aivectormemory 2.2.4

轻量级 MCP Server，为 AI 编程助手提供跨会话持久记忆能力

🌐 简体中文 | 繁體中文 | English | Español | Deutsch | Français | 日本語

AIVectorMemory

More than memory — Memory + Issue Tracking + Task Management, an all-in-one AI development workflow engine

---

Other AI memory tools (mem0, Cline Memory Bank, etc.) only do one thing: store and retrieve memories. AI remembers the context, then what? Bugs go untracked, dev tasks go unmanaged, progress is lost when switching sessions, and rules you wrote get ignored anyway. Memory is just the starting point, not the finish line.

AIVectorMemory is the only MCP Server that combines memory, issue tracking, and task management in one. Semantic search with precise recall (search "database timeout" and find "MySQL connection pool pitfall"), built-in track issue tracking + task task management so AI runs the full dev workflow automatically, status cross-session state sync that never loses progress, and Hooks that enforce your workflow rules. One-click install across 10 IDEs, all data stored locally with zero cloud dependency.

✨ Core Features

What others don't have:

Unique Capability	Description	Does mem0 / Cline MB have it?
🔗 Issue Tracking (track)	Bug found → investigate → fix → test → archive, full lifecycle management	❌ Neither has it
📋 Task Management (task)	requirements → design → tasks, multi-step requirements auto-split and executed	❌ Neither has it
📡 Cross-Session State (status)	Block state, current task, progress — never lost when switching sessions	❌ Neither has it
🛡️ Hooks Rule Enforcement	bash_guard / stop_guard / check_track, hard-block rule violations	❌ Neither has it

Core capabilities also leading:

Feature	Description
🧠 Cross-Session Memory	Pitfalls, decisions, conventions — all persist across sessions
🔍 Semantic Search	Vector similarity matching, precise recall even with different wording
💰 Save 50%+ Tokens	On-demand retrieval loads only relevant memories, no more bulk injection
🏠 Fully Local	ONNX local inference, zero cloud dependency, data never leaves your machine
🔌 10 IDEs	Cursor / Kiro / Claude Code / Windsurf / VSCode / Copilot / OpenCode / Trae / Codex / Gemini CLI
📊 Desktop App + Web Dashboard	Visual management for memories and tasks, 3D vector network reveals knowledge connections
🔄 Smart Dedup	Similarity > 0.95 auto-merges, memory store stays clean forever
🌐 7 Languages	简体中文 / 繁體中文 / English / Español / Deutsch / Français / 日本語

QQ群：1085682431  |  微信：changhuibiz
共同参与项目开发加QQ群或微信交流

Login

Project Selection

Overview & Vector Network

🏗️ Architecture

┌─────────────────────────────────────────────────┐
│                   AI IDE                         │
│  OpenCode / Codex / Claude Code / Cursor / ...  │
└──────────────────────┬──────────────────────────┘
                       │ MCP Protocol (stdio)
┌──────────────────────▼──────────────────────────┐
│              AIVectorMemory Server               │
│                                                  │
│  ┌──────────┐ ┌──────────┐ ┌──────────────────┐ │
│  │ remember │ │  recall   │ │   auto_save      │ │
│  │ forget   │ │  task     │ │   status/track   │ │
│  └────┬─────┘ └────┬─────┘ └───────┬──────────┘ │
│       │            │               │             │
│  ┌────▼────────────▼───────────────▼──────────┐  │
│  │         Embedding Engine (ONNX)            │  │
│  │      intfloat/multilingual-e5-small        │  │
│  └────────────────────┬───────────────────────┘  │
│                       │                          │
│  ┌────────────────────▼───────────────────────┐  │
│  │     SQLite + sqlite-vec (Vector Index)     │  │
│  │     ~/.aivectormemory/memory.db            │  │
│  └────────────────────────────────────────────┘  │
└──────────────────────────────────────────────────┘

🚀 Quick Start

Option 1: pip install (Recommended)

# Install
pip install aivectormemory

# Upgrade to latest version
pip install --upgrade aivectormemory

# Navigate to your project directory, one-click IDE setup
cd /path/to/your/project
avmrun install

avmrun install interactively guides you to select your IDE, auto-generating MCP config, Steering rules, and Hooks — no manual setup needed.

macOS users note:

• If you get externally-managed-environment error, add --break-system-packages
• If you get enable_load_extension error, your Python doesn't support SQLite extension loading (macOS built-in Python and python.org installers don't support it). Use Homebrew Python instead:

  brew install python
  /opt/homebrew/bin/python3 -m pip install aivectormemory
  

Option 2: uvx (zero install)

No pip install needed, run directly:

cd /path/to/your/project
uvx aivectormemory install

Requires uv to be installed. uvx auto-downloads and runs the package — no manual installation needed.

Option 3: Manual configuration

{
  "mcpServers": {
    "aivectormemory": {
      "command": "run",
      "args": ["--project-dir", "/path/to/your/project"]
    }
  }
}

📍 IDE Configuration File Locations

IDE	Config Path
Kiro	.kiro/settings/mcp.json
Cursor	.cursor/mcp.json
Claude Code	.mcp.json
Windsurf	.windsurf/mcp.json
VSCode	.vscode/mcp.json
Trae	.trae/mcp.json
OpenCode	opencode.json
Codex	.codex/config.toml

For Codex, use project-scoped TOML instead of JSON:

[mcp_servers.aivectormemory]
command = "run"
args = ["--project-dir", "/path/to/your/project"]

Codex only loads project-scoped .codex/config.toml after the repository is marked as a trusted project.

🛠️ 8 MCP Tools

remember — Store a memory

content (string, required)   Memory content in Markdown format
tags    (string[], required)  Tags, e.g. ["pitfall", "python"]
scope   (string)              "project" (default) / "user" (cross-project)

Similarity > 0.95 auto-updates existing memory, no duplicates.

recall — Semantic search

query   (string)     Semantic search keywords
tags    (string[])   Exact tag filter
scope   (string)     "project" / "user" / "all"
top_k   (integer)    Number of results, default 5

Vector similarity matching — finds related memories even with different wording.

forget — Delete memories

memory_id  (string)     Single ID
memory_ids (string[])   Batch IDs

status — Session state

state (object, optional)   Omit to read, pass to update
  is_blocked, block_reason, current_task,
  next_step, progress[], recent_changes[], pending[]

Maintains work progress across sessions, auto-restores context in new sessions.

track — Issue tracking

action   (string)   "create" / "update" / "archive" / "list"
title    (string)   Issue title
issue_id (integer)  Issue ID
status   (string)   "pending" / "in_progress" / "completed"
content  (string)   Investigation content

task — Task management

action     (string, required)  "batch_create" / "update" / "list" / "delete" / "archive"
feature_id (string)            Linked feature identifier (required for list)
tasks      (array)             Task list (batch_create, supports subtasks)
task_id    (integer)           Task ID (update)
status     (string)            "pending" / "in_progress" / "completed" / "skipped"

Links to spec docs via feature_id. Update auto-syncs tasks.md checkboxes and linked issue status.

readme — README generation

action   (string)    "generate" (default) / "diff" (compare differences)
lang     (string)    Language: en / zh-TW / ja / de / fr / es
sections (string[])  Specify sections: header / tools / deps

Auto-generates README content from TOOL_DEFINITIONS / pyproject.toml, multi-language support.

auto_save — Auto save preferences

preferences  (string[])  User-expressed technical preferences (fixed scope=user, cross-project)
extra_tags   (string[])  Additional tags

Auto-extracts and stores user preferences at end of each conversation, smart dedup.

📊 Web Dashboard

avmrun web --port 9080
avmrun web --port 9080 --quiet          # Suppress request logs
avmrun web --port 9080 --quiet --daemon  # Run in background (macOS/Linux)

Visit http://localhost:9080 in your browser. Default username admin, password admin123 (can be changed in settings after first login).

• Multi-project switching, memory browse/search/edit/delete/export/import
• Semantic search (vector similarity matching)
• One-click project data deletion
• Session status, issue tracking
• Tag management (rename, merge, batch delete)
• Token authentication protection
• 3D vector memory network visualization
• 🌐 Multi-language support (简体中文 / 繁體中文 / English / Español / Deutsch / Français / 日本語)

    
Scan to join WeChat group  |  Scan to join QQ group

⚡ Pairing with Steering Rules

AIVectorMemory is the storage layer. Use Steering rules to tell AI when and how to call these tools.

Running avmrun install auto-generates Steering rules and Hooks config — no manual setup needed.

IDE	Steering Location	Hooks
Kiro	.kiro/steering/aivectormemory.md	.kiro/hooks/*.hook
Cursor	.cursor/rules/aivectormemory.md	.cursor/hooks.json
Claude Code	CLAUDE.md (appended)	.claude/settings.json
Windsurf	.windsurf/rules/aivectormemory.md	.windsurf/hooks.json
VSCode	.github/copilot-instructions.md (appended)	.claude/settings.json
Trae	.trae/rules/aivectormemory.md	—
OpenCode	AGENTS.md (appended)	.opencode/plugins/*.js
Codex	AGENTS.md (appended)	—

📋 Steering Rules Example (auto-generated)

# AIVectorMemory - Workflow Rules

## ⚠️ Message Type Judgment
Classify → casual chat: reply directly; issue/bug: track create → Issue Tracking flow; multi-step feature: Spec flow

## ⚠️ Issue Tracking Flow
1. track create → 2. investigate (recall + read code) → 3. present solution, set block
→ 4. user confirms, modify code → 5. run tests + grep side effects → 6. track update
→ 7. set block for verification → 8. user confirms, track archive

## ⚠️ Task Management Flow (Spec)
1. track create → 2. create spec dir → 3. requirements.md → 4. design.md → 5. tasks.md
→ 6. task batch_create → 7. execute subtasks in order → 8. full self-test, set block

## ⚠️ Blocking Rules / Self-Test Standards / Development Standards
(Full rules auto-generated by `avmrun install`)

🔗 Hooks Config Example (Kiro only, auto-generated)

Auto-save on session end removed. Dev workflow check (.kiro/hooks/dev-workflow-check.kiro.hook):

{
  "enabled": true,
  "name": "Dev Workflow Check",
  "version": "1",
  "when": { "type": "promptSubmit" },
  "then": {
    "type": "askAgent",
    "prompt": "Core principles: verify before acting, no blind testing, only mark done after tests pass"
  }
}

🇨🇳 Users in China

The embedding model (~200MB) is auto-downloaded on first run. If slow:

export HF_ENDPOINT=https://hf-mirror.com

Or add env to MCP config:

{
  "env": { "HF_ENDPOINT": "https://hf-mirror.com" }
}

📦 Tech Stack

Component	Technology
Runtime	Python >= 3.10
Vector DB	SQLite + sqlite-vec
Embedding	ONNX Runtime + intfloat/multilingual-e5-small
Tokenizer	HuggingFace Tokenizers
Protocol	Model Context Protocol (MCP)
Web	Native HTTPServer + Vanilla JS

📋 Changelog

v2.2.3

Enhancement: Rules restructure — streamlined workflow with clear flow separation

• 📝 Restructured from 19 numbered sections to 9 clean topic-based sections (no numbering)
• 📝 Separated Issue Tracking flow (8 steps) and Task Management / Spec flow (8 steps)
• 📝 Added Self-Test Standards as standalone section with clear test method selection
• 📝 Hooks injection (inject-workflow-rules.sh) streamlined — removed IDE Safety, post-edit checklist, violation examples
• 📝 check_track hook: non-code files (.md/.sh/.json/.yaml etc.) now bypass track-issue check
• 🌐 All 7 languages synchronized

v2.2.2

Enhancement: Rule numbering overhaul — A-I → 1-19 flat numbering

• 📝 All 19 rules now use flat numeric numbering (1-19), no more A-I letter substeps
• 📝 Issue tracking field specs merged into steps 7/8/11.4/13 (removed standalone section)
• 📝 Self-test duplicate removed from Development Standards (now only in section 11)
• 📝 G1-G4 checklist strengthened: "execute immediately, don't wait for user reminder"
• 🌐 All 7 languages synchronized

v2.2.1

Hotfix: Remove git commit/push hard-block + Expand manual-operation detection

• 🐛 Fixed bash_guard blocking git commit/git push with exit 2 — users couldn't commit even when explicitly requested. Git operations now governed by steering rules + stop_guard post-check only
• 🛡️ Expanded stop_guard manual-operation word list — shorter substrings (请用/请你/验证一下/please verify) to catch AI phrasing variants
• 📝 Strengthened G1-G4 checklist wording: "execute immediately, don't wait for user reminder"

v2.2.0

Major: Universal Hooks — 8 IDEs, 7 Languages, Cross-Platform, Auto-Upgrade

• 🛡️ Hooks migrated from .sh scripts to Python modules (python3 -m aivectormemory.hooks.xxx) — cross-platform (macOS/Linux/Windows), auto-upgrades via pip
• 🛡️ bash_guard expanded to 7 rules: + git commit blocking + git push blocking + deploy command blocking (ssh/docker/kubectl/systemctl)
• 🛡️ stop_guard expanded to 7 checks: + backend test detection (pytest/curl) + grep side-effect check + track update verification + status blocking verification
• 🌐 All hook error messages now support 7 languages (zh-CN/zh-TW/en/ja/de/fr/es) via _messages.py
• 🔌 bash_guard deployed to all IDEs: Cursor (bash matcher), Windsurf (pre_run_command), Kiro (shell preToolUse), Codex CLI, Copilot (VSCode+Cloud), Gemini CLI
• 🆕 New IDE support: Codex CLI (.codex/hooks.json), GitHub Copilot (.github/hooks/), Gemini CLI (.gemini/settings.json)
• 🔄 Auto-upgrade: pip install --upgrade updates hook logic instantly — no re-install needed
• ✅ Test suite: 48 → 114 tests (66 hooks tests covering all rules, cross-IDE format compatibility, i18n message validation)

v2.1.11

Fix: Desktop memory delete + Web dashboard batch delete

• 🐛 Fixed desktop app memory delete not working — replaced native confirm() (unsupported in Wails WebView) with custom Modal component
• ✨ Added batch delete UI to Web dashboard memory pages (project + global) — batch mode button, checkbox selection, select all, batch delete with confirmation
• 🌐 Added batch delete i18n keys across all 7 languages

v2.1.10

Enhancement: Self-correction rule — AI must fix its own mistakes without asking

• 📝 Core principle #5 enhanced across all 7 languages: "Your own operational mistakes must be self-corrected — never ask the user whether to fix them"

v2.1.9

Enhancement: Hook-Based Rule Enforcement — Bash Guard + Stop Guard + Test Decision Tree

• 🛡️ New bash_guard.sh (PreToolUse Bash): blocks open http (must use Playwright MCP), multiline python3 -c, $()+pipe combos, mysql -e multi-statements
• 🛡️ New stop_guard.sh (Stop hook): parses transcript to detect — code edited without Playwright verification + response contains "manual operation" words. AI must either use Playwright or explicitly state "this change does not affect frontend pages"
• 🎯 Testing decision tree added to G1 rule across all 7 languages: choose test method based on impact scope (frontend code → Playwright, API affecting pages → curl + Playwright, pure backend → pytest/curl, unsure → Playwright)
• 🔧 Removed _cleanup_legacy_playwright (no longer deletes existing Playwright config on re-install)
• 🔧 Playwright MCP install default changed from N to Y
• 🔧 Self-test rules enhanced: must use ToolSearch to load Playwright MCP from deferred tools, never assume tools unavailable

v2.1.8

Enhancement: Steering Rules Restoration — More Detailed Workflow Steps + Anti-Skip Safeguard

• 📝 Restored detailed workflow steps from pre-simplification version (steps C/D/E/F/I with explicit recall formats, investigation checkpoints, interrupt handling)
• 🛡️ New safeguard rule: when user mentions negative words ("wrong/not working/missing/error"), default to track create — AI can no longer self-judge "by design" and skip recording
• ⚠️ All 11 section headers now prefixed with ⚠️ for higher attention priority
• 🌐 Section 1 unified to IDENTITY & TONE with English field keys (Role/Language/Voice/Authority) across all 7 languages
• 🔧 Fixed _write_steering anchor to support flexible section header formats

v2.1.7

Fix: Playwright MCP Config — No Longer Force-Injected

• 🔧 Playwright MCP config is now opt-in during install (prompted only when npx is available, default: No)
• 🩹 install auto-cleans legacy Playwright configs written by older versions — fixes OpenCode "mcp.playwright: Invalid input" crash
• 🗑️ Removed auto_repair_playwright_config from server startup (unreachable when config validation fails)
• ➕ Added avmrun as a short CLI alias (avmrun install, avmrun web, etc.)

v2.1.6

Fix: CLI Entry Point Renamed

• 🔧 Renamed CLI entry point from run to aivectormemory — uvx aivectormemory now works directly without --from workaround
• ♻️ Updated argparse prog name and install runner config to match

v2.1.5

Fix: Playwright MCP Config Compatibility

• 🔧 Fixed mcp.playwright: Invalid input error on OpenCode after upgrade — _build_playwright_config was missing OpenCode format handling (missing type: local + array command)
• ♻️ Refactored _build_playwright_config to reuse _build_config format logic — eliminates duplicate if-else branches, automatically adapts to all IDE formats
• 🩹 Added auto_repair_playwright_config: MCP server auto-detects and fixes incorrect Playwright config on startup — seamless upgrade, no manual reinstall needed

v2.1.4

Fix: Superseded Memory Visibility

• 🔓 Removed hard filter that completely hid superseded memories from recall results — previously exclude_superseded=true (default) blocked memories before scoring, making them permanently invisible
• 📊 Superseded memories now ranked naturally via importance reduction (×0.3) + sqrt(importance) scoring — they appear lower in results instead of disappearing entirely
• 🧹 Removed _load_superseded_ids function and related dead code

v2.1.3

Fix: Scoring Engine Overhaul

• 🧮 Fixed critical bug: composite score now uses original vector similarity instead of RRF rank score — previously a ~0.8 similarity was replaced by ~0.015 RRF score, destroying semantic relevance signal
• √ importance changed from direct multiplier to sqrt(importance) — reduces extreme penalty (0.15 → 0.387 instead of 0.15) while preserving supersede suppression
• 🛡️ Similarity floor: memories with similarity ≥ 0.85 get a guaranteed minimum score, preventing high-relevance memories from being buried by low importance
• ⚖️ Rebalanced weights: similarity 0.55 (was 0.5), recency 0.30, frequency 0.15 (was 0.2) — semantic relevance now dominates ranking
• 📉 FTS-only fallback reduced from 0.5 to 0.3 — pure keyword matches no longer get inflated similarity scores

v2.1.2

Fix: Memory Recall Accuracy

• 🔍 Fixed tiered search greedy cutoff: long_term results previously blocked short_term memories from being searched, causing highly relevant memories to be invisible
• 🔧 Both tiers now searched simultaneously, ranked by composite score (similarity × recency × frequency × importance)
• 🛡️ Fixed filters dict mutation bug in _search_tier — original filters no longer modified by reference

v2.1.1

Enhancement: AI Rule System Upgrade

• 📋 CLAUDE.md completion: added Identity & Tone (§1), 7 Core Principles (§3), message type judgment examples, expanded IDE safety and self-test sections
• ⚠️ Hook added Common Violations Reminder: ❌ negative examples reinforcing the 4 most frequently missed rules (self-test, recall, track create, IDE safety)
• 🌐 All 7 language rule files updated in sync (zh-CN/zh-TW/en/ja/es/de/fr)
• 🔢 CLAUDE.md sections renumbered to §1–§11, cross-references updated accordingly

v2.1.0

New: Smart Memory Engine + Uninstall

• 🧠 FTS5 full-text search with Chinese tokenization (jieba) — keyword search now actually works for CJK content
• 🔀 Hybrid retrieval: vector + FTS5 dual-path with RRF (Reciprocal Rank Fusion) merging
• 📊 Composite scoring: results ranked by similarity × 0.5 + recency × 0.3 + frequency × 0.2, weighted by importance
• ⚡ Conflict detection: similar memories (0.85–0.95) auto-superseded, old facts fade automatically
• 📦 Memory tiers: frequently accessed memories auto-promote to long_term and get searched first
• 🗑️ Auto-archive: stale short_term memories (90 days inactive + low importance) cleaned up automatically
• 🔗 Relation expansion: tag overlap ≥ 2 builds related links, 1-hop expansion surfaces connected memories
• 📝 Auto-summary: long memories (>500 chars) get summaries, brief mode returns summaries to save tokens
• 🧹 Code cleanup: removed 15 dead code items, refactored 7 duplicate patterns into shared utilities
• ❌ avmrun uninstall — cleanly removes all IDE configurations (MCP, steering, hooks, permissions) while preserving memory data

v2.0.9

Enhancement: Security & Rule Optimization

• 🔒 Fixed SQL injection, command injection, and path traversal vulnerabilities
• 🛡️ Added transaction protection for data integrity (archive, insert, update operations)
• 🧠 Unified similarity formula across all search paths
• 📏 Compressed AI workflow rules by 38% (219→136 lines) with zero process removal
• 🧹 v12 migration cleans up legacy garbage memories automatically
• 🌐 All 7 languages synchronized

v2.0.8

New: Playwright Browser Testing Built-in

• 🎭 avmrun install now automatically configures Playwright browser testing — AI can open a real browser to verify frontend changes instead of guessing
• 🎭 Uses a dedicated test browser (Chrome for Testing) that won't interfere with your personal browser tabs
• 🔑 Simplified permission setup — no more manual permission popups for common tools
• 📏 Updated AI rules across all 7 languages to enforce proper browser testing behavior

v2.0.7

Enhancement: More IDE Support

• 🖥️ Added support for Antigravity and GitHub Copilot IDEs
• 🔑 avmrun install now auto-configures tool permissions, reducing manual setup
• 📏 Streamlined AI self-testing rules

v2.0.6

Enhancement: Faster Startup

• ⚡ Optimized memory loading on session start — loads faster with less context usage
• 🔑 Auto-configures Claude Code permissions during installation
• 🌐 All 7 languages synchronized

v2.0.5

Enhancement: Simpler Rules

• 📏 AI workflow rules restructured for clarity and reduced token usage
• 💾 AI now automatically saves your preferences at the end of each session
• 🌐 All 7 languages synchronized

v2.0.4

Fix: Tool Reliability

• 🔧 Comprehensive audit and fix of all MCP tool parameters — improved reliability across all IDEs

v2.0.3

Enhancement: Better Search & Safety

• 🔍 Memory search now combines semantic and keyword matching for more accurate recall
• 🛡️ Added cross-project protection — AI won't accidentally modify files in other projects

v2.0.2

Enhancement: Rule Generalization & Desktop Version Fix

• 📏 Added "recall before asking user" rule — AI must query memory system before asking user for project information (server address, passwords, deploy config, etc.)
• 📏 Generalized pre-operation check rule — removed specific examples to apply to all operation scenarios
• 🖥️ Fixed desktop app settings page showing hardcoded version "1.0.0" instead of actual app version
• 🌐 All 7 language i18n steering rules and workflow prompts synchronized

v2.0.1

Fix: Hook Cross-Project Compatibility

• 🔧 check_track.sh now derives project path from script location instead of $(pwd), fixing track detection failure when Claude Code runs hooks from non-root working directory
• 🔧 compact-recovery.sh now uses relative path derivation instead of hardcoded absolute paths, ensuring correct behavior when installed to any project
• 🔧 Removed redundant CLAUDE.md re-injection from compact-recovery (already auto-loaded by Claude Code)
• 🔧 install.py template synchronized with all hook fixes
• 🌐 All 7 language i18n compact-recovery hints updated

v2.0

Performance: ONNX INT8 Quantization

• ⚡ Embedding model auto-quantized from FP32 to INT8 on first load, model file from 448MB down to 113MB
• ⚡ MCP Server memory usage reduced from ~1.6GB to ~768MB (50%+ reduction)
• ⚡ Quantization is transparent to users — automatic on first use, cached for subsequent loads, falls back to FP32 on failure

New: Remember Password

• 🔐 Login page on both desktop and web dashboard now has a "Remember password" checkbox
• 🔐 When checked, credentials are saved to localStorage and auto-filled on next login; when unchecked, saved credentials are cleared
• 🔐 Checkbox is hidden in registration mode

Enhancement: Steering Rules

• 📝 IDENTITY & TONE section strengthened with more specific constraints (no pleasantries, no translating user messages, etc.)
• 📝 Self-testing requirements now distinguish between backend-only, MCP Server, and frontend-visible changes (Playwright required for frontend)
• 📝 Development rules now mandate self-testing after completing development
• 📝 All 7 language versions synchronized

v1.0.11

• 🐛 Desktop app version comparison switched to semantic versioning, fixing false upgrade prompts when local version is higher
• 🐛 Health check page field names aligned with backend, fixing consistency status always showing Mismatch
• 🔧 check_track.sh hook adds Python fallback, resolving silent hook failure when system sqlite3 is unavailable (#4)

v1.0.10

• 🖥️ Desktop app one-click install + upgrade detection
• 🖥️ Auto-detect Python and aivectormemory installation status on startup
• 🖥️ Show one-click install button when not installed, check PyPI and desktop new versions when installed
• 🐛 Installation detection switched to importlib.metadata.version() for accurate package version

v1.0.8

• 🔧 Fix PyPI package size anomaly (sdist from 32MB down to 230KB), excluded accidentally packaged dev files

v1.0.6

New: Native Desktop App

• 🖥️ Native desktop client supporting macOS (ARM64), Windows (x64), Linux (x64)
• 🖥️ Desktop app shares the same database as Web dashboard, fully feature-equivalent
• 🖥️ Dark/light theme switching, Glass frosted visual style
• 🖥️ Login auth, project selection, stats overview, memory management, issue tracking, task management, tag management, settings, data maintenance — full feature coverage
• 📦 Auto-published installers via GitHub Releases, download and use

New: CI/CD Auto Build

• 🔄 GitHub Actions auto-builds desktop installers for all 3 platforms
• 🔄 Push a tag to trigger the full compile, package, and release pipeline

Fixes

• 🐛 Windows platform compatibility fixes
• 🐛 sqlite-vec extension download URL fix

v1.0.5

Optimization: Token Usage Reduction

• ⚡ Steering rules changed from per-message dynamic injection to static loading, reducing repeated token consumption
• ⚡ Greatest impact for Claude Code users — ~2K fewer tokens per message

v1.0.4

New: Full-Stack i18n (7 Languages)

• 🌐 Web dashboard + desktop UI fully supports 7 languages: 简体中文 / 繁體中文 / English / Español / Deutsch / Français / 日本語
• 🌐 One-click language switch in settings page, takes effect immediately
• 🌐 MCP tool responses follow language setting, AI replies automatically use the corresponding language
• 🌐 Switching language auto-regenerates steering rules for all installed projects

New: Web Dashboard Settings Page

• ⚙️ Language switch, theme settings, system info display
• ⚙️ Database health check, repair, backup and other maintenance tools

v1.0.3

Optimization: Memory Search

• 🔍 recall search supports OR/AND tag matching modes, fixing missed results with multi-tag searches
• 🔍 Semantic search + tag filter defaults to OR matching (broader), tags-only browsing keeps AND matching (more precise)

📋 v0.2.x and earlier changelog

See CHANGELOG-archive.md

License

Apache-2.0