$ loading_
Compresses LLM conversation context while preserving meaning and reducing token usage.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "compresh-mcp" yet — see the docs or source repo.
Compress the following agent conversation history into equivalent context. Preserve key constraints, open questions, supporting facts, and risk markers while minimizing tokens: {{conversation}}A shorter but semantically equivalent conversation summary that can be fed back to the model.
Condense this multi-step reasoning trace and mark confirmed facts, inferred claims, information gaps, and supporting evidence without losing critical assumptions: {{reasoning trace}}A compressed result with epistemic markers for safer downstream agent continuation and decisions.
Extract reusable long-term semantic memory from the following interaction history, deduplicate similar content, and produce a compressed representation for future retrieval: {{interaction history}}Structured semantic memory entries and compressed representations for retrieval and context injection.
Compress and proxy MCP responses to reduce token usage for LLM tool calls.
Compress MCP tool schemas to cut tokens while preserving semantics deterministically.
Monitor AI coding context usage and preserve state before compaction.
Give AI agents persistent memory, searchable knowledge, and automatic consolidation.
Compress context and persist checkpoints to cut AI agent token usage.
Compress and analyze massive LLM payloads while preserving critical meaning.