Ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Simple file-backed memory layer for Claude agents. Markdown files on disk.
A minimal, file-backed memory layer for a Claude-powered agent, built per the technical article. No vector DB, no embeddings — just markdown files on disk managed through Anthropic's beta memory tool. - `memory_backend.py` — `LocalFilesystemMemoryTool`, a subclass of `BetaAbstractMemoryTool` that implements view/create/str_replace/insert/ delete/rename against `./memory/memories`, with path-traversal guards. -
git clone --depth 1 https://github.com/adedayoagarau/agent_memory.git ~/.claude/skills/agent-memory
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/agent-memory instead.
No specific triggers listed.
A minimal, file-backed memory layer for a Claude-powered agent, built per the technical article. No vector DB, no embeddings — just markdown files on disk managed through Anthropic's beta memory tool. - `memory_backend.py` — `LocalFilesystemMemoryTool`, a subclass of `BetaAbstractMemoryTool` that implements view/create/str_replace/insert/ delete/rename against `./memory/memories`, with path-traversal guards. -
Clone it into your personal skills folder: git clone --depth 1 https://github.com/adedayoagarau/agent_memory.git ~/.claude/skills/agent-memory — then restart Claude Code.
Agent_Memory is open source on GitHub (1 stars at last check) and published by adedayoagarau.
Browse other meta skills in the Meta category of this directory.