Home/AI Agents/entroly

entroly

juyterman1000/entroly

Know exactly what your AI agent saw.

GitHub Website

GraphCanon updated Oct 3, 2026 · GitHub synced Oct 3, 2026

57views this month

471 stars71 forksLast push Oct 2, 2026 Python Apache-2.0

Decision brief

Know exactly what your AI agent saw with Entroly.

Good fit when

When you require proof of evidence selection to ensure transparency in model decisions, use Entroly.
Use Entroly when working on projects that demand context-control and auditing across multiple coding agents like Cursor or Claude Code.

Avoid when

Avoid using Entroly if your AI workflows are already finely optimized for minimal intervention and do not benefit from additional context management layers.
Do not use Entroly if you have no need for replayable Context Commits, which Entroly offers to trace evidence selection and omissions.

Observed Jul 17, 2026 · Source: enrich:decision_facts

entroly alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (0d since push); As of Oct 3, 2026
Provenance: Not a fork · Personal account; As of Oct 3, 2026
Security (OSV): 1 medium (1 medium); As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install entroly

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

learn-claude-code

A nano claude code-like agent harness built from scratch

77k★

oh-my-openagent

A coding agent for complex codebases, supporting multiple AI agents like ChatGPT and Claude.

69k★

claude-plugins-official

Official directory of high quality Claude Code Plugins by Anthropic

37k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Local context-control plane for AI coding agents that manages evidence selection, compresses and keeps caches hot, verifies answers, and serves as an MCP/proxy/SDK for Cursor, Claude Code, Codex, and Aider among others.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Oct 3, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Oct 3, 2026
CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Oct 3, 2026
MCP server: No MCP server detected
Source: repo_scan · Oct 3, 2026
Languages: python
Source: github.language+pyproject.toml · Oct 3, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Oct 3, 2026)

| 📦 **Node / npm** | `npm install -g entroly` | The same engine, nothing Python required |

Source link

Python runtimePython

Source: README excerpt (regex_v1, Oct 3, 2026)

> **Not sure which one?** Pick **Python**. It's the complete version and what

Source link

README

Install Not sure which one? Pick Python . It's the complete version and what most people use. The others are alternate ways to run the same engine. Platform Install What you get 🐍 Python (pip) — recommended Everything: the command line tool, the server your AI editor talks to, a...

For agents

This page has a .md twin and JSON over the API.

/tools/juyterman1000-entroly.md GET /api/graphcanon/tools/juyterman1000-entroly GET /api/graphcanon/graph?tool=juyterman1000-entroly