engramory
Curated file-based long-term memory for coding agents
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install Engramory?โผ
Run `npx skills add tinqiao-oss/engramory --all -g -y` in your terminal to install the skill globally, then follow AGENT-SETUP.md to wire it into your host's rules file.
How to give a coding agent long-term memory?โผ
Engramory stores durable facts as small markdown files with one always-loaded index, so your agent recalls user preferences, decisions, and project state across sessions without any database.
Does Engramory need a database or embeddings?โผ
No. It uses only plain-text markdown files you can open, edit, and diff in any editor, with zero infrastructure or external services.
Which agent hosts does Engramory support?โผ
It works on any host that can read and write local files, with ready-made adapters for Claude Code, Codex, OpenClaw, Kiro, Cursor, and DeepSeek Harness.
How does Engramory prevent memory bloat?โผ
It enforces a bounded index with soft and hard size caps, plus a pre-write hook that blocks growth past the limit so memories never silently fall out of context.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core