Log inSubmit server
Entroly logo

Entroly

by juyterman1000

Local MCP control plane for auditable context selection, compression, recovery, and AI coding workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Entroly

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "juyterman1000-entroly": {
      "command": "npx",
      "args": [
        "-y",
        "entroly@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

juyterman1000/entroly gives AI coding tools a local context control plane that selects repository evidence within a token budget and records the decision in a receipt. It can compress context while retaining handles for recovering omitted source bytes, and supports MCP, proxy, CLI, and library usage. Reach for it when coding agents need smaller prompts, inspectable context decisions, or durable evidence across agent handoffs. The Python package provides the broadest runtime surface, including the MCP server, CLI, SDK, and proxy.

Use cases

  • Reduce repository context before sending coding tasks to a model
  • Inspect which evidence an agent retained or omitted
  • Resume unfinished work when switching coding agents
  • Simulate context selection locally before using a paid provider

Key features

  • Budgeted repository evidence selection
  • Receipt-backed reversible context compression
  • Content-addressed source recovery
  • Local claim verification and simulation
  • Durable budget-aware agent memory
  • MCP server, HTTP proxy, and library interfaces

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

21/21 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · entroly@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars480Stargazers on the source repository.
npm downloads727Package downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Entroly works

What juyterman1000/entroly does

juyterman1000/entroly adds a local evidence-selection layer for AI coding tools. It examines repository material, chooses content within a token budget, and records what it included, what it omitted, and the reasoning behind the selection. The result is a receipt that can be inspected later.

Omitted material remains recoverable through content-addressed references, provided the referenced store and original source bytes are still available. This makes context reduction reversible rather than a permanent deletion of repository evidence.

The project also supports durable repository evidence for continuing work between agents. The entroly-work resume flow can reconstruct unfinished work for a receiving agent, which must review and acknowledge the inferred state before taking ownership.

How it works

Entroly operates locally and can be used as an MCP server, an HTTP proxy, or a Python or Rust library. With a verified prompt hook, it can run before a model plans. MCP-only usage exposes callable tools that an agent may choose not to invoke, while API traffic is intercepted only when routed through the Entroly proxy.

Context selection combines budgeted evidence handling with receipt-backed recovery. The project description identifies BM25 ranking, entropy, and dependency-graph knapsack selection as part of its context compression approach. It also describes prompt-prefix stabilization for provider caching and a Bayesian router for directing simpler work to lower-cost models.

The installation includes local checks such as entroly verify-claims and entroly simulate. These commands operate on the local project without an API key and help inspect behavior before connecting a paid model or provider.

Setup and configuration

The recommended installation is the Python package:

Terminal
pip install -U entroly

From the repository you want to inspect, run:

bash
entroly verify-claims
entroly simulate

simulate accepts a task-specific query. Other supported installation paths include the npm package, a Rust source build with the proxy feature, Homebrew on macOS or Linux, and the published Docker image. Package-runner options include uvx, pipx, npx, pnpm dlx, and bunx.

The Python distribution is the complete option for the MCP server, CLI, SDK, proxy, verification, and native-engine paths. The Node package provides a local Node/WASM CLI, while the Rust build produces a standalone program.

Tools and capabilities

  • Select repository evidence under a token budget.
  • Compress context while preserving recoverable references to omitted bytes.
  • Produce receipts describing retained and excluded material.
  • Recover source evidence through content-addressed storage.
  • Verify claims and simulate selection locally.
  • Store working, episodic, and semantic memory with budget awareness, decay, safety scanning, and durable persistence.
  • Support agent continuity through repository-backed work resumption.
  • Serve context functions through MCP or route API traffic through an HTTP proxy.

Limitations and notes

Exact recovery depends on keeping the referenced store and source bytes available. Receipt-backed recovery does not guarantee answer quality. Prompt hooks require host activation, so an installed integration should not be assumed to be active; entroly activation status --json checks that state.

The local verification and simulation commands do not call an AI, prove activation, demonstrate answer quality, or establish a lower provider bill. Cost and cache effects depend on the workload, provider, and routing path. MCP integrations are callable tools, so an agent may skip them unless the surrounding workflow uses them.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Entroly

juyterman1000/entroly is an MCP server that connects AI coding tools to local repository context controls, including budgeted evidence selection, recoverable context compression, receipt generation, source recovery, and local verification. It helps agents inspect and reuse selected project evidence without requiring an API key for its local verification and simulation commands.

Install the complete Python package with `pip install -U entroly`. It includes the CLI, MCP server, SDK, and proxy. You can also use the npm package, Homebrew, Docker, a Rust source build, or `uvx` and `pipx`; run `entroly verify-claims` and `entroly simulate` locally afterward.

Yes, Cursor is among the coding tools supported by Entroly. The project also identifies VS Code, Claude Code, Codex, OpenClaw, GitHub Copilot, Aider, and OpenAI- or Anthropic-compatible applications as supported environments. Check `entroly activation status --json` rather than assuming an installed integration is active.

Yes, compressed context can be recovered through receipt-backed, content-addressed references when the referenced store and original source bytes remain available.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewEntroly AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/juyterman1000-entroly?style=directory)](https://allmcps.com/mcp/juyterman1000-entroly)
HTML Embed
<a href="https://allmcps.com/mcp/juyterman1000-entroly"><img src="https://allmcps.com/api/badge/juyterman1000-entroly?style=directory" alt="Entroly on AllMCPs" /></a>