Overview
Refact.ai is designed to improve teams' productivity. It is focused on security and allows users to customize the AI coding assistant to their needs.
For enterprises seeking to boost developer efficiency by 45%, the Refact.ai Enterprise plan offers:
- Ultimate Security: Deploy Refact.ai on-premise on your servers or private cloud. Your data remains under your control with open-source transparency.
- Fine-tuning: Simplified fine-tuning without needing a data engineer. The fine-tuned model learns your coding style, internal API usage, and tech stack, aiding in writing around 45% of your code.
- User Statistics: Track code contributions from each team member and measure productivity gains.
- Efficient Inference: Support for paged attention and continuous batching allows up to 50 engineers per GPU for code completion.
- Priority Support: Access dedicated support from setup through fine-tuning and beyond.
- Access to 20+ LLMs: Includes models like Refact/1.6B, GPT-4, Code Llama, StarCoder2, Mistral, and Mixtral, with fine-tuning options for many.
Choose Refact.ai to improve your coding efficiency, security, and customization with an AI assistant that perfectly fits your needs.
To get started and obtain a license, email us at enterprise@refact.ai or complete the form at https://refact.ai/enterprise/ ! Our team is eager to help you unlock your full potential with Refact.ai.
Highlights
- Knows Your Code: Refact.ai focuses on automated customization for internal codebases and improving over time.
- Fine-Tuning: We've solved all the complexity for you, no data engineer required. A fine-tuned code completion model will provide you with more relevant suggestions: it can memorize your coding style, the right way to use your internal APIs, and the tech stack you use. After fine-tuning, auto-completion helps our clients to write around 45% of their code.
- User Statistics: Keep track of how much code Refact.ai helps to write for each team member. Measure productivity gains with real numbers.
Details
Pricing
Additional AWS infrastructure costs
Type | Cost |
|---|---|
EBS General Purpose SSD (gp3) volumes | $0.08/per GB/month of provisioned storage |
Vendor refund policy
According to our terms of use: https://refact.ai/terms-of-use/
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Hello everyone! It's been a while since we shared the news, so we are excited to bring you Refact 1.6.3!
Here's what's new:
Refact.ai Self-hosted:
- Llama3 8k Context:
llama3models now support 8k context. - Credentials Management: We added information about tokens and keys.
- Deprecated Models: The models
starcoder,wizardlm, andllama2are deprecated and will be removed in the next release.
Refact.ai Enterprise:
- Refact Model 4k Context:
refactmodel now supports 4k context.
Go try it out and build amazing things with Refact!
Additional details
Usage instructions
Getting Started: https://docs.refact.ai/guides/deployment/aws/getting-started/ Launch from EC2 console: https://docs.refact.ai/guides/deployment/aws/ec2/ Launch from Website: https://docs.refact.ai/guides/deployment/aws/marketplace/ Usage: https://docs.refact.ai/guides/deployment/aws/usage/
Resources
Vendor resources
Support
Vendor support
AWS marketplace subscribers are entitled to our Standard Support and our Community Support via Discord & GitHub. Discord channel: https://smallcloud.ai/discord VSCode GitHub: https://github.com/smallcloudai/refact-vscode/issues JetBrains GitHub: https://github.com/smallcloudai/refact-intellij/issues Support: support@refact.ai
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
