Skip to content

This release adds 8 notable features for engineering teams evaluating rollout.

Published 2mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Hybrid search with semantic and keyword capabilities, reranking results.

Full changelog

First major release with comprehensive MCP toolset.

Highlights

  • 28 MCP tools for Claude Desktop
  • 173 tests with GitHub Actions CI
  • Hybrid search — semantic + keyword with reranking
  • Cross-session memory — remember, recall, tag, export/import
  • Auto-sync — background file watcher re-indexes on changes
  • Search analytics — query tracking, zero-result detection
  • Document freshness — stale document detection by project
  • Health check — comprehensive workspace diagnostics
  • Knowledge graph — Mermaid diagram of document relationships

What's new since v0.4.0

  • 13 new tools (unified_search, find_similar, memory_tags, search_by_tag, export/import_memories, search_analytics, check_document_freshness, health_check, tessera_status, list_memories, forget_memory)
  • Config externalization to workspace.yaml
  • Query suggestions on zero results (Korean + English)
  • Search result caching + embedding LRU cache
  • Content hash deduplication
  • File watcher auto-sync (30s poll, 5s debounce)
  • CLI: tessera init/ingest/sync/status/check/version

Install

git clone https://github.com/besslframework-stack/project-tessera.git
cd project-tessera
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
tessera init

Full changelog: https://github.com/besslframework-stack/project-tessera/blob/main/CHANGELOG.md

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track besslframework-stack/project-tessera

Get notified when new releases ship.

Sign up free

About besslframework-stack/project-tessera

Local workspace memory for Claude Desktop. Indexes your documents (Markdown, CSV, session logs) into a vector store with hybrid search, cross-session memory, auto-learn, and knowledge graph visualization. Zero external dependencies — fastembed + LanceDB, no Ollama or Docker required. 15 MCP tools.

All releases →

Beta — feedback welcome: [email protected]