10 tagged compression, measured the same way as everything else here.
Browse within: LLM 5
MCP server Claude CodeCodexCursor +2
Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%. Runs locally from the @ooples/token-optimizer-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery. Runs locally from the mcp-slim-guard npm package.
MCP server Claude CodeCodexCursor +2
MCP server "cyberchef-mcp" as configured in doublegate/CyberChef-MCP. Runs in Docker (ghcr.io/doublegate/cyberchef-mcp_v4:4.2.0).
MCP server Claude CodeCodexCursor +2
Living memory for AI agents. Episodes compress into identity. Runs locally from the anneal-memory Python package.
MCP server Claude CodeCodexCursor +2
Lossless context compression for LLMs: 2x-8x fewer tokens, byte-exact reconstruction, sha256-verified. Runs locally from the densely Python package.
MCP server Claude CodeCodexCursor +2
MCP server "furl" as configured in omar-y-abdi/furl-ctx. Launched with sh -c PATH="$PATH:$HOME/.local/bin:$HOME/.cargo/bin:/opt/homebrew/bin:/usr/local. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
Lossless-first compression layer for AI-agent tool outputs — byte-faithful on fields you mark critical, configurable lossy reduction only where you opt in. Runs locally from the terse-mcp Python package.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for ASON compression/decompression. Compatible with Claude Desktop, Cline, Continue, and other MCP clients. Runs locally from the @ason-format/mcp-server npm package.
MCP server Claude CodeCodexCursor +2
MCP server that compresses, summarizes, and filters context to minimize LLM token usage. Runs locally from the compendium-mcp npm package.