Comparison · Updated 2026-10-31
SuperCompress vs LeanCTX (lean-ctx)
Short answer: LeanCTX (lean-ctx) is local context gateway (read modes, shell hook, proxy). Where it runs: Locally (CLI, MCP, hooks, proxy). SuperCompress is hosted, query-aware compression that keeps the original lines answering the current question. Pick LeanCTX (lean-ctx) if you want a local, policy-aware gateway that controls what your agent reads, with search, memory and a code graph. Pick SuperCompress if your agent keeps pulling big tool results, logs or retrieved docs and only a few lines matter for the question at hand, and you want those lines kept verbatim.
Side by side
| LeanCTX (lean-ctx) | SuperCompress | |
|---|---|---|
| What it optimizes | File reads, shell output, requests | Input context (tool output, logs, files, MCP results, RAG) |
| How it decides | Local context gateway (read modes, shell hook, proxy) | Query-aware extraction of original lines |
| Where it runs | Locally (CLI, MCP, hooks, proxy) | Hosted API, plus an MCP tool and hooks for coding agents |
| Setup | Install script or cargo | npm install -g supercompress-proxy && supercompress setup |
| Licence | Apache-2.0 | Hosted service |
LeanCTX (lean-ctx)
A. LeanCTX (lean-ctx)
Best if you want a local, policy-aware gateway that controls what your agent reads, with search, memory and a code graph.
An Apache-2.0 'context gateway' that runs locally as a CLI, MCP server, shell hook and optional request proxy. It offers read modes, caching, deltas, search, a code graph, session memory and compression of common shell commands.
- How it works: Local context gateway (read modes, shell hook, proxy)
- Runs: Locally (CLI, MCP, hooks, proxy)
- Setup:
Install script or cargo - Licence: Apache-2.0
Strengths:
- Local and open source
- Broad surface: read modes, caching, search, graph, memory
- Optional wire-level proxy
Limitations:
- Large surface area to configure
- Shell compression is rule-based, not question-aware
- Proxy features carry their own compatibility limits
SuperCompress
B. SuperCompress (our product)
Best if your agent keeps pulling big tool results, logs or retrieved docs and only a few lines matter for the question at hand, and you want those lines kept verbatim.
Hosted, query-aware context compression. Your agent or app sends a bulky block (tool output, a log, a diff, a file read, an MCP result, retrieved docs) with the current question, and the hosted Neural Keep model keeps the original lines that answer it, word for word, and drops the rest.
- How it works: Query-aware extraction of original lines
- Runs: Hosted API, plus an MCP tool and hooks for coding agents
- Setup:
npm install -g supercompress-proxy && supercompress setup - Licence: Hosted service
Strengths:
- Keeps original lines verbatim, so error messages, paths, IDs and code survive exactly
- Query-aware: what is kept depends on the current question, not only on the content type
- One setup command wires an MCP tool into each detected coding agent (Claude Code, Cursor, Codex, Windsurf, Cline, Gemini CLI, OpenCode and more), plus hooks where supported
- HTTP API returns original_tokens and kept_tokens so you can measure on your own traffic
- Works with any model provider because the output is plain text
Limitations:
- Hosted: the context you compress is sent to the SuperCompress API
- Compresses input only; it does not change how verbose model replies are
- Not a code index or retrieval system; it shrinks what is already being sent
How to test any of these fairly
Every tool here, including ours, publishes its own numbers. Fewer tokens do not always mean a smaller bill once prompt caching, retries and extra agent turns are counted. Run the same tasks with and without a tool, check the tasks still succeed, and compare cost per finished task on your provider bill.
Disclosure: SuperCompress publishes this page and is listed first because it is ours. Every claim about other tools comes from their own docs or repositories as of 2026-10-31; tell us if anything is out of date and we will fix it.
See also: LeanCTX (lean-ctx) alternatives, all comparisons.
FAQ
Is SuperCompress better than LeanCTX (lean-ctx)?
They solve different parts of the problem. Best if you want a local, policy-aware gateway that controls what your agent reads, with search, memory and a code graph. Best if your agent keeps pulling big tool results, logs or retrieved docs and only a few lines matter for the question at hand, and you want those lines kept verbatim.
What is the main difference between SuperCompress and LeanCTX (lean-ctx)?
LeanCTX (lean-ctx) works on file reads, shell output, requests and runs locally (cli, mcp, hooks, proxy). SuperCompress works on input context and is hosted.
Can I use both?
Usually, if they act on different tokens. Measure cost per finished task with each on and off.