Skip to content

Releases: hanzoai/node

v1.14.0

26 Jan 06:57

Choose a tag to compare

Release v1.14.0 - Binary builds for all 5 platforms

v1.13.0 - AI Compute & Smart Contract Testing

04 Dec 07:54

Choose a tag to compare

Features:
- hanzo-compute: Distributed AI compute workload scheduling
- hanzo-ai-format: AI artifact storage and manifest management
- hanzo-mining: EVM bridge, consensus, ledger, wallet modules
- AITestMiner smart contract with comprehensive Foundry tests
- CI integration for Foundry smart contract testing

Smart Contract Tests:
- 9 tests including fuzz testing (256 iterations)
- Mining, attestation tracking, duplicate prevention
- Multi-user scenarios

All tests passing.

Make R2 upload step non-blocking for v1.2.2 release

23 Nov 17:59

Choose a tag to compare

- Add continue-on-error: true to R2 upload step
- Allows release to complete even if R2 credentials are invalid
- GitHub Releases upload and Docker image push will proceed normally
- Fixes AccessDenied error blocking v1.2.2 release

v1.2.0 - Native Embedding Support

21 Nov 21:10

Choose a tag to compare

🎉 Major Release: Native Embedding Support

This release introduces native embedding model support through the Hanzo Engine integration, enabling local inference without external API dependencies.

✨ New Features

  • Native Embedding Models: Integrated Hanzo Engine for local inference
  • Qwen3 Embedding Models: Added support for state-of-the-art Qwen3 models (8B, 4B, 0.6B)
  • Qwen3 Reranker Models: Implemented reranking for improved search quality
  • GGUF Format Support: Efficient model deployment with GGUF format
  • GPU Acceleration: Full GPU support for faster embeddings

🛠️ Improvements

  • CI/CD Pipeline: Added GitHub Actions workflow for automated testing
  • Makefile: Created simplified build and development commands
  • Test Fixes: Resolved compilation errors and unreachable patterns
  • Post-Quantum Ready: Infrastructure prepared for post-quantum cryptography

🔧 Technical Details

  • Default embedding model: Qwen3-8B (4096 dimensions, #1 MTEB multilingual)
  • Support for 32K context windows
  • Native inference without Ollama dependency
  • Automatic model downloading and caching

📦 Installation

# Build from source
make build

# Run locally
make run

⚠️ Known Issues

  • CI tests are still being stabilized
  • Some test framework imports need adjustment

📝 Notes

The node compiles and runs successfully locally. CI infrastructure is being improved for automated testing.

v1.1.14: ci: make R2 upload step optional to allow GitHub release upload

06 Nov 01:09

Choose a tag to compare

Adds continue-on-error to R2 upload step so that the workflow
can proceed to upload binaries to GitHub releases even when
R2 credentials are not available.