Entroly

Tokens saved·Estimated cost avoided·Compression savings·Tool-schema deferral savings

Tool schemas are never hidden by a relevance guess. To opt in for a request, send a comma-separated active set such asX-Entroly-Active-Tools: search_files,read_file. Forced tool choices and unnamed provider tools remain available; an invalid or non-matching set leaves the request unchanged.

Use Entroly at the SDK, framework, proxy, MCP, plugin or agent boundary. A listed name is not automatically a claim that hosted subscription inference is intercepted; provider-bound savings exist only when the request traverses an Entroly-controlled route.

AI coding assistants have a memory limit. Hand one your whole codebase and it gets slow, expensive, and distracted — like giving someone a 500-page manual when they only needed page 47.

It sits between your code and the AI, reads everything, and passes along only the parts that matter for the question actually being asked. Three things make that safe to do:

Not sure which one?PickPython. 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|pip install -U entroly| Everything: the command-line tool, the server your AI editor talks to, and the code library | | 📦Node / npm|npm install -g entroly| The same engine, nothing Python required | | 🦀Rust(source build) |cd entroly-core && cargo build --release --bin entroly-rs --features proxy| One self-contained program, no Python or Node needed | | 🍺Homebrew|brew install juyterman1000/entroly/entroly| The command-line tool on macOS/Linux | | 🐳Docker|docker pull ghcr.io/juyterman1000/entroly:latest| Runs in a container, nothing installed on your machine |Now check that it worked — free, offline, no API key:

cd /your/repo entroly verify-claims entroly simulate

Both run locally. Neither one calls an AI or costs anything.

Just want it working?pip install -U entroly && entroly go— that's the whole thing. It finds your editor, sets itself up, and shows you a before/after dashboard. The rest of this table is for specific setups. | Your situation | Do this | What it gets you | |---|---|---| | 🟢"I just want it on."(pip / Python user)|pip install -U entroly && entroly go| Auto-detects your editor, wraps your agent, opens a dashboard showing tokens before and after | |"I use Node, not Python."(npm user)|npm install -g entroly && entroly init| Same engine, nothing Python required | |"I want one binary, no runtime."(Rust user)|cargo build --release --bin entroly-rs --features proxy(fromentroly-core/) | A single native program with no dependencies | |"I use Claude Code / Cursor / Windsurf / VS Code."(MCP user)|entroly attach create --client claude --project . --ttl 4h --install(orentroly initfor Cursor/VS Code) | Your editor gets compression, receipts, and recovery as built-in tools — access expires on its own, and you change zero code | |"I'm building my own app in Python."(SDK user)|from entroly import compress, compress_messages, optimize| Call it straight from your code, anywhere you assemble a prompt | |"I have an API key and my own app."(proxy user)|entroly proxy→ pointANTHROPIC_BASE_URL/OPENAI_BASE_URL/GOOGLE_GEMINI_BASE_URLatlocalhost:9377| Every request gets optimized on the way past — no code changes on your side |Why bother:less unnecessary context reaches the model (lower bill, less distraction for the model), nothing is silently lost (every drop is recoverable and receipted), and you can prove it —entroly verify-claimsandentroly simulateshow real numbers on your own repo before you connect a paid key.

from entroly import compress, compress_messages, optimize compressed = compress(api_response, budget=2000) messages = compress_messages(messages, budget=30000) context = optimize(fragments, budget=8000, query="fix the login bug")

entroly compress response.json --out small.json entroly recover sha256:0b957c79... --out restored.json

Not mocked recordings — each video is rendered from a checked-in command that verifies its source artifact before printing a number.

entroly verify-claims— import, compression, receipts, WITNESS checks, recovery, proxy routing, replay. No API key.

On a frozen 24-case holdout, Entroly answered24/24; a published baseline answered18/24at roughly 1.5x the effective context.python scripts/readme_proof.py model-recovery

Omitted evidence recoveredbyte-exactafter a process restart, 66/66 payloads.python scripts/readme_proof.py restart-recovery

The question that matters:if you send less, does the AI start getting things wrong?These are standard public tests, run with and without Entroly.

How to read this:Retentionis how well the AI still answered — 100% means it did just as well on far less text.Token savingsis how much less was sent (and therefore paid for). Measured withgpt-4o-mini; intervals are Wilson 95% CIs.

Being straight with you:look at the SQuAD 2.0 row — accuracy wentdown(80% → 72%). Compression is a trade, not magic, and it doesn't win everywhere. That's whyentroly simulateexists: run it on your own project and see your own numbers before you commit to anything.

- Picks first, shrinks second— it works out which files actually answer your question,thencompresses them.
- Gives you the original back, exactly— anything left out can be restored character-for-character and checked against a fingerprint.
- Shows its work— a receipt for every decision: what was kept, what was left out and why, and what risk remains.
- Fact-checks answers— compares what the AI said against the evidence it was given, on your machine, without paying for a second AI call.
- Doesn't wreck your caching— keeps the unchanging parts of your prompt stable so your provider's discount for repeated text still applies.
- Rescues sessions before they crash— when a conversation grows too big, it trims recoverable output instead of letting the provider reject the request mid-task.
- Can route cheap work to cheap models— optional and fail-closed when uncertain.

NVIDIA Nemotron 3.5 Lightning with Ollama

Entroly supportsnemotron-3.5-lightningthrough its existing local Ollama discovery and OpenAI-compatible proxy path. This is a model-neutral integration: Entroly manages evidence selection, budgets, recovery handles, Context Receipts, and optional verification around the request; Ollama runs the model.

ollama pull nemotron-3.5-lightning python -m entroly.models discover ollama --inspect-ollama-context # Set ENTROLY_OPENAI_BASE=http://127.0.0.1:11434 in your shell, then: entroly proxy

Great fit:large repos where the agent only sees a few files at a time · chatty multi-turn agents · anywhere you want answers checked against evidence · cutting a real, growing AI bill.

Skip it:tiny repos or short prompts that already fit the budget · judgment-heavy tasks where you always want the full flagship model.

Compressing abadselection is still a bad selection. Entroly ranks first, then compresses — so the model gets structure, not just fewer tokens.

Apache-2.0 · local-first · no outbound analytics by default

pip install entroly && entroly go

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Create crafted UI components inspired by the best 21st.dev design engineers.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

ALAPI MCP Tools,Call hundreds of API interfaces via MCP

AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform

MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.

APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.