Long-term Code Project Maintenance
Continuously modify the same codebase across multiple sessions without repeatedly explaining module relationships, naming conventions, and historical decisions
Кому підходить:Software developers
Персональний Agent / Продуктивність

claude-mem is an open-source plugin for allowing Claude to retain and restore contextual memory across different sessions.
Рейтинг використання токенів OpenRouter
#25
Джерела: OpenRouter
Унікальні відвідувачі на місяць
41,848
Джерела: SimilarWeb

Coding Plan
Знижки на моделі Coding Pro
This product is positioned as a session memory extension tool for Claude users, primarily by installing and running it in environments such as Claude Code, Cursor, or Cowork. It records user-AI interaction history, code changes, and decision processes, then compresses and automatically injects relevant content when new sessions start later. Its core feature is cross-platform and cross-session memory transfer, avoiding the need to rebuild context from scratch each time. It suits developers who use Claude long-term for code projects or planning tasks, as well as individual users needing continuous collaboration. Compared to other memory tools, it integrates directly into the Claude plugin system, focusing on session history compression and automatic recovery rather than standalone knowledge base management.
Коротко
claude-mem is an open-source plugin for allowing Claude to retain and restore contextual memory across different sessions.
Для чого використовується
After installation, users enter commands in Claude sessions to record current work, then automatically receive architecture, conventions, and modification records from previous projects when new sessions begin. Users can also use it to continue unfinished tasks after Cowork container restarts without repeating background explanations.
Кому підходить
Individual productivity users, operations teams, and automation builders
Як це працює
Users typically enter the product from the command line, IDE, or desktop, then complete work through multi-step task planning and tool calls.
Тип продукту
Extension / Plugin
Ціни
Невідомо
Real-time pricing for the current enhanced version batch is not maintained for this product; please refer to the official website or official documentation.
Інтеграція з APIMaster
Підтримується
Provider selection in the installation process, or provider configuration items
Надійність даних
Середня
Остання перевірка: 2026-09-02
Automatically compresses session history into semantic summaries, stores them locally, and injects relevant context in subsequent sessions
Provides three MCP tools: search (returns memory index), timeline (view events before and after), get_observations (retrieve full details)
All memory data is stored in a local SQLite database, supporting private tags to exclude sensitive content
Memory can automatically follow and recover across Claude Code, Cursor, and other Agent platforms
Automatically runs background tasks such as extractMemories and sessionMemory after each response to generate structured memory files
Continuously modify the same codebase across multiple sessions without repeatedly explaining module relationships, naming conventions, and historical decisions
Кому підходить:Software developers
View tool call records and observation results from previous sessions to quickly locate previously encountered issues
Кому підходить:Programmers
Continue the same writing or project planning across different sessions, automatically bringing in user preferences, background, and constraints
Кому підходить:Content creators
After completing tasks in disposable cloud containers, automatically load previous work memory when new sessions or new Agents start
Кому підходить:AI Agent users
Base URL
https://apimaster.ai/v1Змінна середовища API-ключа
APIMASTER_API_KEYМодель
Ваш Model ID APIMasterПідсумок обговорень
Users typically understand claude-mem as a cross-session memory plugin for Claude AI that compresses historical conversations and injects key context, allowing Agents to retain project structure, decisions, and preferences in long-term tasks. Discussions focus on using it for coding collaboration, project maintenance, and planning writing scenarios to reduce the need for repeated context explanations. Users also frequently discuss integration methods with other memory tools and impacts on usage volume and performance.
Users discuss how to configure it to remember code architecture, module relationships, and historical decisions, avoiding the need to re-explain project background in every new session.
Users share practices of combining claude-mem with basic memory systems or knowledge graph tools to build a more durable Agent memory layer.
Users exchange information on whether it increases token consumption after context compression and how to optimize to avoid affecting overall usage efficiency.
Users explore how to make it remember personal preferences, constraints, and background information to make long-term collaborative conversations more coherent.
We currently classify it under the Personal Agent / Productivity category; page descriptions are based on official websites and public sources such as OpenRouter.
The enhanced version page of claude-mem prioritizes displaying collected core tasks and use cases to help you quickly determine if it matches your current needs.
There is currently no reliable source confirming that the product supports third-party keys or custom compatible endpoints, so the page status will show as pending verification.
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
Джерела:Офіційний вебсайтGitHub
Остання перевірка: 2026-09-02 · Повідомити про виправлення