Open-source, secure environment with real-world tools for enterprise-grade agents.
Python agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Update readme
Vasek Mlejnsky0ec82db6f943
diff --git a/README.md b/README.mdindex 7df370963..5fe37e1b5 100644--- a/README.md+++ b/README.md@@ -3,7 +3,7 @@<img width="200" src="docs-assets/logoname-white.svg#gh-dark-mode-only" alt="e2b"></h1>-<h2 align="center">Developer-first AgentOps platform - deploy, test, and monitor AI agents</h2>+<h2 align="center">Developer-first platform for deploying, testing, and monitoring AI agents</h2><h4 align="center"><a href="https://e2b.dev">Website</a> |@@ -20,92 +20,64 @@</a></h4>-<!--  -->+[e2b](https://e2b.dev) (_english2bits_) is like AWS for AI agents. Our goal is+to build a developer-first platform that helps developers to build reliable AI+agents.-[e2b](https://e2b.dev) or etob (*english2bits*) allows you to deploy AI agents.+E2b allows developers to debug, test, deploy, and monitor their AI agents.-Agents operate in our own secure sandboxed cloud environments that's powered by [Firecracker](https://github.com/firecracker-microvm/firecracker/).+# How e2b works++E2b is made of three parts:++1. Infrastructure+2. Cloud dashboard+3. SDK (Launching Soon)++Every agent deployed on e2b gets their own small virtual machine.# π Get started-We're working on the cloud-hosted version. In the meantime, the fastest way try out e2b is to run it locally via Docker.++We're working on the cloud-hosted version. In the meantime, the fastest way try+out e2b is to run it locally via Docker.## π³ Start e2b with Docker+You will need:-- [OpenAI API key](https://platform.openai.com/account/api-keys) (support for more and custom models coming soon)++- [OpenAI API key](https://platform.openai.com/account/api-keys) (support for+ more and custom models coming soon)- Docker-- Node.js *16+*-- Free ports 3000 (Next.js app), 54321 (Supabase API Gateway), 54322 (Supabase Database)+- Node.js _16+_+- Free ports 3000 (Next.js app), 54321 (Supabase API Gateway), 54322 (Supabase+ Database)To start e2b run:+```npm start```Then open page on [http://localhost:3000](http://localhost:3000).-`npm start` starts local Supabase in the background - to stop it you have to run `npm run stop`.+`npm start` starts local Supabase in the background - to stop it you have to run+`npm run stop`.## π» Development setup-For developing with hot reloading and contributing to the project you may want to run the app locally without Docker (`npm start` command).-[Follow these steps](DEVELOPMENT_SETUP.md) to set it up.+For developing with hot reloading and contributing to the project you may want+to run the app locally without Docker (`npm start` command).-# Features-## π Bring your own X-While e2b will offer the "batteries-included" solution, our goal is to let users:-- **BYOM** - Bring Your Own Model-- **BYOP** - Bring Your Own Prompt-- **BYOT** - Bring Your Own Tools--## π€ Supported models and model hosting providers-- [x] [OpenAI](https://openai.com/)- - [x] GPT-4- - [x] GTP-3.5-- [x] [Anthropic](https://anthropic.com/)- - [x] Claude v1.3- - [x] Claude Instant v1-- [x] [Replicate](https://replicate.com/)-- [x] [Hugging Face](https://huggingface.co/)- - [x] Inference API- - [x] Inference Endpoints-- [x] [Banana](https://www.banana.dev/)-- [x] [Azure OpenAI](https://azure.microsoft.com/en-us/products/cognitive-services/openai-service)--### **Model or model hosting provider you like isn't supported?**--π Please open the ["New model request" issue](https://github.com/e2b-dev/e2b/issues/new?assignees=&labels=new+model+request&template=new-model-request.md&title=) π--π Or open a PR and [start contributing](./CONTRIBUTING.md#π€-adding-a-new-model-provider) π--## π Early demos-- [AI Agent using coding tools](https://twitter.com/mlejva/status/1636103084802822151)-- [Build your custom "Just-In-Time" UI](https://twitter.com/mlejva/status/1641151421830529042)-- [Agent coded a full Stripe customer checkout by following a technical spec provided by user](https://twitter.com/mlejva/status/1641072535163875330)+[Follow these steps](DEVELOPMENT_SETUP.md) to set it up.# βΉοΈ Community & Support+- [Discord](https://discord.gg/U7KEcGErtQ) - live discussion and support- [GitHub issues](https://github.com/e2b-dev/e2b/issues) - for reporting bugs- [Twitter](https://twitter.com/e2b_dev) - to stay up to date# π€ Contributing-We welcome any contributions! If you want to contribute to the project check out the [contibution guide](CONTRIBUTING.md) and join our [Discord](https://discord.gg/dSBY3ms2Qr).--# π Short-term Roadmap-1. β ~~Make sure people can run e2b locally without issues and the DX is smooth.~~-2. π§ Add support for more models.- - β ~~OpenAI~~- - β ~~Anthropic~~- - Model hosting providers:- - β ~~Replicate~~- - β ~~Hugging Face Inference API~~- - β ~~Hugging Face Inference Endpoints~~- - β ~~Banana~~- - Paperspace-3. π§ Improve agent's reliability and quality of output.-4. π§ Improve the feedback loop (UX/UI) between the developer and agents.-5. π§ Improve agent's understanding of the context based on the instructions.-6. π§ Deployable agents.-7. Support more tools and 3rd party integrations that agents can use.-8. β ~~Let users edit prompts.~~-9. Let users customize tools and build custom workflows for the agent.-10. Release cloud version.++We welcome any contributions! If you want to contribute to the project check out+the [contibution guide](CONTRIBUTING.md) and join our+[Discord](https://discord.gg/dSBY3ms2Qr).