Basic Memory
- 3.6k repo stars
- Updated August 5, 2026
- basicmachines-co/basic-memory
basic-memory is a Claude Code plugin skill that bridges working memory to Basic Memory's knowledge graph so developers can resume sessions with briefings and durable checkpoints.
About
basic-memory is a Claude Code skill and plugin that bridges Claude's ephemeral working memory to Basic Memory's local-first markdown knowledge graph. Developers install it when sessions keep losing architecture decisions, task context, or research across compactions and new chats. Hooks deliver session-start briefings and pre-compaction checkpoints, while slash commands set up projects and capture durable notes searchable via the Basic Memory MCP server.
- SessionStart hook briefs Claude from active tasks and recent graph notes
- PreCompact hook writes session checkpoints before context window compaction
- Slash commands: bm-setup, remember, share, and status for graph management
- Requires Basic Memory MCP server; complements Claude Code built-in auto-memory
Basic Memory by the numbers
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/basicmachines-co/basic-memory --skill plugins/claude-codeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| repo stars | ★ 3.6k |
|---|---|
| Last updated | August 5, 2026 |
| Repository | basicmachines-co/basic-memory ↗ |
How do I stop losing project context across Claude Code sessions and context compactions without relying only on ephemeral auto-memory?
Bridge Claude Code sessions to Basic Memory's markdown knowledge graph with briefings, compaction checkpoints, and capture commands.
Who is it for?
Developers using Basic Memory MCP who want automatic session briefings, compaction checkpoints, and capture reflexes inside Claude Code.
Skip if: Teams not running the Basic Memory MCP server or users satisfied with static CLAUDE.md files alone for all context.
When should I use this skill?
You start a Claude Code session and need prior graph context loaded, or compaction is imminent and session knowledge must persist.
What you get
Sessions begin with a knowledge brief, compaction saves a session note to the graph, and /basic-memory commands capture and share durable markdown knowledge.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Do I need Basic Memory MCP installed first?
Yes—the plugin hooks and skills call the Basic Memory MCP server, so connecting it via uvx basic-memory mcp is a hard prerequisite.
How does this differ from Claude Code auto-memory?
Auto-memory is fast in-context notes; Basic Memory is a searchable portable markdown graph you and Claude both own across tools.
What does the PreCompact hook do?
It writes a session checkpoint note to the knowledge graph before Claude Code compacts the context window so the next session can resume.