Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.
unmodeled-tyler 
posted an update 10 days ago
view post
Post
151
Centauri ADE: https://github.com/unmodeled-tyler/centauri

This is Centauri - It's a lightweight Agent Development Environment for Linux with git source control and codebase understanding.

I've tried out several different IDE/ADEs and nothing has really worked as well as I'd like for what I need. For the options that I did like, BYOK was second-class, or in the case of a full IDE, it sometimes felt like I was trying to get an airliner into low-earth-orbit.

Enter: Centauri - a simple local-first CLI harness wrapper with a focused git source-control workspace.

It gives you a clean side-by-side flow:
- run your preferred CLI coding agent in an embedded terminal
- watch repository changes appear in the Changes panel
- generate an industry-standard commit message
- commit and push without leaving the app

It's designed to complement tools like Claude Code, Codex, Pi, OpenCode, etc. It does not replace Git, your terminal, or your existing credentials - it wraps the tools you already use into a tighter cohesive workspace optimized for engineering with an agent.

I built Centauri for myself after trying way too many different options. It solves several pain points for me and I'm sharing it in case it solves some for you too!
  • 1 reply
·
unmodeled-tyler 
posted an update 18 days ago
view post
Post
2968
The UFO/UAP Dataset is complete!

unmodeled-tyler/DoW-UFO-UAP-1

The most recent release from the Department of War is there up in full and ready for analysis!

The dataset ships with an Hermes Agent Skill so you can quickly and easily start parsing through the data immediately.

Go chase some anomalies! 🚀

unmodeled-tyler 
posted an update 23 days ago
view post
Post
3013
Just started a fun project!

unmodeled-tyler/DoW-UFO-UAP-1

I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!

There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.

This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.

Check it out! Who knows what you'll find in there?
  • 3 replies
·
unmodeled-tyler 
posted an update 25 days ago
view post
Post
4117
Hey Hugging Face!

Repo: https://github.com/unmodeled-tyler/vessel-browser

I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!

You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.

Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.

Check it out!
  • 1 reply
·
unmodeled-tyler 
posted an update about 1 month ago
view post
Post
2076
Just published a new blog!: https://huggingface.co/blog/unmodeled-tyler/vessel-browser-for-agents

I do a lightweight overview of the open source AI-native browser I've been building called Vessel Browser!

It recently passed 50 stars on Github, and I tremendously appreciate everyone that's given it a try so far! I'm in it for the long haul with Vessel Browser so expect many, many more improvements to come.

If you'd like to check out the repo: https://github.com/unmodeled-tyler/vessel-browser
unmodeled-tyler 
posted an update 2 months ago
view post
Post
2293
RESULTS ARE IN!

- Videos of each evaluation: https://www.youtube.com/playlist?list=PLkDBfeR-zsShiZ2HpcscFDH-36uDwsl5W
- Link to repo: https://github.com/unmodeled-tyler/vessel-browser
-
quanta-intellect

Finally just wrapped up a comparative analysis of my new open source AI browser, Vessel, against Claude Chrome from Anthropic.

The test evaluates both web navigation harnesses for speed and efficiency on a simple real-world e-commerce task. Opus 4.6 was used for each of the 3 evaluations, and the results show that Opus 4.6 was AT LEAST 2X FASTER when using Vessel Browser for web navigation in place of Claude Chrome.

Results (in order, fastest to slowest)

1. Claude Code + Vessel Browser: 3 minutes and 10s

2. Hermes Agent + Vessel Browser: 4 minutes and 13s

3. Claude Code + Claude Chrome: 7 minutes and 57s

Vessel Browser is open source, designed explicitly for agents from the ground-up (it is not a fork of a human browser with AI features bolted on), and supports a local MCP server for agent control, or BYOK custom OAI endpoints. Check it out for yourself!
unmodeled-tyler 
updated a Space 2 months ago
unmodeled-tyler 
published a Space 2 months ago
unmodeled-tyler 
posted an update 2 months ago
view post
Post
1983
Hey Hugging Face!

PRODUCT HUNT LINK: https://www.producthunt.com/products/quanta-intellect?utm_source=other&utm_medium=social

I've been sharing my new AI browser Vessel the last few days and I've gotten some great feedback/interest from a lot of you!

I'm excited to announce that Vessel Browser is now live on Product Hunt! If this is the first you've heard of it, check it out! Vessel is an open source AI browser built specifically for agents on Linux. It's not a fork of an existing browser, and it doesn't assume that the human is the primary operator.

If you've already tried Vessel Browser, feel free to leave a review on Product Hunt of what you thought - or if you'd prefer, send me an email directly or reach out on twitter if you have any questions about it. I'm perpetually online & happy to chat 😀

I'm committed to building the best open source AI browser out there, and Vessel is only going to improve as time goes on!
unmodeled-tyler 
posted an update 2 months ago
view post
Post
1476
PSA: LiteLLM has been compromised on PyPI - if you have it installed, CHECK NOW.

LiteLLM is used as a dependency in A LOT of AI tooling, so there's a pretty good chance that you have it installed somewhere on your machine (my instance was part of Hermes Agent, but I was unaffected by the hack)

Versions 1.82.7 & 1.82.8 on PyPI have been compromised with a multi-stage credential stealer.

- Version 1.82.8 uses a .pth file that executes on EVERY python process startup. You don't even need to import litellm. Just having it installed is enough.
- The payload harvests SSH keys, .env files, AWS/GCP/Azure credentials, Kubernetes configs, database passwords, crytpo wallets, shell history - basically every secret on your machine.
- Stolen data is encrypted with a hardcoded RSA key and exfiltrated to a domain that is NOT part of a legitimate litellm infrastructure.
- If you're running Kubernetes, it attempts lateral movement across the entire cluster.
- The C2 is hosted on the Internet Computer blockchain, making it essentially impossible to take down.

This is part of a coordinated campaign by a threat actor called TeamPCP who have also hit Trivy (Aqua Security), Checkmarx KICS, and multiple npm packages in the last week ALONE.

What to do:

1. Run 'pip show litellm' in every environment you have
2. If you're on 1.82.7 or 1.82.8 - rotate EVERY secret on that machine immediately.
3. Check for persistence artifacts ~/.config/sysmon/sysmon.py & ~/.config/systemd/user/sysmon.service

I was lucky in this case that my litellm version was out of date, but if you've installed litellm as a dependency in ANY package within the last 24ish hours, you're gonna want to check.

SOURCES
https://futuresearch.ai/blog/litellm-pypi-supply-chain-attack/

Same group, different attack a couple of days ago: https://www.stepsecurity.io/blog/canisterworm-how-a-self-propagating-npm-worm-is-spreading-backdoors-across-the-ecosystem
  • 5 replies
·
unmodeled-tyler 
posted an update 2 months ago
view post
Post
3468
Here's a demo of Vessel Browser in action!

Minimax M2.7 was challenged with navigating to a large Ecom site, curate a selection of 5 different products, and add them all to the cart with included reasoning behind choices. (or try it yourself - open source, MIT license, and BYOK!)
npm i @quanta-intellect/vessel-browser

Vessel is a browser that I've been working on which is designed specifically for agents with human-in-the-loop visibility. It comes with a local MCP server allowing any harness that supports custom MCP to control the browser. Additionally, you can BYOK to 8+ different providers (including custom OAI compatible endpoints and local models).

One of my favorite features of the browser is persistent, bi-directional highlighting - meaning that both you AND the agent can highlight anything on the screen and the agent receives the context.

Vessel Browser is unique in that it surfaces available tools contextually to the agent, meaning the agent doesn't have to decide between 80+ tools at any given time, but rather is focused on a subset of tools most applicable to the current state.

Give it a try!

https://github.com/unmodeled-tyler/vessel-browser
  • 2 replies
·
unmodeled-tyler 
posted an update 3 months ago
view post
Post
5789
LINK: https://github.com/unmodeled-tyler/vessel-browser

Hey Hugging Face!

It's been quiet from me over here for the last few weeks, but I've been busy building! I just submitted my project to the Hermes Agent Hackathon, and wanted to share it with all of you.

This is Vessel Browser - an AI-native web browser that runs locally on Linux, and is operated by your personal AI agent via MCP server. Vessel is built from the ground up around the agent as first-class and visible UI for human-in-the-loop with 3 different levels of permissions.

Your agent finds, reads, and organizes the web for you, based on what you actually care about - not what a platform's algorithm thinks you care about.

Once your agent finds what it's looking for, it can organize bookmarked pages into custom folders with summaries for later browsing, take screenshots with highlighted text, and integrate with Obsidian for long-term browsing related-memory.

Check it out!
  • 3 replies
·
unmodeled-tyler 
posted an update 3 months ago
view post
Post
3032
Link to Repo: https://github.com/unmodeled-tyler/thought-tracer

I had a great time at Mistral's Hackathon in SF over the weekend! There were a lot of incredibly talented builders there and it was an honor to be a part of it! 😄

I built Thought Tracer - a TUI-based logitlens application for Ministral 3B/8B with optional AI analysis from Mistral Large on the Mistral API.

Thought Tracer allows you to see what the model "believes" at each layer until it arrives at it's final next token prediction. The Entropy tab displays entropy through each layer, additionally providing both token-level and prompt-level risk for hallucination.

If you have a Mistral API key, the AI analysis section is actually pretty cool because it's returned in rendered markdown and easily understandable language - providing a commentary on how the model likely arrived at it's final prediction, and also offering diagnostics for model developers. This commentary actually makes the tool pretty beginner friendly to anyone interested in exploring AI research tools for the first time.

Check it out if you're interested!
  • 4 replies
·
unmodeled-tyler 
posted an update 3 months ago
view post
Post
1954
New Article: https://huggingface.co/blog/unmodeled-tyler/how-we-learned-to-talk-to-machines

I was inspired by a single word in a Mac terminal prompt recently; "we."

The result is a bit of a journey through computational culture and history where we explore collaborative software design from the earliest computing systems to modern day AI systems.

I discuss how Large Language Models and collaborative AI interaction as we experience it today are a natural evolution in a long lineage of tools that came before; each compounding on last.

From CLI tools in the 60s-70s, to Clippy, to ChatGPT. I trace the history of "machines with a voice." Check it out!
unmodeled-tyler 
posted an update 3 months ago
view post
Post
2523
NEW MODEL: vanta-research/PE-Type-4-Solene-4B

PE-Type-4-Solene-4B is the fourth release in Project Enneagram from VANTA Research, an initiative to study nuance in AI persona design wherein each of the 9 Enneagram types will be finetuned on the Gemma3 4B architecture.

Solene is finetuned to exhibit the Individualist profile as defined by the Enneagram Institute; emotional honesty/depth, growth & transformation intelligence, and creative expression.

As with the other releases in this project, Solene is perfect for research applications, persona exploration, or self-improvement.

Type 5 soon!
unmodeled-tyler 
posted an update 4 months ago
view post
Post
385
NEW MODEL: vanta-research/PE-Type-3-Nova-4B

PE-Type-3-Nova-4B is the 3rd release in Project Enneagram, an initiative from VANTA Research that sets out to finetune each of the 9 Enneagram types onto Gemma 3 4B.

Type-3-Nova-4B is designed to embody the Type 3 or "Achiever" profile; ambitious, competent, energetic, and highly-driven for advancement.

Nova is great for goal-setting, long-term planning, and AI persona research.

Give Type-3 a try! Type-4 coming soon!
unmodeled-tyler 
posted an update 4 months ago
view post
Post
2314
Hey Hugging Face!

Type 2 in Project Enneagram just came out: vanta-research/PE-Type-2-Alma-4B

PE-Type-2-Alma-4B is the second release in Project Enneagram, where I'm finetuning each of the 9 Enneagram types onto Gemma 3 4B

Type 2-Alma is designed to exhibit the "helper" profile:
- Empathetic Support: Emotional attunement - managing bad days, anxiety, grief, rejection, or feeling unseen
- Interpersonal Connections: Relationship building - making friends, listening, conflict, reciprocity, apologies
- Generous Guidance: Going above and beyond - cover letters, meal prep, gardening, wedding speeches, etc
- Identity: Alma's name, tone, and conversational style

Type 3 soon!

  • 1 reply
·
unmodeled-tyler 
posted an update 4 months ago
view post
Post
501
NEW MODEL: vanta-research/PE-Type-1-Vera-4B

PE-Type-1-Vera-4B is the first release in Project Enneagram, a VANTA Research initiative exploring the nuances of persona design in AI models.

Built on the Gemma 3 4B architecture, Vera embodies the Type 1 Enneagram profile; The Reformer—characterized by principled rationality, self-control, and a relentless pursuit of improvement.

Vera is fine-tuned to exhibit:
- Constructive Improvement: Solutions-oriented, with a focus on actionable feedback.
- Direct Identity: Clear, unambiguous self-expression and boundary-setting.
- Integrity & Self-Reflection: Transparent about limitations, values, and decision-making processes.
- Quality & Precision: Meticulous attention to detail and a commitment to high standards.

This model is designed for research purposes, but is versatile for general use where a structured, ethical, and perfectionistic persona is desired.

Type 2 coming soon!

*A note for the sake of transparency, this post originally included a variant of Vera trained on Ministral 3 3B - that model is still available, but for the purposes of this project, the base architecture was swapped out for Gemma 3.
  • 3 replies
·
unmodeled-tyler 
posted an update 4 months ago
view post
Post
1259
NEW MODEL: vanta-research/mox-small-1

Mox-Small-1 has landed on the Hub!

Finetuned from the fantastic Olmo3.1 32B architecture by AllenAI, Mox-Small-1 was trained using the same datasets and methodology as Mox-Tiny-1, making this model our second addition to the Mox-1 family of models.

Mox-1 is designed to prioritize clarity, honesty, and genuine utility over blind agreement. These models are perfect for when you want to be challenged in a constructive, helpful way.

By utilizing Olmo3.1 32B's architecture, Mox-Small-1 brings greater conversational depth and reasoning quality to the Mox-1 model family. Check it out!
unmodeled-tyler 
posted an update 4 months ago
view post
Post
3698
NEW MODEL: vanta-research/mox-tiny-1

Excited to share the first model from the new Mox-1 model family from VANTA Research!

Mox-Tiny-1 is finetuned from Llama's 3.1 8B architecture specifically for thinking partnership and high-fidelity AI interaction.

Training domains were carefully selected with this goal in mind, and all datasets used were synthetically generated for the Mox-1 models specifically.

Domains include but not limited to:
- Direct opinions (clear stances on various topics)
- Constructive disagreement (Pushing back on flawed premises)
- Epistemic confidence (calibrated certainty and uncertainty)
- Warmth & presence (Empathetic, human responses)
- Wonder & puzzlement (Intellectual curiosity)

Interaction Examples:

Direct opinions:
User: What's the best programming language?
Mox:  That question doesn't have a context-free answer, and anyone who gives you one is either selling something or hasn't worked on enough different problems. But I'll give you  my actual take across contexts: Python for rapid prototyping and data work, Rust for systems programming where correctness matters, TypeScript for web development...

Warmth & Humor:
User: I've been debugging this issue for six hours. 
Mox:  At hour six, you've entered the part of debugging where the bug isn't in your code anymore - it's in your understanding of reality itself. The semicolon starts looking suspicious. Show me what you're dealing with. Fresh eyes help, and mine haven't been staring at it since lunch.

Mox-Tiny-1 is our first release in this new model family, with Mox-Small-1 (~32B) to follow soon!

  • 5 replies
·