
Memory Research
When you drop a company name, URL, or "research X" into a conversation, this runs web searches, checks if you already have notes on it, then proposes creating a structured memory entity with what it found. It hedges uncertain info, stores source URLs, and won't create anything without your approval. The workflow is thorough: 3-5 searches per subject, checks for duplicates in your existing knowledge graph, captures any context you mentioned alongside the name. Useful if you're building up a knowledge base of companies, people, or technologies and want research folded directly into your memory system rather than just getting a one-off answer.
- skills.sh installs
- 525
- GitHub stars
- 23
- last updated
- Aug 21, 2026
Install
$ npx -y skills add basicmachines-co/basic-memory-skills --skill memory-research --agent claude-codeInstalls into .claude/skills of the current project.
Files
Memory Research
Research an external subject, synthesize what you find, and create a structured Basic Memory entity — with the user's approval.
When to Use
Explicit triggers:
- "Research [subject]"
- "Look up [subject]"
- "What do you know about [subject]?"
- "Evaluate [subject]"
Implicit triggers (also activate this skill):
- A bare name: "Terraform"
- A URL: "https://example.com"
- A name with context: "Acme Corp — saw them at the conference"
Workflow
Step 1: Web Research
Search for current information across multiple sources. Aim for 3-5 searches to build a well-rounded picture:
[subject name] site
[subject name] overview
[subject name] news [current year]
[subject name] [relevant domain keywords]
What to gather by entity type:
Sponsors
Details
- Repository
- github.com/basicmachines-co/basic-memory-skills
- Category
- Data Science & ML
- First seen
- Jun 3, 2026