Long-term Code Project Maintenance
Continuously modify the same codebase across multiple sessions without repeatedly explaining module relationships, naming conventions, and historical decisions
Best for：Software developers
Personal Agent / Productivity
claude-mem
claude-mem is an open-source plugin for allowing Claude to retain and restore contextual memory across different sessions.
Product type: Extension / PluginPricing: UnknownAPIMaster integration: Supported
OpenRouter token usage rank
#25
Source: OpenRouter
Monthly unique visitors
41,848
Source: SimilarWeb
Coding Plan
Stop juggling model subscriptions
Coding Pro model discounts
- glm-5.250% off
- glm-5.350% off
- deepseek-v4-flash40% off
- deepseek-v4-pro40% off
- qwen3.8-max40% off
- kimi-k2.7-code30% off
- kimi-k330% off
- minimax-m330% off
Overview
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.
One-line summary
claude-mem is an open-source plugin for allowing Claude to retain and restore contextual memory across different sessions.
What people use it for
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.
Best for
Individual productivity users, operations teams, and automation builders
How it works
Users typically enter the product from the command line, IDE, or desktop, then complete work through multi-step task planning and tool calls.
Quick facts
Product type
Extension / Plugin
Pricing
Unknown
Real-time pricing for the current enhanced version batch is not maintained for this product; please refer to the official website or official documentation.
APIMaster integration
Supported
Provider selection in the installation process, or provider configuration items
Data confidence
Medium
Last verified: 2026-09-02
Core features and differentiators
Cross-session Memory Compression and Injection
Automatically compresses session history into semantic summaries, stores them locally, and injects relevant context in subsequent sessions
Three-layer Memory Retrieval Tools
Provides three MCP tools: search (returns memory index), timeline (view events before and after), get_observations (retrieve full details)
Local SQLite Storage
All memory data is stored in a local SQLite database, supporting private tags to exclude sensitive content
Multi-platform Memory Synchronization
Memory can automatically follow and recover across Claude Code, Cursor, and other Agent platforms
Background Memory Extraction and Organization
Automatically runs background tasks such as extractMemories and sessionMemory after each response to generate structured memory files
What is claude-mem best for?
Cross-session Debugging and Issue Tracking
View tool call records and observation results from previous sessions to quickly locate previously encountered issues
Best for：Programmers
Writing or Planning Task Continuation
Continue the same writing or project planning across different sessions, automatically bringing in user preferences, background, and constraints
Best for：Content creators
Cowork Container Task Handover
After completing tasks in disposable cloud containers, automatically load previous work memory when new sessions or new Agents start
Best for：AI Agent users
Third-party key setup for claude-mem (APIMaster integration)
Setup steps
- 1When installing or first launching claude-mem, enter the provider selection process.
- 2Select an external provider option, such as OpenRouter or Gemini key explicitly mentioned in the official documentation.
- 3Enter the third-party API Key; if the current version additionally provides a compatible endpoint or Base URL field, also enter the APIMaster Base URL.
- 4After completion, perform a minimal test to confirm that claude-mem is working through your own third-party key.
Config values
Base URL
https://apimaster.ai/v1API key environment variable
APIMASTER_API_KEYModel
Your APIMaster model IDCommunity discussion
Discussion summary
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.
Most discussed topics
- 1
How to implement cross-session project memory with claude-mem?
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.
- 2
How to integrate claude-mem with other memory tools (such as mem0, Obsidian)?
Users share practices of combining claude-mem with basic memory systems or knowledge graph tools to build a more durable Agent memory layer.
- 3
Impact of claude-mem on Claude usage volume and performance?
Users exchange information on whether it increases token consumption after context compression and how to optimize to avoid affecting overall usage efficiency.
- 4
Applications of claude-mem in writing and planning tasks?
Users explore how to make it remember personal preferences, constraints, and background information to make long-term collaborative conversations more coherent.
FAQ
What type of product is claude-mem?
We currently classify it under the Personal Agent / Productivity category; page descriptions are based on official websites and public sources such as OpenRouter.
What is claude-mem suitable for?
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.
Can claude-mem directly connect to APIMaster now?
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.
Similar agents
Hermes Agent
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
WorkBuddy
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
OpenClaw
Belongs to the same Personal Agent / Productivity category and can be used for horizontal comparison of different task entry points and product forms.
Sources：Official websiteGitHub
Last verified: 2026-09-02 · Report a correction