$ loading_
Compress and analyze massive LLM payloads while preserving critical meaning.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "distill-mcp-v2" yet — see the docs or source repo.
Compress this AI agent execution log into a model-ready context. Preserve goals, key decisions, error causes, tool results, and unfinished tasks, and return it as bullet points.
A dense summary that preserves key meaning for continued reasoning or execution.
Analyze this multi-turn conversation and tool output. Extract user goals, constraints, attempted solutions, failure patterns, and recommended next steps while minimizing token usage.
A structured context summary ready to be reused as compact input for later model calls.
Inspect this large prompt and attached payload, identify redundancy, repeated information, key semantic blocks, and safely removable parts, then provide an optimized compressed version.
A payload diagnostic report and a compressed prompt version that reduces context cost.
Compress and proxy MCP responses to reduce token usage for LLM tool calls.
Compress MCP tool schemas to cut tokens while preserving semantics deterministically.
Build, debug, and manage software tasks with natural language across LLMs.
Manage multiple MCP servers and load tool schemas on demand efficiently.
Access multiple AI providers in one terminal for generation, search, and comparison.
Compresses LLM conversation context while preserving meaning and reducing token usage.