Two-pronged fix for cross-compilation:
1. git2 with vendored-openssl feature - compiles OpenSSL from source,
eliminating system dependency issues across all platforms
2. houseabsolute/actions-rust-cross@v1 - dedicated GitHub Action that
properly handles cross-compilation with Docker containers
Sources:
- https://github.com/rust-lang/git2-rs
- https://github.com/houseabsolute/actions-rust-cross
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- macOS ARM64: macos-latest (Apple Silicon)
- macOS x86_64: macos-13 (Intel) - no cross-compilation
- Linux x86_64: ubuntu-latest with OpenSSL
- Linux ARM64: cross tool for proper Docker-based cross-compilation
Install OpenSSL via homebrew on macOS and set OPENSSL_DIR.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Cross-compilation for aarch64-unknown-linux-gnu requires OpenSSL
dev libraries for the target platform. Using `cross` handles this
automatically via Docker containers with pre-installed dependencies.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Document how to pin to specific versions
- List available versions (v1.0.0, v1.1.0)
- Add version check command
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Address common question: users don't need to disable Claude's native
memory to use Vestige. They're independent systems that can run
simultaneously.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Detail what causes data loss (delete, corrupt, lost device)
- Clarify "For AI memory = fine, For critical data = not fine"
- Add automated cron job backup example
- Mention Time Machine / Windows Backup as options
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Simple 4-step Quick Start (2 minutes)
- Global install instructions (sudo cp to /usr/local/bin)
- Claude Code and Claude Desktop config examples
- Full 29-tool reference with descriptions
- Prediction Error Gating section with visual diagram
- Troubleshooting section
- Updating instructions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace BGE-base-en-v1.5 with nomic-embed-text-v1.5
- 8192 token context window (vs 512 for BGE)
- Matryoshka representation learning support
- Fully open source with training data released
- Same 768 dimensions, no schema changes required
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
FSRS-6 spaced repetition, spreading activation, synaptic tagging,
hippocampal indexing, and 130 years of memory research.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
