$ loading_
Offload large tool outputs and recall them to save context tokens.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.JesusGarcia9009/lethe" MCP server from askskill: Run: claude mcp add 'io-github-jesusgarcia9009-lethe' -- npx -y lethe-llm-context
Please archive this long tool output, keep a retrievable reference, and give me a brief summary.
Creates a recallable archive reference and returns a compressed summary.
Based on the previously archived content, recall the parts related to error diagnosis and output only the key excerpts.
Retrieves relevant excerpts from archive without reusing full context.
Please move tool outputs that don't need to stay in context right now out of the context window, but keep them recoverable later.
Reduces context size while preserving later recovery.
Let VS Code agents search and reuse context from your LLMemory vault.
Manage token-efficient memory for AI coding agents with dedup, merge, and decay.
Provide Git-native project memory for AI coding agents with safe, reviewable context.
Give AI coding agents persistent project memory that detects stale knowledge.
Authorize AI agent actions with policy, approval, and audit trails.
Let AI agents search, read, and update a self-hosted Markdown team wiki.