The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"octopoda-os": {
"command": "uvx",
"args": [
"octopoda-os"
]
}
}
}
📋 Copy
Run in terminal:
claude mcp add octopoda-os uvx octopoda-os
📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"octopoda-os": {
"command": "uvx",
"args": [
"octopoda-os"
]
}
}
}
📋 Copy
Or install with pip: pip install octopoda-os
README Excerpt
<h1 align="center">🐙 Octopoda</h1> <p align="center"> <strong>The open-source memory and observability layer for AI agents.</strong><br /> Persistent memory, loop detection, audit trails, and a live dashboard — automatic on <code>pip install</code>. </p> <p align="center"> <a href="https://pypi.org/project/octopoda/"><img src="https://img.shields.io/pypi/v/octopoda?style=flat-square&label=pypi" alt="PyPI" /></a>
Tools (9)
OCTOPODA_API_KEY OCTOPODA_EMBEDDING_MODEL OCTOPODA_LICENSE_KEY OCTOPODA_LLM_PROVIDER OCTOPODA_LOCAL_MODE OCTOPODA_OPENAI_API_KEY SYNRIX_DATA_DIR SYNRIX_HEARTBEAT_INTERVAL_SEC SYNRIX_MAX_VERSIONS_PER_RUNTIME_KEY
Topics
agent-framework ai-agents ai-memory autogen crash-recovery crewai developer-tools knowledge-graph langchain llm-agents loop-detection mcp mcp-server memory-engine multi-agent