entroly
01MCP server Claude CodeCodexCursor +2
MCP server "entroly" as configured in juyterman1000/entroly. Launched with entroly serve. Needs 1 environment variable to run.
18 tagged context compression, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
MCP server "entroly" as configured in juyterman1000/entroly. Launched with entroly serve. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "colab-mcp" as configured in juyterman1000/entroly. Runs locally from the git+https://github.com/googlecolab/colab-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "fixture" as configured in lennney/mcp-slim-guard. Runs ../../../dist/mock-server.js with node.
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
Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test. Runs locally from the distil-llm Python package.
MCP server Claude CodeCodexCursor +2
MCP server "savecontext" as configured in AlexanderBoger/SaveContext. Runs savecontext with python. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Loop engineering substrate for coding agents — state, lossless optimization, and hook enforcement: verify-gated loops that can't lie, run away, or go broke. For Claude Code, Codex, Cursor, Gemini CLI, VS Code Copilot, and any MCP client. Runs locally from the knitbrain npm package.
MCP server Claude CodeCodexCursor +2
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en. Runs locally from the cctx-optimizer npm package.
MCP server Claude CodeCodexCursor +2
Session-scoped knowledge graph engine for AI chat context compression. Runs locally from the fish-bridge-mcp Python package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor
Drop-in compression for LLM agent tool outputs. Shrink bloated HTML/JSON/log results before they re-enter context — cut tokens, stay on-task, keep full output retrievable. Runs locally from the tooltrim Python package.
MCP server Claude CodeCodexCursor
MCP server "capsule" as configured in hakiyaka/capsule. Runs ./mcp/server.cjs with node.
MCP server Claude CodeCodexCursor
Token-level context compression for LLM and agent workflows. Runs locally from the contextcrumb Python package.
MCP server Claude CodeCodexCursor
MCP server "tokensaver-mcp" as configured in pozii/tokensaver. Runs locally from the tokensaver-mcp Python package.
liangyuan0219/session-migrator
MCP server Claude CodeCodexCursor
MCP server "session-migrator" as configured in liangyuan0219/session-migrator. Runs locally from the session-migrator Python package.
MCP server Claude CodeCodexCursor
Zero-dependency, fully-reversible context compression for AI agents. Runs locally from the slimctx Python package.
MCP server Claude CodeCodexCursor
Apply sql-like filters to GeoJSON. Runs locally from the winnow npm package.
MCP server Claude CodeCodexCursor +2
MCP server "tokenslim-mcp" as configured in robertruben98/tokenslim-mcp. Runs locally from the tokenslim-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "sarup" as configured in PHUICMT/sarup. Runs locally from the sarup Python package.