aide-memory MCP server

aide-memory

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.

Website: https://aide-memory.dev

Docs: https://aide-memory.dev/docs

Install: npm install -g aide-memory && aide-memory init

The problem

Coding with agents has made developers significantly more productive. But it's created a new kind of friction.

You explain how the feature you're building ties into the rest of the system, the way you like to structure your code, the patterns to follow in this area. The agent gets it. You ship great work together. Next session, it's a blank slate. You re-explain the same things.

Critical decisions being made during conversations aren't being captured. Preferences, corrections, area knowledge, guidelines. So much valuable context doesn't persist, doesn't flow to the next session, to a different tool, or to a teammate's agent when they pick up work in the same area.

Rules files (CLAUDE.md, .cursorrules) help, but they have real limits:

• No unified convention or structure. A team guideline, a personal preference, an area decision, and a stack fact all blur into one file. The whole file gets injected on every turn, even when most of it might not be relevant to the area the agent is working in.
• Corrections don't make it back. What you teach the agent in conversation doesn't make it back into the rules file on its own.
• Tool-specific. What you teach your agent in Claude Code doesn't carry to Cursor unless you copy the file over manually.
• Unscoped recall. The whole file lands in context, or nothing does. There's no prompt for the agent to pull a relevant subset based on the file it just opened.

aide-memory fills these gaps. It sits alongside your rules files, not above or below. Rules files for static, always-on guidance. aide-memory for the dynamic, scoped knowledge that grows with the codebase.

How it works

Capture happens automatically

Six hooks fire across the session lifecycle, installed by aide-memory init:

• UserPromptSubmit: detects corrections ("no, use X instead") and prompts the agent to store them scoped to the code area
• Stop: periodic reflection ("anything worth remembering?") on a tunable schedule picks up decisions and findings
• SessionStart: injects top preferences, guidelines, and priority-always memories so the agent starts with context
• PreToolUse: before the agent reads or edits a file, checks if relevant memories exist for that path and prompts recall
• PostToolUse: records what was recalled so re-reads don't re-prompt
• PreCompact: clears session tracking before context compaction so post-compact reads re-prompt cleanly

Recall is scoped

Memories attach to code areas via glob scopes (src/components/dashboard/, packages/api/). When the agent opens a file, aide-memory matches the path against stored scopes and surfaces what's relevant to that area.

Four layers organize the knowledge:

Recall ranks area_context first (most specific), then technical, then preferences, then guidelines. Scoped memories rank above project-wide ones.

Git-synced for teams

Shortened. The full README is on GitHub.