agent-memory

Save 60-90% on LLM token costs with intelligent memory compression for multi-agent systems.

agent-memory compresses raw LLM tool output into structured observations, shares context across agents via a memory bus, and injects only relevant memory into each prompt — keeping your token budget under control.

The Problem

Running 5+ concurrent LLM agents burns tokens fast:

• Each agent re-reads the same files, re-discovers the same context
• Raw tool output (file reads, command results) consumes thousands of tokens
• No shared memory means redundant API calls across agents
• You hit rate limits and token budgets within minutes

The Solution

agent-memory sits between your agents and their context window:

Tested results: 66-94% token savings, 3-74x compression ratio.

Quick Start

As a Claude Code Plugin

Step 2: Use It (It's Automatic)

Once installed, the plugin works silently in the background with zero configuration:

What happens automatically:

• Every time Claude reads a file, runs a command, or edits code, the PostToolUse hook compresses that tool output into a structured observation and stores it locally
• Every time you start a new session (or resume one), the SessionStart hook injects relevant past observations into Claude's context
• Your plan is auto-detected (Pro/Max/API) and memory budgets adjust accordingly