Agent Memory Journal
v0.1.0Durable episodic memory for agents — file-based, inspectable, and easy to review. Use when an agent needs to keep a working journal of what happened, what ma...
⭐ 0· 77·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match what the code and instructions do: a file-based memory CLI that appends/searches daily notes and a MEMORY.md file. The code optionally honors AGENT_MEMORY_ROOT (not listed as required) and creates files under the specified root; this is expected behavior.
Instruction Scope
SKILL.md and README instruct agents to clone the repo, create a venv, run tests, and invoke the CLI with --root. The runtime instructions and code operate only on local files under the chosen root and a lock file (.agent_memory_journal.lock). They do not access network endpoints or other system credentials. One minor scope note: the tool uses fcntl-based locking (POSIX), so it is effectively targeted to POSIX/Linux environments — the skill metadata declares no OS restriction, which is a small mismatch to be aware of.
Install Mechanism
There is no automated install spec in the registry; the documentation recommends cloning the GitHub repo and using a Python venv. No remote downloads, archives, or package installation from untrusted URLs are performed by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The code optionally reads AGENT_MEMORY_ROOT as a convenience fallback (not mandatory). No tokens, secrets, or unrelated env vars are requested.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It writes and modifies files only under the selected memory root and creates a local lock file; it does not modify other skills or global agent configuration.
Assessment
This tool is a local, file-based journal. Before installing, pick a memory root directory you control (do NOT point it at system or sensitive directories); the CLI will create MEMORY.md, a memory/ directory with YYYY-MM-DD.md files, and a .agent_memory_journal.lock file. The code uses POSIX file locking (fcntl), so it may not behave correctly on Windows. There are no network calls or credential requirements in the shipped code, but if you don't trust the source, review agent_memory_journal.py before running it. If you plan to automate an agent to call it, prefer passing --root explicitly and avoid pointing --root at directories containing secrets.Like a lobster shell, security has layers — review code before you run it.
latestvk97d92pwkftq7mhwr1f9x2bxan83xp60
License
MIT-0
Free to use, modify, and redistribute. No attribution required.