Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing Mentat - an open source, GPT-4 powered coding assistant! Mentat runs in your command line, giving it the context of your projects and allowing it to coordinate edits across multiple files! More videos and a link to github below:

292,778 Aufrufe • vor 3 Jahren •via X (Twitter)

10 Kommentare

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

Here's an example of using Mentat to work with @karpathy's new llama2.c - Mentat can explain unfamiliar codebases, help you plan out changes, and edit in languages you're unfamiliar with.

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

I believe combining human and AI capabilities is the way to unlock new levels of productivity, so a powerful interface is key. Mentat modifies, creates, and deletes files, and is aware of the current git diff so it can extend your work. Use interactive mode to select suggestions

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

Mentat is open source and available on Github!

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

There's also a discord community!

Profilbild von kache
kachevor 3 Jahren

very good call to keep it based on terminal. you dodged so much compat stuff

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

thanks! yeah eventually I imagine plugins for editors, but at this point goal is to move fast with core functionality

Profilbild von anton
antonvor 3 Jahren

This is cool, tried it but it made an error and code didn't run after :)

Profilbild von BioBootloader
BioBootloadervor 3 Jahren

it's not 100% yet! I'm working on this full time and it will continue to improve. I have a lot of plans for improving robustness

Profilbild von honey
honeyvor 3 Jahren

nice, impressive. (i will try it once i get arch running)

Profilbild von Brian Sunter
Brian Suntervor 3 Jahren

Been using this and it works great. I was copying code into ChatGPT like a caveman before.

Ähnliche Videos

Anthropic just got outplayed again. Devs built the multiplayer assistant Anthropic couldn't, and open-sourced it. Claude Cowork is a solo desktop agent. You point it at a folder, give it a task, and it works through your local files on your own machine. The moment a teammate enters the picture, it has nothing to offer. Most real work does not happen alone. A teammate asks for a status update on something you own. The context they need is scattered across your meetings, your notes, and decisions made last week. Typing all of that out takes time you do not have. This is the gap Claude Cowork was never designed to cross. Rowboat Spaces is built on a different model entirely. Each person brings their own assistant into a shared channel. Your assistant is your second brain. It knows your meetings, your notes, and your open decisions. That personal context stays yours. When a teammate asks a question in the channel, you ask your assistant to brief them. It pulls from everything you know and delivers the answer on your behalf, attributed to you. Your teammate's assistant does the same, from their own context. Teams can draft specs, track decisions, and update shared files from plain conversation. Each assistant reads the full channel history, cross references it against what exists, and flags what is missing. The whole thing is open-source, and each assistant acts as the person it belongs to, not as a shared bot pulling from a common pool. The video below shows this in action. I joined a shared space and asked my team member for a status update. My team member asked their second brain to answer. A spec got built from that conversation, versioned, with every change tracked back to the message that triggered it. Rowboat GitHub: (don't forget to star 🌟) My co-founder also wrote a great article on building your second brain with Rowboat, and I highly recommend reading it as well. The article is quoted below.

Akshay 🚀

117,616 Aufrufe • vor 1 Monat