Ebbinghaus forgetting curve memory lifecycle manager for AI agents. Automatically calculates memory strength decay, supports review reinforcement, archiving,...
Security Analysis
high confidenceThe skill appears to implement a local forgetting-curve memory manager as described: it only reads/writes a local JSON DB and archive file and contains no network calls or unexpected credential requests.
Name, description, SKILL.md, and the included Python script are consistent: the tool manages memory items with a forgetting-curve formula and supports add/review/decay/archive/forget/heartbeat. Minor documentation mismatch: SKILL.md lists the default DB path as './memory_db.json' (current dir) while the script's default is the repository root (parent of scripts/). This is an implementation/documentation divergence but not a functional mismatch.
Runtime instructions and commands are narrowly scoped to local file operations and memory workflows. SKILL.md does not ask the agent to read unrelated system files, credentials, or contact external endpoints. Heartbeat integration simply runs the script and expects textual output.
No install spec; this is instruction + included script. The script is plain Python, uses only stdlib, and requires no external downloads or package installs.
The skill declares no required credentials and uses two optional environment variables (EBBINGHAUS_DB, EBBINGHAUS_ARCHIVE) to pick file paths. This is proportional to the purpose. Note: because these env vars accept arbitrary paths, a user (or misconfigured agent) could point them to sensitive or system files, causing accidental overwrite/appends; that is a usage risk rather than a hidden requirement.
The skill does not request permanent 'always' inclusion, does not modify other skills, and does not alter agent-wide config. It writes only its own DB and archive files (paths configurable).
Guidance
This skill is internally coherent and implements a local memory manager. Before installing or running it: (1) review and keep a copy of the included scripts (you already have them); (2) run it in a safe directory (don't set EBBINGHAUS_DB or EBBINGHAUS_ARCHIVE to system or sensitive file paths); (3) back up any existing memory_db.json or MEMORY.md you care about; (4) if you plan to add this to an automated heartbeat, ensure the process runs with appropriate user permissions so it cannot write to protected system locations; (5) if you need the script to use the current working directory, update the environment-variable guidance or edit the DB_PATH default in the script to match your expectations.
Latest Release
v1.0.0
- Initial release of memory-ebbinghaus: an Ebbinghaus forgetting curve memory lifecycle manager for AI agents. - Tracks memory items with automatic strength decay, review reinforcement, archiving, and deletion. - Integrates spaced repetition by recalculating memory strength and adjusting stability on review. - Supports heartbeat mode to alert on fading (🔴) memory items. - Command-line interface provided for adding, reviewing, forgetting, archiving, and status checking. - Triggers on memory management and forgetting curve-related tasks in both English and Chinese.
More by @subcoldzhang
Published by @subcoldzhang on ClawHub
