micrograd
tinygrad
PyTorch
TensorFlow
PyCaret
TigerBeetle
TorchStudio
Deeplearning4j
ForthWrite
ReclaimAI
Superhuman
Shortwave
Serif AI
Gemini
Gmail
LIAM
ForthWrite is an AI email writing assistant for Gmail and Outlook that learns your writing style from your real sent mail. The more you use it, the more it sounds like you. Get smart drafts in seconds, auto-draft replies before you open your inbox, and maintain your personal voice at scale. Free to start, no credit card required. Works inside Gmail and Outlook on the web.
How it works
ForthWrite captures your tone, sentence rhythm, and sign-offs from your actual sent emails, then uses that profile to generate drafts that match how you write, not a generic AI voice. Every draft you edit or send improves the model over time.
Key features
Who uses it
Professionals who send high volumes of relationship-critical email: lawyers, financial advisors, recruiters, account executives, founders, and anyone who wants their inbox handled without sounding like a chatbot wrote it.
Pricing
Free tier includes 10 drafts per week with no credit card required. Paid plans start at $12/month and include unlimited drafts, custom persona prompts, and auto-draft.
micrograd ForthWriteNo features have been listed yet.
ForthWrite's answer:
Next.js, React, Supabase, Anthropic Claude, OpenAI, Stripe, Vercel, Chrome Extensions API
ForthWrite's answer:
ForthWrite learns your writing style from your actual sent mail, not a generic prompt. Every draft sounds like you wrote it because it was trained on how you actually write. It also auto-drafts replies before you open your inbox, so your email is partially handled before your day starts.
ForthWrite's answer:
Most AI email tools give you a blank box and a "write for me" button. ForthWrite builds a voice profile from your sent history and gets more accurate with every draft you edit or send. Unlike ChatGPT or Gemini, it works natively inside Gmail and Outlook with no copy-paste. Unlike Lavender, it writes the draft, not just scores it.
ForthWrite's answer:
Professionals who send high volumes of relationship-critical email and cannot afford to sound generic: lawyers, financial advisors, recruiters, account executives, consultants, and founders managing their own inbox.
ForthWrite's answer:
Built out of frustration with AI writing tools that produce text that sounds nothing like the person sending it, and as a way to handle large amounts of daily email. The core insight was that your sent mail is the best training data you already have, and no tool was using it.
I built ForthWrite because I kept sending emails that sounded like they came from the same generic AI as everyone else. After launching it, I still use it for my own inbox every day, which is about the most honest endorsement I can give.
The Chrome extension lives inside Gmail and Outlook on the web. Open a thread, hit Alt+Shift+D, and a draft comes back in your voice, not a template. The free tier is real: 10 drafts per week, no API key, no credit card. Voice matching is included on free, because that is the point.
What keeps it useful compared to Gemini or a chat tab: it learns from what you actually send. Every edit you make before hitting send becomes a signal. Over time the drafts drift closer to how you really write, and the dashboard shows the improvement curve so you can see it happening.
The web compose surface lets you draft from forthwrite.ai without installing anything, useful for people who want to try before committing to the extension.
Standard adds recipient-aware and intent-aware drafting plus AI coaching. Pro adds auto-draft (replies waiting when you open Gmail), batch replies, and Prompt Lab for version-controlling your prompts. Teams adds a shared persona and seat-level analytics.
ForthWrite is not for everyone. If you just need quick replies and tone does not matter, Gemini is free and already in your inbox. ForthWrite is for people where tone does matter: client communication, relationship-driven threads, external correspondence where sounding off costs something real.
Disclosure: I am the founder and use it daily. Happy to answer questions in the comments.
Based on our record, micrograd seems to be more popular. It has been mentiond 5 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
I built the first version of DeepFork to understand micrograd โ Andrej Karpathy's 100-line autograd engine. Most people read micrograd for the aha moment. DeepFork turns that moment into an artifact. - Source: dev.to / about 2 months ago
Karpathy built a small project called micrograd. You can see the code here. This is made up of just a few simple lines of code, but it shows us how neural networks are built under the hood. In the video, he demonstrated how to build Micrograd and how it works step by step. - Source: dev.to / 2 months ago
It can happen like this: - write sleek operator-overloading-based code for simple mathematical operations on your custom pet algebra - decide that you want to turn it into an autograd library [0] - realise that you now need either `RefCell` for interior mutability, or arenas to save the computation graph and local gradients - realise that `RefCell` puts borrow checks on the runtime path and can panic if you get... - Source: Hacker News / 3 months ago
Good introduction! Building pytorch-lite using python and numpy is the way to go. Free book: https://zekcrates.quarto.pub/deep-learning-library/ Ml by hand : https://github.com/workofart/ml-by-hand Micrograd: https://github.com/karpathy/micrograd. - Source: Hacker News / 6 months ago
Let me be completely honest: I didn't invent anything here. This is Andrej Karpathy's brilliant micrograd ported to C++, nothing more, nothing less. But sometimes the best way to really understand something is to rebuild it in a different language, and that's exactly what I needed. - Source: dev.to / 11 months ago
tinygrad - This may not be the best deep learning framework, but it is a deep learning framework.
ReclaimAI - Helps users prioritize their work and personal calendars
PyTorch - Open source deep learning platform that provides a seamless path from research prototyping to...
Superhuman - Superhuman is an email management tool.
TensorFlow - TensorFlow is an open-source machine learning framework designed and published by Google. It tracks data flow graphs over time. Nodes in the data flow graphs represent machine learning algorithms. Read more about TensorFlow.
Shortwave - Email smarter & faster with a reinvented experience for your Gmail