v0.3.1 - Shared-memory docs and Gemini CLI rollout

Patch release for cross-client continuity documentation and Gemini CLI support.\n\nHighlights:\n- document shared local project memory handoffs across Codex and Gemini CLI\n- add Gemini CLI client integration guidance, smoke coverage, and ready fixture\n- update live client tiers so server_info/self_test include Gemini CLI\n- refresh release-facing install/version references to v0.3.1

v0.3.0

Highlights

• Added version-aware markdown and retrieval manifests with automatic rebuilds when derived indexes become stale after an upgrade.
• Added persistent usage telemetry outside project/global memory, including estimated byte/token savings, milestone headlines, and optional USD estimates when TQMEMORY_INPUT_COST_PER_1M_TOKENS_USD is configured.
• Hardened retrieval behavior with project-safe default scope, stale freshness detection, removed-root pruning, incremental sync with full-sync fallback, Unicode-aware lexical fallback, and cached server_info() storage snapshots.
• Refreshed README, smoke coverage, and client rollout examples for v0.3.0.

Verification

• uv run ruff check src tests scripts
• uv run pytest -q
• uv run python scripts/smoke_test.py

v0.2.4 - Knowledge-base linting and release refresh

Highlights

• Added new MCP tool: lint_knowledge_base(...) for markdown knowledge-base hygiene checks.
• Added deterministic lint diagnostics for broken internal links, orphan candidates, duplicate normalized titles, and Obsidian-style wikilinks.
• Extended server/tool contracts and self-test catalog to include the new lint tool.
• Added dedicated lint test coverage and updated smoke flow to validate lint behavior end-to-end.

Documentation

• Updated README files in English, Ukrainian, and Russian.
• Updated technical specs and client smoke checklists for the new tool and updated install commands.

Versioning

• Bumped package version from 0.2.3 to 0.2.4.

v0.2.3

Turbo Quant Memory v0.2.3

• splits user-facing repository docs into clean English, Ukrainian, and Russian files instead of mixed bilingual pages
• adds localized versions of Memory Strategy, Technical Specification, Client Integrations, benchmark report, and client smoke checklist
• refreshes benchmark artifacts against the new 17-file documentation corpus and keeps the readable summary SVG layout in the generator
• bumps the package and install contract to v0.2.3 and updates tests, examples, and release-facing commands accordingly

v0.2.2

Turbo Quant Memory v0.2.2

• fixes package metadata so the published package version now matches the Git tag, install contract, and server version
• keeps the v0.2.1 memory hygiene, agent instruction, benchmark, and SVG fixes intact
• is the recommended release for installation and agent rollout

v0.2.1

Turbo Quant Memory v0.2.1

• improves default memory hygiene by skipping low-signal folders such as .planning, .serena, and generated benchmark reports during project-root indexing
• adds explicit Codex and Claude Code memory workflow instructions through AGENTS.md and CLAUDE.md
• cleans README benchmark snapshots and localized install docs
• fixes overflow in localized README hero SVG assets
• refreshes benchmark artifacts and keeps the release install contract pinned to v0.2.1

v0.2.0

Highlights

• Added note lifecycle management with deprecate_note for stale or superseded memory
• semantic_search now stays focused on active knowledge while preserving historical audit trail
• Updated English, Russian, and Ukrainian README files with clearer setup and stale-memory guidance
• Added visual benchmark SVG summaries and refreshed benchmark artifacts
• Updated smoke validation and Codex startup timeout guidance

Validation

• uv run pytest -q
• uv run python scripts/smoke_test.py
• uv run python scripts/benchmark_context_savings.py

v0.1.0

Turbo Quant Memory for AI Agents v0.1.0

Highlights

• Shipped the Phase 5 retrieval surface with explicit hydrate(...) support.
• Added typed write-back for decision, lesson, handoff, and pattern notes.
• Added storage stats and freshness reporting in server_info().
• Added client fixtures for Claude Code, Codex, Cursor, OpenCode, and Antigravity.
• Split the public project documentation into separate English, Russian, and Ukrainian README files.
• Added a reproducible benchmark script and committed the latest benchmark report.

Install

uv tool install git+https://github.com/Lexus2016/turbo_quant_memory@v0.1.0
turbo-memory-mcp serve

Fallback:

python -m pip install git+https://github.com/Lexus2016/turbo_quant_memory@v0.1.0
turbo-memory-mcp serve

Benchmarks

Measured on the repository corpus committed in this release:

• 117 Markdown files
• 1015 indexed blocks
• 17.11 s full index
• 2.32 s idle incremental index
• 78.39% average byte savings with semantic_search only
• 66.46% average byte savings with semantic_search + hydrate(top1)
• 83.25% average word savings with semantic_search only
• 74.98% average word savings with semantic_search + hydrate(top1)

Benchmark method:

• Baseline without MCP guidance: open the full source text of every unique Markdown file represented in the top-5 project search hits.
• Compact MCP path: use the semantic_search response only.
• Guided MCP path: use semantic_search and then hydrate for the top Markdown hit.

Verification

• uv run pytest -q
• uv run python scripts/smoke_test.py
• uv run python scripts/benchmark_context_savings.py