sqz
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.
Runssource: GitHubhomepageRustApache-2.0commit ff33708e2a31
Rust, Apache-2.0 licensed. The project labels itself: agentic ai, ai agents, claude code, cli, codex, coding agents, context compression and context window.
sqz runs. An Argusic agent installed it in 14 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The sqz workspace builds and its 1715 tests pass; sqz 2.1.1 runs, compresses with byte-exact expand, the sqz-mcp stdio server completes the MCP initialize handshake and lists 7 tools, and the local proxy answered HTTP 200 on POST /v1/chat/completions with a compressed body.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- no Rust toolchain in container (cargo/rustc not found)2 minutes
- global npm install failed: EACCES mkdir /usr/local/lib/node_modules/sqz-cli (no root)1 minute
- Install time
- 14 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- cargo test --workspace exited 0 (12 suites, 1715 passed); sqz --version printed 'sqz 2.1.1'; sqz doctor reported all-ok; compress produced §ref: dedup tokens expanded byte-exact; sqz-mcp answered initialize with serverInfo sqz-mcp 2.1.1; curl -X POST http://127.0.0.1:8898/v1/chat/completions returned HTTP 200
- Model tokens used
- 264,529
- Exact commit tested
- ff33708e2a31
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 264,529 All verification is done. The full run took about 14 minutes including two full test-suite passes a… **What I did** - Read the README install paths; no Rust toolchain was present, so I installed Rust 1.99.1 via rust… - `cargo build --workspace --all-targets` succeeded (39.8s, warnings only) and `cargo build --relea… - `cargo test --workspace` passed: 12 suites, 1715 passed, 0 failed (verified twice, including doc-… - Exercised the binaries: `sqz --version` → `sqz 2.1.1`; `sqz init` created hooks for all detected … **Errors encountered and fixes** 1. Global npm install failed (`EACCES` on `/usr/local`) — fixed by installing with a user `--prefix… 2. No Rust toolchain / no `cargo` — fixed by installing rustup in the user HOME. Final one-line result:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 14 minutes to install, slower than the median of the 26 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 27 agentic-ai projects Argusic has installed and timed, sqz was the 18th fastest to reach a running state, and 16 of 27 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agentic-aiai-agentsclaude-codeclicodexcoding-agentscontext-compressioncontext-windowcost-optimizationcursordeveloper-toolsllmllmsmcpmcp-serveropen-sourceprompt-cachingrusttoken-optimizationtokens
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/sqz)Questions
- Does sqz run?
- Yes. sqz runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test sqz?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ff33708e2a31. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test sqz?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does sqz take to install?
- 14 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does sqz need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing sqz?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does sqz compare with the alternatives?
- Of the 27 agentic-ai projects Argusic has installed and timed, sqz was the 18th fastest to reach a running state, and 16 of 27 reached one at all.
- Where is the evidence for sqz?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.