The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Entroly
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,…
Install
npx -y entroly@latest --helpclaude mcp add entroly -- npx -y entroly@latest --help{
"mcpServers": {
"entroly": {
"command": "npx",
"args": [
"-y",
"entroly@latest",
"--help"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Entroly — Select AI context with auditable recovery.
Receipt-backed selection records: what was kept, what was omitted, and the handle that recovers the exact original bytes. Compression you can undo, on your own repository, in one command — without replacing your model or agent architecture.
pip install -U entroly · entroly verify-claims · entroly simulate
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.
English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · हिन्दी · Français · Deutsch · Português · Italiano · Türkçe · Tiếng Việt · Bahasa Indonesia · Polski · Nederlands · ไทย · Svenska · Čeština · Tagalog · Română
What is it? · Install · Quickstart · Benchmarks · Questions · Contribute
What is Entroly? (in plain English)
Entroly is a local-first context control plane for AI coding tools. It selects evidence within a token budget, preserves recoverable omissions, and records selection decisions in receipts. Three properties to evaluate on your task:
| 💰 Avoidable input cost | Smaller requests can reduce input cost when they reach a provider through an Entroly-controlled route. The result depends on the workload and provider cache — see the real numbers below. |
| 🔍 Recoverable originals | Receipt-backed recovery retains source material locally. Exact recovery requires the referenced store and source bytes to remain available; it does not guarantee answer quality. |
| 🧾 You can check its work | Every decision comes with a receipt: what was kept, what was left out, and why. |
Do I have to change my code? No. On hosts with a verified prompt hook,
Entroly runs before the model plans. MCP-only integrations remain callable
tools that an agent may skip; API traffic is intercepted only when it is routed
through the Entroly proxy. Check entroly activation status --json instead of
assuming an installed integration is active.
Do I need to pay for anything to try it? No. The two commands in the Install section below run on your own machine, with no API key, and show you real numbers on your own project before you connect anything paid. (Missing native-engine support is reported without downloading packages — see the note under Install.)
Switching coding agents mid-task? entroly-work resume reconstructs
unfinished work from durable repository evidence, even if the previous agent
left no handoff. The receiving agent must review the inferred state and
acknowledge it before claiming work through Entroly. Start with
entroly-work --project . --json resume --to-agent codex;
the agent continuity guide shows the complete flow
and how to measure whether it actually saves rediscovery work on your tasks.
Contributing
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io