Skip to main content
Glama

summarize_messages

Compress chat message history using AI summarization to manage conversation context within token limits while preserving recent messages and system instructions.

Instructions

Compress chat message history using AI-powered summarization strategy. Creates concise summaries of older messages while preserving system messages and recent context.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messagesYesArray of chat messages to compress
maxModelTokensNoModel's maximum token context window
thresholdPercentNoPercentage threshold to trigger compression (0-1)
minRecentMessagesNoMinimum recent messages to always preserve
openaiApiKeyNoOpenAI API key (can also be set via OPENAI_API_KEY environment variable)
openaiModelNoOpenAI model to use for summarizationgpt-4o-mini
customPromptNoCustom prompt for summarization (optional)

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agentailor/slimcontext-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server