entroly MCP Server
juyterman1000/entroly
[](https://agentrank-ai.com/tool/juyterman1000--entroly/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
juyterman1000/entroly is a Python tool licensed under Apache-2.0. Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper. Topics: ai-agents, claude-code, mcp, token-optimization, context-compression, hallucination-detection, llm, codex, context-engineering, openclaw, ai-coding-agents, context-optimization, context-window, github-copilot, agent, developer-tools-ai-agent, graph, harness-engineering, loop-engineering, tokenomics.
Ranked #1715 out of 24849 indexed tools.
In the top 7% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
472 stars → growing community
Last commit today → actively maintained
3/4 issues closed → decent issue management
3 contributors → small team
No dependents → no downstream usage
415 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/juyterman1000--entroly/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/juyterman1000--entroly/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/juyterman1000--entroly" alt="AgentRank"></a> Matched Queries
From the README
<p align="center"> </p> <h1 align="center">Entroly — Select AI context with auditable recovery.</h1> <p align="center"><b>Receipt-backed selection records: what was kept, what was omitted, and the handle that recovers the exact original bytes.</b><br> Compression you can undo, on your own repository, in one command — without replacing your model or agent architecture.</p> <p align="center"> </p> <p align="center"><code>code --install-extension entroly.entroly-vscode</code> · <code>pip install -U entroly && entroly go</code> · <code>npx entroly</code></p> <p align="center"> <sub>Entroly is an open-source, local-first AI token-efficiency and Context Assurance layer: budgeted evidence selection, recoverable context compression, content-addressed evidence recovery, and auditable receipts. Works through VS Code, Claude Code, Cursor, Codex, OpenClaw, GitHub Copilot, Aider, and OpenAI/Anthropic-compatible apps.</sub> </p> <p align="center"> <a href="httpsRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.