Nexa SDK
github.comSummary
Nexa SDK is a local on-device inference framework for GGML and ONNX models. It provides capabilities for text generation, image generation, vision-language models, audio language models, speech-to-text, and text-to-speech. The SDK offers an OpenAI-compatible API and supports various device types including CPU, GPU (CUDA, Metal, ROCm), iOS, and Android.
Features5/13
See allMust Have
2 of 5
Conversational AI
API Access
Safety & Alignment Framework
Fine-Tuning & Custom Models
Enterprise Solutions
Other
3 of 8
Image Generation
Code Generation
Multimodal AI
Research & Publications
Security & Red Teaming
Synthetic Media Provenance
Threat Intelligence Reporting
Global Affairs & Policy
PricingTiered
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, plus...
- 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, plus...
- 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
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models, explicitly stating support for text generation (conversational AI), image generation, vision-language models (multimodal AI), and audio language models. It also offers an OpenAI-compatible API, directly aligning with the API Access feature. While it doesn't explicitly mention 'safety & alignment framework' or 'enterprise solutions' as core features of the SDK itself, its focus on local on-device inference and developer tools strongly aligns with the target audience and core value proposition of the OpenAI Platform.
