e2b-cookbook
SmartGPT
| e2b-cookbook | SmartGPT | |
|---|---|---|
| 9 | 2 | |
| 225 | 62 | |
| 55.6% | - | |
| 9.3 | 6.6 | |
| 7 days ago | about 1 month ago | |
| TypeScript | JavaScript | |
| - | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
e2b-cookbook
- Open-source secure sandboxes for AI code execution
-
Llama 3 with Function Calling and Code Interpreter
We have a full code on GitHub.
- Show HN: Llama 3 with function calling and code interpreter
- Llama 3 with open source code interpreter
-
Show HN: Add AI code interpreter to any LLM via SDK
Hi, I'm the CEO of the company that built this SDK.
We're a company called E2B [0]. We're building and open-source [1] secure environments for running untrusted AI-generated code and AI agents. We call these environments sandboxes and they are built on top of micro VM called Firecracker [2].
You can think of us as giving small cloud computers to LLMs.
We recently created a dedicated SDK for building custom code interpreters in Python or JS/TS. We saw this need after a lot of our users have been adding code execution capabilities to their AI apps with our core SDK [3]. These use cases were often centered around AI data analysis so code interpreter-like behavior made sense
The way our code interpret SDK works is by spawning an E2B sandbox with Jupyter Server. We then communicate with this Jupyter server through Jupyter Kernel messaging protocol [4].
We don't do any wrapping around LLM, any prompting, or any agent-like framework. We leave all of that on users. We're really just a boring code execution layer that sats at the bottom that we're building specifically for the future software that will be building another software. We work with any LLM. Here's how we added code interpreter to Claude [5].
Our long-term plan is to build an automated AWS for AI apps and agents.
Happy to answer any questions and hear feedback!
[0] https://e2b.dev/
[1] https://github.com/e2b-dev
[2] https://github.com/firecracker-microvm/firecracker
[3] https://e2b.dev/docs
[4] https://jupyter-client.readthedocs.io/en/latest/messaging.ht...
[5] https://github.com/e2b-dev/e2b-cookbook/blob/main/examples/c...
- Show HN: Add Code Interpreter to Claude 3 Opus
- AI Developer working on your repo
- Show HN: AI Agent with access to GitHub and it's own cloud sandbox to edit files
- Build custom code interpreter with GPT
SmartGPT
- SmartGPT: a refined response powered by gpt-4 GUI included.
-
Auto-GPT seems nearly unusable
It’s over hyped. It’s not that smart either. Try out smartGPT. I have my own version that produces better results. https://github.com/nschlaepfer/SmartGPT
What are some alternatives?
open-cravat - A modular annotation tool for genomic variants
EmbedAI - An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks
chatgpt-plugin - Powered by AI Playgrounds by E2B. Code interpreter on steroids for ChatGPT. Run any language, any terminal process, use filesystem freely. All with access to the internet. [Moved to: https://github.com/e2b-dev/llm-code-interpreter]
camel - 🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Language Model Society (NeruIPS'2023) https://www.camel-ai.org
WordPress-Plugin-Boilerplate-Tutorial - Tutorials and Examples for WordPress Plugin Boilerplate, a foundation for WordPress Plugin Development.
GPT-Prompter - Browser extension to get a fast prompt (of the selected text) for OpenAI`s GPT-3, GPT-4 & ChatGPT API . Available in the Chrome web store and Firefox browser add-ons
llm-code-interpreter - [DEPRECATED] Powered by AI Playgrounds by E2B. Code interpreter on steroids for ChatGPT. Run any language, any terminal process, use filesystem freely. All with access to the internet.
copycat-js - A JavaScript implementation of Douglas Hofstadter and Melanie Mitchell's Copycat program.
evalgpt - EvalGPT is an code interpreter framework that utilizes large language models to automate the process of code-writing and execution, delivering precise results for user-defined tasks.
GPT-Models-Plus - 用于在ChatGPT 网页版 强制锁定模型，支持GPT3.5/GPT4/GPT3.5M/GPT4M/GPT4B/GPT4P等模型
DuckDuckGPT - 🐤 DuckDuckGo add-on that brings the magic of ChatGPT to search results (powered by GPT-4!)
llm-client-sdk - SDK for using LLM