Skip to content

Release v0.0.13

Choose a tag to compare

@github-actions github-actions released this 10 Jun 08:40
· 29 commits to develop since this release
bcb9162

What's New in v0.0.13

Added

  • FTS5 hybrid search with RRF β€” Full-text search (FTS5) as parallel retrieval channel merged with vector search via Reciprocal Rank Fusion (RRF, k=60). New RecallStrategy enum: hybrid (default), vector, fts5. FTS5 virtual table auto-created; existing DBs get schema migration v1β†’v2. Phrase search + token-OR fallback. Deprecated memories excluded from FTS5. 6 new tests (#250, PR #261)
  • Metadata enrichment via CLI flags β€” --entity, --category, --meta key:value,... on remember. Post-filter on recall and list by --entity and --category. parse_meta_pairs() with auto type detection (string/number/bool). JSON output includes metadata when present (#251, PR #262)
  • Concurrent reads via RwLock β€” Mutex<VectorIndex> β†’ RwLock<VectorIndex> for read-heavy workload. Multiple concurrent recalls share read lock. Embedder remains Mutex (ONNX tokenizer requires &mut self) (#209, PR #260)

Fixed

  • Vector index consistency β€” Atomic save for .keys sidecar file (temp + rename). insert() and build() now return Result for error propagation (#139, PR #263)
  • FTS5 BM25 score conversion β€” Negative unbounded BM25 values were always clamped to 0.0. Fixed to proper sigmoid-based normalization (PR #264)
  • RRF normalization β€” .min(1.0) β†’ .clamp(0.0, 1.0) with clearer math (PR #264)
  • memories.remove().unwrap() β€” Replaced with .expect() for meaningful panic message (PR #264)
  • Server-mode metadata support β€” remember via HTTP API now includes entity, category, and meta in request body (PR #264)
  • Clippy collapsible_else_if β€” 2 pre-existing warnings fixed (PR #260)

Changed

  • Repository transferred β€” ajianaz/uteke β†’ codecoradev/uteke. All references updated across 16 files
  • Cora Review CI β€” switched from local Infisical OIDC action to codecoradev/cora-review-action@v1 with GitHub Secrets. Removed .cora.yaml project config
  • README simplified β€” 400 β†’ 97 lines. Detailed content moved to VitePress docs (docs/architecture.md, docs/cli-reference.md, etc.)
  • Roadmap cleaned β€” consolidated old versions, removed speculative Phase B/C phases
  • CONTRIBUTING.md β€” added Cora CLI integration docs, CI checks table, architecture updated to 3 crates, Key Design Decisions section
  • AGENT.md β€” new file with persistent AI agent context: critical rules, architecture, lessons learned, proven workflow
  • docs/architecture.md β€” new VitePress page with system overview, data flow diagrams, performance benchmarks, design decisions
  • docs/roadmap.md β€” v0.0.12 section added, old versions consolidated, "What's Next" list
  • Star History chart added to README (cora-cli + uteke)

πŸ“¦ Binaries

Each archive contains two binaries:

  • uteke β€” CLI tool
  • uteke-serve β€” HTTP server daemon
Platform File
Linux (x86_64) uteke-v0.0.13-x86_64-unknown-linux-gnu.tar.gz
Linux (ARM64) uteke-v0.0.13-aarch64-unknown-linux-gnu.tar.gz
macOS (Apple Silicon) uteke-v0.0.13-aarch64-apple-darwin.tar.gz
Windows (x86_64) uteke-v0.0.13-x86_64-pc-windows-msvc.zip

πŸš€ Quick Start

# Quick install (Linux / macOS)
curl -fsSL https://raw.githubusercontent.com/codecoradev/uteke/main/install.sh | sh

# Pin a specific version
UTEKE_VERSION=v curl -fsSL https://raw.githubusercontent.com/codecoradev/uteke/main/install.sh | sh

# Store a memory
uteke remember "Important context" --tags project

# Recall by meaning
uteke recall "what was that context?"

# Start server for fast AI agent access
uteke-serve --port 8767

Full changelog: https://github.com/codecoradev/uteke/blob/main/CHANGELOG.md