Alex Newman
f38b5b85bc
* docs: add investigation reports for 5 open GitHub issues Comprehensive analysis of issues #543, #544, #545, #555, and #557: - #557: settings.json not generated, module loader error (node/bun mismatch) - #555: Windows hooks not executing, hasIpc always false - #545: formatTool crashes on non-JSON tool_input strings - #544: mem-search skill hint shown incorrectly to Claude Code users - #543: /claude-mem slash command unavailable despite installation Each report includes root cause analysis, affected files, and proposed fixes. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(logger): handle non-JSON tool_input in formatTool (#545) Wrap JSON.parse in try-catch to handle raw string inputs (e.g., Bash commands) that aren't valid JSON. Falls back to using the string as-is. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(context): update mem-search hint to reference MCP tools (#544) Update hint messages to reference MCP tools (search, get_observations) instead of the deprecated "mem-search skill" terminology. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(settings): auto-create settings.json on first load (#557, #543) When settings.json doesn't exist, create it with defaults instead of returning in-memory defaults. Creates parent directory if needed. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(hooks): use bun runtime for hooks except smart-install (#557) Change hook commands from node to bun since hooks use bun:sqlite. Keep smart-install.js on node since it bootstraps bun installation. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore: rebuild plugin scripts * docs: clarify that build artifacts must be committed * fix(docs): update build artifacts directory reference in CLAUDE.md * test: add test coverage for PR #558 fixes - Fix 2 failing tests: update "mem-search skill" → "MCP tools" expectations - Add 56 tests for formatTool() JSON.parse crash fix (Issue #545) - Add 27 tests for settings.json auto-creation (Issue #543) Test coverage includes: - formatTool: JSON parsing, raw strings, objects, null/undefined, all tool types - Settings: file creation, directory creation, schema migration, edge cases 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(tests): clean up flaky tests and fix circular dependency Phase 1 of test quality improvements: - Delete 6 harmful/worthless test files that used problematic mock.module() patterns or tested implementation details rather than behavior: - context-builder.test.ts (tested internal implementation) - export-types.test.ts (fragile mock patterns) - smart-install.test.ts (shell script testing antipattern) - session_id_refactor.test.ts (outdated, tested refactoring itself) - validate_sql_update.test.ts (one-time migration validation) - observation-broadcaster.test.ts (excessive mocking) - Fix circular dependency between logger.ts and SettingsDefaultsManager.ts by using late binding pattern - logger now lazily loads settings - Refactor mock.module() to spyOn() in several test files for more maintainable and less brittle tests: - observation-compiler.test.ts - gemini_agent.test.ts - error-handler.test.ts - server.test.ts - response-processor.test.ts All 649 tests pass. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * refactor(tests): phase 2 - reduce mock-heavy tests and improve focus - Remove mock-heavy query tests from observation-compiler.test.ts, keep real buildTimeline tests - Convert session_id_usage_validation.test.ts from 477 to 178 lines of focused smoke tests - Remove tests for language built-ins from worker-spawn.test.ts (JSON.parse, array indexing) - Rename logger-coverage.test.ts to logger-usage-standards.test.ts for clarity 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * docs(tests): phase 3 - add JSDoc mock justification to test files Document mock usage rationale in 5 test files to improve maintainability: - error-handler.test.ts: Express req/res mocks, logger spies (~11%) - fallback-error-handler.test.ts: Zero mocks, pure function tests - session-cleanup-helper.test.ts: Session fixtures, worker mocks (~19%) - hook-constants.test.ts: process.platform mock for Windows tests (~12%) - session_store.test.ts: Zero mocks, real SQLite :memory: database Part of ongoing effort to document mock justifications per TESTING.md guidelines. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * test(integration): phase 5 - add 72 tests for critical coverage gaps Add comprehensive test coverage for previously untested areas: - tests/integration/hook-execution-e2e.test.ts (10 tests) Tests lifecycle hooks execution flow and context propagation - tests/integration/worker-api-endpoints.test.ts (19 tests) Tests all worker service HTTP endpoints without heavy mocking - tests/integration/chroma-vector-sync.test.ts (16 tests) Tests vector embedding synchronization with ChromaDB - tests/utils/tag-stripping.test.ts (27 tests) Tests privacy tag stripping utilities for both <private> and <meta-observation> tags All tests use real implementations where feasible, following the project's testing philosophy of preferring integration-style tests over unit tests with extensive mocking. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * context update * docs: add comment linking DEFAULT_DATA_DIR locations Added NOTE comment in logger.ts pointing to the canonical DEFAULT_DATA_DIR in SettingsDefaultsManager.ts. This addresses PR reviewer feedback about the fragility of having the default defined in two places to avoid circular dependencies. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
🇨🇳 中文 • 🇯🇵 日本語 • 🇧🇷 Português • 🇰🇷 한국어 • 🇪🇸 Español • 🇩🇪 Deutsch • 🇫🇷 Français 🇮🇱 עברית • 🇸🇦 العربية • 🇷🇺 Русский • 🇵🇱 Polski • 🇨🇿 Čeština • 🇳🇱 Nederlands • 🇹🇷 Türkçe • 🇺🇦 Українська • 🇻🇳 Tiếng Việt • 🇮🇩 Indonesia • 🇹🇭 ไทย • 🇮🇳 हिन्दी • 🇧🇩 বাংলা • 🇷🇴 Română • 🇸🇪 Svenska • 🇮🇹 Italiano • 🇬🇷 Ελληνικά • 🇭🇺 Magyar • 🇫🇮 Suomi • 🇩🇰 Dansk • 🇳🇴 Norsk
Persistent memory compression system built for Claude Code.
Quick Start • How It Works • Search Tools • Documentation • Configuration • Troubleshooting • License
Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.
Quick Start
Start a new Claude Code session in the terminal and enter the following commands:
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
Restart Claude Code. Context from previous sessions will automatically appear in new sessions.
Key Features:
- 🧠 Persistent Memory - Context survives across sessions
- 📊 Progressive Disclosure - Layered memory retrieval with token cost visibility
- 🔍 Skill-Based Search - Query your project history with mem-search skill
- 🖥️ Web Viewer UI - Real-time memory stream at http://localhost:37777
- 💻 Claude Desktop Skill - Search memory from Claude Desktop conversations
- 🔒 Privacy Control - Use
<private>tags to exclude sensitive content from storage - ⚙️ Context Configuration - Fine-grained control over what context gets injected
- 🤖 Automatic Operation - No manual intervention required
- 🔗 Citations - Reference past observations with IDs (access via http://localhost:37777/api/observation/{id} or view all in the web viewer at http://localhost:37777)
- 🧪 Beta Channel - Try experimental features like Endless Mode via version switching
Documentation
📚 View Full Documentation - Browse markdown docs on GitHub
Getting Started
- Installation Guide - Quick start & advanced installation
- Usage Guide - How Claude-Mem works automatically
- Search Tools - Query your project history with natural language
- Beta Features - Try experimental features like Endless Mode
Best Practices
- Context Engineering - AI agent context optimization principles
- Progressive Disclosure - Philosophy behind Claude-Mem's context priming strategy
Architecture
- Overview - System components & data flow
- Architecture Evolution - The journey from v3 to v5
- Hooks Architecture - How Claude-Mem uses lifecycle hooks
- Hooks Reference - 7 hook scripts explained
- Worker Service - HTTP API & Bun management
- Database - SQLite schema & FTS5 search
- Search Architecture - Hybrid search with Chroma vector database
Configuration & Development
- Configuration - Environment variables & settings
- Development - Building, testing, contributing
- Troubleshooting - Common issues & solutions
How It Works
Core Components:
- 5 Lifecycle Hooks - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
- Smart Install - Cached dependency checker (pre-hook script, not a lifecycle hook)
- Worker Service - HTTP API on port 37777 with web viewer UI and 10 search endpoints, managed by Bun
- SQLite Database - Stores sessions, observations, summaries
- mem-search Skill - Natural language queries with progressive disclosure
- Chroma Vector Database - Hybrid semantic + keyword search for intelligent context retrieval
See Architecture Overview for details.
MCP Search Tools
Claude-Mem provides intelligent memory search through 4 MCP tools following a token-efficient 3-layer workflow pattern:
The 3-Layer Workflow:
search- Get compact index with IDs (~50-100 tokens/result)timeline- Get chronological context around interesting resultsget_observations- Fetch full details ONLY for filtered IDs (~500-1,000 tokens/result)
How It Works:
- Claude uses MCP tools to search your memory
- Start with
searchto get an index of results - Use
timelineto see what was happening around specific observations - Use
get_observationsto fetch full details for relevant IDs - ~10x token savings by filtering before fetching details
Available MCP Tools:
search- Search memory index with full-text queries, filters by type/date/projecttimeline- Get chronological context around a specific observation or queryget_observations- Fetch full observation details by IDs (always batch multiple IDs)__IMPORTANT- Workflow documentation (always visible to Claude)
Example Usage:
// Step 1: Search for index
search(query="authentication bug", type="bugfix", limit=10)
// Step 2: Review index, identify relevant IDs (e.g., #123, #456)
// Step 3: Fetch full details
get_observations(ids=[123, 456])
See Search Tools Guide for detailed examples.
Beta Features
Claude-Mem offers a beta channel with experimental features like Endless Mode (biomimetic memory architecture for extended sessions). Switch between stable and beta versions from the web viewer UI at http://localhost:37777 → Settings.
See Beta Features Documentation for details on Endless Mode and how to try it.
System Requirements
- Node.js: 18.0.0 or higher
- Claude Code: Latest version with plugin support
- Bun: JavaScript runtime and process manager (auto-installed if missing)
- uv: Python package manager for vector search (auto-installed if missing)
- SQLite 3: For persistent storage (bundled)
Configuration
Settings are managed in ~/.claude-mem/settings.json (auto-created with defaults on first run). Configure AI model, worker port, data directory, log level, and context injection settings.
See the Configuration Guide for all available settings and examples.
Development
See the Development Guide for build instructions, testing, and contribution workflow.
Troubleshooting
If experiencing issues, describe the problem to Claude and the troubleshoot skill will automatically diagnose and provide fixes.
See the Troubleshooting Guide for common issues and solutions.
Bug Reports
Create comprehensive bug reports with the automated generator:
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes with tests
- Update documentation
- Submit a Pull Request
See Development Guide for contribution workflow.
License
This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). All rights reserved.
See the LICENSE file for full details.
What This Means:
- You can use, modify, and distribute this software freely
- If you modify and deploy on a network server, you must make your source code available
- Derivative works must also be licensed under AGPL-3.0
- There is NO WARRANTY for this software
Note on Ragtime: The ragtime/ directory is licensed separately under the PolyForm Noncommercial License 1.0.0. See ragtime/LICENSE for details.
Support
- Documentation: docs/
- Issues: GitHub Issues
- Repository: github.com/thedotmack/claude-mem
- Author: Alex Newman (@thedotmack)
Built with Claude Agent SDK | Powered by Claude Code | Made with TypeScript