Basic Memory
github.comSummary
Basic Memory is a local-first knowledge management system that uses AI to help users build and navigate a semantic graph from their conversations. It stores information in Markdown files on the user's computer, allowing for bi-directional interaction between humans and AI, and integrates with tools like Obsidian and Claude Desktop.
Features6/15
See allMust Have
4 of 5
AI File Chat
Semantic Search
Cloud Storage Integration
Privacy Controls
Automated Sorting Rules
Other
2 of 10
Manual Approval Workflow
Local File Access
Feedback-Driven Refinement
Demo Mode
Usage Credits & Quotas
Multi-User Collaboration
Enterprise SSO & Compliance
Centralized Team Billing
Advanced AI Model
Data Encryption & Security
PricingFreemium
See allFree
- Unlimited public/private repositories
- Dependabot security and version updates
- Issues & Projects
- Community support
- 2,000 CI/CD minutes/month (Free for public repositories)
- 500MB of Packages storage (Free for public repositories)
Team
- Everything included in Free
- Access to GitHub Codespaces
- Protected branches
- Multiple reviewers in pull requests
- Draft pull requests
- Code owners
- Required reviewers
- Pages and Wikis
- Environment deployment branches and secrets
- Web-based support
- 3,000 CI/CD minutes/month (Free for public repositories)
- 2GB of Packages storage (Free for public repositories)
Enterprise
- Everything included in Team
- Data residency
- Enterprise Managed Users
- User provisioning through SCIM
- Enterprise Account to centrally manage multiple organizations
- Environment protection rules
- Repository rules
- Audit Log API
- SOC1, SOC2, type 2 reports annually
- FedRAMP Tailored Authority to Operate (ATO)
- SAML single sign-on
- Advanced auditing
- GitHub Connect
- 50,000 CI/CD minutes/month (Free for public repositories)
- 50GB of Packages storage (Free for public repositories)
Rationale
Basic Memory is a knowledge management system that allows users to build a persistent semantic graph from conversations with AI assistants, stored in standard Markdown files on their computer. It integrates directly with Obsidian.md and supports local-first storage. The system allows AI assistants to load context from local files, create and read notes, and search for information, aligning with AI file chat and semantic search. While it stores files locally, it also mentions integration with Claude Desktop, implying a form of cloud interaction or at least a connection to an external AI service. The emphasis on 'local-first' and 'everything stays in files you control' strongly suggests privacy controls. The 'How It Works in Practice' section demonstrates the AI creating and updating notes, which implies a form of manual approval workflow as the user can see and interact with the generated files. The 'Local File Access' feature is directly supported by the description of storing files on the user's computer.