TabbyML/tabby
github.comSummary
TabbyML/tabby is an open-source, self-hosted AI coding assistant designed as an alternative to GitHub Copilot. It provides features like code completion, chat-based assistance, and an 'Answer Engine' for internal knowledge. The platform supports various AI models and offers enterprise-grade security and management features.
Features9/13
See allMust Have
5 of 5
Conversational AI
API Access
Safety & Alignment Framework
Fine-Tuning & Custom Models
Enterprise Solutions
Other
4 of 8
Code Generation
Multimodal AI
Research & Publications
Security & Red Teaming
Image Generation
Synthetic Media Provenance
Threat Intelligence Reporting
Global Affairs & Policy
PricingFreemium
See allFree
- Unlimited public/private repositories
- Dependabot security and version updates
- 2,000 CI/CD minutes/month (Free for public repositories)
- 500MB of Packages storage (Free for public repositories)
- Issues & Projects
- Community support
Team
- Everything included in Free
- Access to GitHub Codespaces
- Protected branches
- Multiple reviewers in pull requests
- Draft pull requests
- Code owners
- Required reviewers
- Pages and Wikis
- Environment deployment branches and secrets
- 3,000 CI/CD minutes/month (Free for public repositories)
- 2GB of Packages storage (Free for public repositories)
- Web-based support
Enterprise
- Everything included in Team
- Data residency
- Enterprise Managed Users
- User provisioning through SCIM
- Enterprise Account to centrally manage multiple organizations
- Environment protection rules
- Repository rules
- Audit Log API
- SOC1, SOC2, type 2 reports annually
- FedRAMP Tailored Authority to Operate (ATO)
- SAML single sign-on
- Advanced auditing
- GitHub Connect
- 50,000 CI/CD minutes/month (Free for public repositories)
- 50GB of Packages storage (Free for public repositories)
Rationale
TabbyML/tabby is a self-hosted AI coding assistant, directly competing with GitHub Copilot, which is a core offering of the OpenAI Platform. It explicitly states 'Self-hosted AI coding assistant' and 'open-source and on-premises alternative to GitHub Copilot'. The features listed, such as 'Answer Engine' for internal knowledge, chat side panel, and inline editing, align with conversational AI and code generation. The mention of 'OpenAPI interface' confirms API access. The focus on 'self-hosted' and 'enterprise upgrades' points to enterprise solutions. The ability to switch between different backend chat models and the mention of 'CodeGemma and CodeQwen model series' suggest custom models and fine-tuning capabilities. The emphasis on security features like 'Secret Protection' and 'Code Security' aligns with safety and alignment frameworks and security/red teaming. The 'GitHub Models' feature, while part of GitHub, is directly related to managing and comparing AI models, which implies research and publications and multimodal AI capabilities.