OpenWebText, The Pile, and C4, the study identified key patterns.
Findings show the data is dominated by topics like Technology, Politics, Health, Business, and Culture, originating from diverse sources including web scrapes, academic papers, code repositories, and news media. The data reflects the work of professionals primarily in Journalism/Media, Content Creation, Analysis/Research, Academia, and Tech/Engineering. Consequently, LLMs learn corresponding skills (e.g., Research, Critical Thinking, Communication, Domain Expertise) and task representations (e.g., Analysis, Content Creation, Compliance).
The analysis also uncovered distinct writing styles, underlying cognitive frameworks (beliefs, frames, schemas, memes), and common cognitive biases (like Confirmation Bias) embedded in the data. LLM capability progression appears linked to data scale and task frequency, following a power law. The study concludes that LLMs are powerful data-driven simulators whose capabilities and limitations are shaped by the composition and inherent biases of their pretraining corpora, highlighting the importance of data understanding and curation.
The document warns of the "intelligence curse," a potential consequence of advanced AI (AGI) where powerful entities lose their incentive to invest in people as AI automates work[cite: 13, 297]. This could lead to job displacement, reduced social mobility, and a concentration of power and wealth based on AI ownership, similar to the "resource curse" in resource-rich states[cite: 17, 18, 31, 329, 353]. To counter this, the authors propose averting AI catastrophes to prevent centralization, diffusing AI widely to keep humans economically relevant, and democratizing institutions to remain anchored to human needs[cite: 22, 23, 25, 35, 36, 37, 566].
Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!
### Model Details - **Model Name**: [lettucedect-large-modernbert-en-v1](KRLabsOrg/lettucedect-large-modernbert-en-v1) - **Organization**: [KRLabsOrg](KRLabsOrg) - **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect) - **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens - **Task**: Token Classification / Hallucination Detection - **Training Dataset**: [RagTruth](wandb/RAGTruth-processed) - **Language**: English - **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.
LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.
