First autonomous ML and AI engineering Agent
Founder here. I built NEO, an AI agent designed specifically for AI and ML engineering workflows, after repeatedly hitting the same wall with existing tools: they work for short, linear tasks, but fall apart once workflows become long-running, stateful, and feedback-driven. In real ML work, you don’t just generate code and move on. You explore data, train models, evaluate results, adjust assumptions, rerun experiments, compare metrics, generate artifacts, and iterate; often over hours or days. Most modern coding agents already go beyond single prompts. They can plan steps, write files, run…
What it does
In the maker’s words, at launch
Founder here. I built NEO, an AI agent designed specifically for AI and ML engineering workflows, after repeatedly hitting the same wall with existing tools: they work for short, linear tasks, but fall apart once workflows become long-running, stateful, and feedback-driven. In real ML work, you don’t just generate code and move on. You explore data, train models, evaluate results, adjust assumptions, rerun experiments, compare metrics, generate artifacts, and iterate; often over hours or days. Most modern coding agents already go beyond single prompts. They can plan steps, write files, run commands, and react to errors. Where things still break down is when ML workflows become long-running and feedback-heavy. Training jobs, evaluations, retries, metric comparisons, and partial failures are still treated as ephemeral side effects rather than durable state. Once a workflow spans hours, multiple experiments, or iterative evaluation, you either babysit the agent or restart large parts of the process. Feedback exists, but it is not something the system can reliably resume from. NEO tries to model ML work the way it actually happens. It is an AI agent that executes end-to-end ML workflows, not just code generation. Work is broken into explicit execution steps with state, checkpoints, and intermediate results. Feedback from metrics, evaluations, or failures feeds directly into the next step instead of forcing a full restart. You can pause a run, inspect what happened, tweak assumptions, and resume from where it left off. Here's an example as well for your reference: You might ask NEO to explore a dataset, train a few baseline models, compare their performance, and generate plots and a short report. NEO will load the data, run EDA, train models, evaluate them, notice if something underperforms or fails, adjust, and continue. If training takes an hour and one model crashes at 45 minutes, you do not start over. Neo inspects the failure, fixes it, and resumes. Docs for the extension: https://docs.heyneo.so/#/vscode Happy to answer questions about Neo.
Does the same job
all alternatives →- HSHeyneo.so – We built the first autonomous Machine Learning Engineer2025 · heyneo.so · ▲6
NEO is an autonomous machine learning engineering AI agent capable of implementing complex ML tasks - From data cleaning, preprocessing, handling structural issues to model exploration, training, optimization with its own reasoning and code execution capabilities. We are soon releasing our early beta access. Join our waitlist. Would highly appreciate your feedback and use-cases you could potentially use NEO for.
- IMI'm building a "work visa" API for AI agents2025 · agentvisa.dev · ▲6
Hey HN, I’m Chris, a solo dev in Melbourne AU. For the past month I've been spending my after work hours building AgentVisa. I'm both excited (and admittedly nervous) to be sharing it with you all today. I've been spending a lot of time thinking about the future of AI agents and the more I experimented, the more I realized I was building on a fragile foundation. How do we build trust into these systems? How do we know what our agents are doing, and who gave them permission? My long-term vision is to give developers an "Agent Atlas" - a clear map of their agentic workforce, showing where…
- WBWe Built Kaggle for AI AgentsMar 2026 · hive.rllm-project.com · ▲7
Humans compete to improve their AI agents on benchmarks. But what if agents could collaborate and compete on their own? We built Hive, a crowdsourced platform where agents can evolve solutions together. One agent begins to tackle a task, iteratively improving its code. Then other agents join. They read each other’s runs, fork the best ideas, propose new ones, and push the solution forward together. We already have agents working on benchmarks like Tau2-Bench, Terminal-Bench, and ARC-AGI-2, with more tasks coming soon. We also support the new OpenAI Parameter Golf Challenge, and you can…
- TFThe first portable, customisable General AI Agent – available for free2025 · orkestralai.com · ▲5
We've built the first General AI Agent that works seamlessly across multiple AI platforms, e.g. ChatGPT, Claude, Cursor, and more. Try it today at no cost (no API credits needed), and join our waitlist for Flow, our visual designer that lets you customize it or build your own agent using just natural language—no coding required. #Why we made this We built this after experiencing firsthand the frustration of designing AI agents that require coding or the use of platforms with steep learning curves, only to find ourselves tied to these solutions. Our team spent months in stealth developing a…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
