basic-memory
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
No outside reports on file
BasicMemory improves AI continuity but introduces data retention risks; use it only for non-sensitive information, verify encryption and access controls, and monitor what memories are being stored.
Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (basicmachines-co/basic-memory)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/basicmachines-co/basic-memory ↗
About Basic Memory
BasicMemory is an MCP (Model Context Protocol) connector that lets AI assistants remember information across multiple conversations. Instead of repeating project details or context each time you chat, the AI can store and retrieve memories to maintain continuity in ongoing work.
Who it’s for
Developers and teams who use Claude or other AI assistants regularly and want to avoid re-explaining the same project context, requirements, or decisions in every new conversation.
Alternatives
- Anthropic's native conversation history in Claude: Built-in memory across messages in one thread, no setup needed.
- LangChain Memory modules: Open-source memory tools that integrate with various AI frameworks for custom retention strategies.
- Pinecone or Weaviate: Vector database tools for semantic memory and retrieval, more complex but highly controllable.
- Custom database solutions: Roll your own memory backend using PostgreSQL or similar with fine-grained access controls.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. The tool is designed as an MCP server, which typically requires adding a configuration block to your Claude Desktop or MCP client settings. Check https://github.com/basicmachines-co/basic-memory (opens external site) for installation and setup instructions.
Why this grade
Signal-based grade (4/7 points): well starred on GitHub, listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 4.4k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Memory storage location: The connector stores conversation summaries and context somewhere (likely local or cloud); attackers or account compromise could expose stored project details or sensitive information you discussed with the AI.
- AI memory injection: If an attacker gains access to memory storage, they could insert false information into your AI's context, causing it to make incorrect decisions based on planted data.
- Unencrypted data: Memories may be stored unencrypted; check whether the tool encrypts data at rest and in transit.
- Oversharing with AI: Users might store confidential information (API keys, passwords, business secrets) in memory that gets retained and could leak if the storage is compromised.
- No recall filtering: The AI may recall sensitive context in conversations with third parties or in logs without clear controls over what gets shared.
How to lower the risk
Least-privilege permissions
- Store only non-sensitive project summaries and public context in memory.
- Never save API keys, passwords, or credentials in memory.
Network isolation
- Verify where memories are stored (local file, cloud service, etc.) and confirm it meets your security policy.
- Use VPN or private networks if storing memories on external servers.
Monitoring
- Review stored memories regularly to check for accidental sensitive data.
- Audit access logs if the service provides them.
Red flags to watch for
- Memory responses that include information you never explicitly told the AI.
- Memories persisting after you delete them from the UI.
- Lack of encryption documentation or security disclosures.
Questions
How do I install Basic Memory?
Basic Memory does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/basicmachines-co/basic-memory.
Are there security reports about Basic Memory?
No reports found for this package in our research (last checked 2026-10-29). Basic Memory currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include memory storage location, ai memory injection, unencrypted data.
Is Basic Memory actively maintained?
Basic Memory has 4.4k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/basicmachines-co/basic-memory before pinning it in production.
What are alternatives to Basic Memory?
Notable alternatives to Basic Memory include Anthropic's native conversation history, LangChain Memory modules (Open-source memory tools that integrate with various AI frameworks for custom retention strategies), Pinecone or Weaviate (Vector database tools for semantic memory and retrieval, more complex but highly controllable), Custom database solutions (Roll your own memory backend using PostgreSQL or similar with fine-grained access controls). You can also compare Basic Memory side by side with other MCP servers in the Related tools section on this page.
Community questions about Basic Memory
- basic-memory MCP: ai_assistant_guide resource not found (No such file or directory)
- basic-memory write_note drops custom frontmatter from content
- Basic Memory 0.12.0: write_note fails with sqlite3.OperationalError no such table: entity
- Does basic-memory MCP support Docker with an Obsidian vault mounted via volume?
- Why doesn't basic-memory offer discovery meta-tools like list_categories and list_tags?
Key facts
- Type
- App connector
- Publisher
- basicmachines-co
- Source code
- github.com/basicmachines-co/basic-memory
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 4.4k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-21
Community
Discussions for Basic Memory
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude