Claude Agent Memory

claude-agent-memory

[](LICENSE) [](https://github.com/itskrishna21/claude-agent-memory)

Open-source Claude Code plugin that passively accumulates long-term knowledge from every session into your `~/.claude/agents/*.md` files. Agents get smarter over time — no manual edits.

How it works

1. After every turn, Claude Code fires the Stop hook.
2. agent_updater.py reads the session transcript and your agent .md files.
3. It asks Claude Haiku (via claude -p) what durable facts belong in each agent's knowledge base.
4. New bullet points are appended to the agent body. Frontmatter is never touched.

Requirements

• Claude Code CLI installed and authenticated
• Python 3.8+
• At least one agent file in ~/.claude/agents/
• No pip packages needed

Install

**Shell (clone or curl):**

git clone https://github.com/itskrishna21/claude-agent-memory
bash claude-agent-memory/install.sh

Or:

curl -fsSL https://raw.githubusercontent.com/itskrishna21/claude-agent-memory/main/install.sh | bash

`install.sh` copies the script to `~/.claude/scripts/agent_updater.py` and registers a Stop hook in `~/.claude/settings.json`.

**Plugin marketplace** (preferred):

/plugin marketplace add itskrishna21/claude-agent-memory
/plugin install claude-agent-memory@claude-agent-memory

Use either the shell installer **or** the marketplace plugin — not both — or you'll register the Stop hook twice.

Uninstall

bash uninstall.sh

Or: `/plugin uninstall claude-agent-memory@claude-agent-memory`

Agent `.md` files are never deleted.

Optional config

Create `~/.claude/agent-memory.json`:

{
  "last_n_messages": 15,
  "dry_run": false,
  "debug": false
}

Key	Default	Meaning
last_n_messages	15	How many recent transcript messa