Entroly CLI
entroly
A layer for selecting and reversibly compressing context for AI agents: records of what was kept and omitted, and a key to restore the original. Works locally
- 476 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The entroly go command wraps the agent launch
- The savings measurements in the README are not verified
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/entrolyDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The entroly go command wraps the agent launch
- The savings measurements in the README are not verified
This is third-party code. Review the repository files before installing.
What it does
Entroly selects and reversibly compresses context for AI agents: it keeps records of what was kept and omitted and gives a key to restore the original. It works locally with no key. Installation: `pip install -U entroly && entroly go`, also `npm install -g entroly` or `brew install juyterman1000/entroly/entroly`, with the VS Code extension `entroly.entroly-vscode`. The `entroly go` command detects the editor itself and wraps the launch of your agent, that is it intervenes in its launch. Version entroly-v1.0.86 from 04.10.2026, Apache-2.0 license.
Who it is for. For developers who want to cut agent context without losing the ability to restore the original.
Good fit when
- You need to compress agent context reversibly
- You need records of what was kept and omitted
- You need a local layer with no keys
Not a fit when
- You cannot let a utility wrap the agent launch
- You need verified savings figures: the author's measurements are not verified
Example request
Compress this repository's context for the session and show what was kept, what was omitted and how to restore the originalLimitations
The entroly go command detects the editor itself and wraps the launch of your agent, so access is extended: check what it changes. We have not verified the savings measurements from the README, so measure on your own project. Everything works locally with no key.
How to disable. Remove the skill from the agent's folder or the plugin through the plugin manager.
FAQ
What does Entroly do?
It selects and reversibly compresses agent context, leaving records and a key to restore the original.
How do I install it?
pip install -U entroly && entroly go, also npm install -g entroly or brew.
Is a key needed?
No, it works locally with no key.
Discussion
No questions or reviews yet.
Related
CLI toolsA local context layer for coding agents: it understands the task, routes and compresses context and tracks the cost
A local context store for coding agents that captures project knowledge and reuses it across Codex, Claude Code and OpenCode
Context Infrastructure
context-infrastructure
A reference implementation of a context system for an agent: structure, data flows, a blueprint the author has used for a year. README in Chinese. For study
A Go CLI that configures the AI coding agents you already use: it gives them shared memory, a workflow and deterministic steps without replacing the agents them
Athena
athena-public
A long-term context layer for agents portable between editors: plain Markdown on disk, the /start and /end commands. Version 10
Local context compression for agents: tool outputs, logs, files and RAG chunks shrink before reaching the LLM. Proxy, CLI, library and MCP
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Entroly (this entry) | no | 476 | ||
| SigMap | no | 646 | a code map and a grounding check of agent answers | |
| Token Optimizer MCP | no | not required | 544 | context compression and caching with Claude hooks on global install |
README in short
The README describes a layer for selecting and reversibly compressing context for agents with installation through pip, npm and brew. Apache-2.0 license.