A coding agent for open models like GLM, Deepseek, and Kimi K3
Seattle
Joined September 2023
- Tweets61
- Following0
- Followers17.6K
- Likes1.7K
Pinned Tweet
We implemented Kimi K3's native harness in Rust.
Now, @OpenInterpreter is the #1 trending Rust repo in the world.
Apache licensed, ACP + Codex SDK compatible — a CLI for the next generation of open models.
Open Interpreter is a drop-in replacement for Codex.
It's also ACP compatible, with Claude Agent SDK compatibility on the way.
However you build with agents, we want to support your switch to open models.
We're still early, so please try it out, report issues, and ⭐ star the repo below!
github.com/openinterpreter/o…
We're on a mission to implement the best harness for each model in one coding agent.
For each model, the most performant harness is used under the hood.
Follow our blog for details:
openinterpreter.com/blog/ope…
Why reimplement a coding harness?
Because harness choice dramatically affects a model's performance. Some models are even trained inside a specific harness.
Now that the provider ecosystem is diversifying, we needed an agent core that could adapt its harness.
ALT The range of benchmark scores (blue line) for each model on different harnesses, including the model-maker's harness (white dot). The chart shows that harnesses dramatically affect the performance of a model.
Interpreter retweeted
Pretty cool to see a popular fork of Codex OSS repo with 60k stars out there with my team being top contributors (due to preserving history with the fork)
Keep building
github.com/openinterpreter/o…
Interpreter retweeted
Today we're discontinuing the 01 light, refunding everyone, and launching a free 01 app.
We're also open-sourcing all our manufacturing materials + a major 01.1 update.
Why? Focus. This software will change the world. That deserves our full attention.
Also phones
🧵/8
Interpreter retweeted
👀 IT SHOULD BE AN APP!?
Menudo giro en los acontecimientos.
Te lo cuento ya mismo 👇🏼
Interpreter retweeted
Llama 3.1 talks to your database for free with @OpenInterpreter
Why pay for a talk-to-your-database service?
Save money!
It's also fully offline and private, nobody else needs to see your data
Join @MikeBirdTech in one hour!
Tomorrow at 1 pm, I'll be talking about @OpenInterpreter on the @MozillaAI Discord
See you there!
discord.gg/xwYPEMFf?event=12…
Interpreter retweeted
What an amazing discussion with @MikeBirdTech from @OpenInterpreter on the future of natural language Ai interfaces and how they're changing the way we connect with technology at a fundamental level.
Check them out on Github and join their next open house party on Discord! discord.gg/Hvz9Axh84z
Watch this episode on Spotify: podcasters.spotify.com/pod/s…
Interpreter retweeted
Llamafile in Colab!
We put together a notebook so you can run @OpenInterpreter in a free instance of Colab that uses llamafile to serve your inference
It's also a nice guide for how you can run OI fully locally
Interpreter retweeted
Local Codestral generating #scikitlearn and Keras code to run a medical imaging prediction on the fly. I like that :)
Open Interpreter's new release looks great for locally running LLMs
The tool lets LLMs run code (Python, Javascript, Shell, and more) locally. You can chat with Open Interpreter through a ChatGPT-like interface in your terminal by running $ interpreter after installing.
Just do `pip install open-interpreter`
and then just run
`- interpreter --local` sets up fast, local LLMs.
Congrats @hellokillian 👏