deeptide
Built by DeepSeek, for DeepSeek, a Swift-native macOS coding agent
Runs with mockssource: GitHubhomepageRustMITcommit b48688d56c3e
Rust, MIT licensed. The project labels itself: codex harness, coding agent, deepseek, deepseek harness, dsh plugin, macos and swift.
deeptide runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
DeepTide Rust workspace builds, CLI runs in local-echo mode and against a mock OpenAI endpoint, all 1314 tests pass, GUI launches on virtual display, npm package entrypoint works under Bun.
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 86 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.
- Bun not installed (no unzip binary)2 minutes
- Rust toolchain not installed1 minute
- Mock server script had syntax error in HTTPServer invocation1 minute
- Install time
- 10 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- `cargo test` exited 0 with 1314 tests passed; `deeptide --version` printed 'deeptide-rs 0.2.0'; `deeptide --provider ollama --print -p 'Hello'` against a mock OpenAI server returned 'Hello! This is a mock AI response.'; `deeptide-gui` launched and stayed alive on Xvfb display; `bun bin.js --version` printed '0.11.25 (DeepTide CLI)'
- Model tokens used
- 364,055
- Exact commit tested
- b48688d56c3e
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 364,055 Let me produce the final report with a full summary of the results. **Total time: ~10 minutes** (started ~16:17, finished ~16:27). Here's what happened: **Rust workspace build and test:** Clean build on first try after installing Rust. 1314 tests pass … **GUI binary:** Built and launches on the virtual display. The `deeptide-gui` binary starts a windo… **npm package:** Installed (`npm install` added 290 packages). The `bin.js` entrypoint works under … **End-to-end verification with mock server:** I stood up an Argusic-compatible mock server on port … **Errors encountered and fixed:** - Rust not installed → installed via rustup (rustc 1.99.0) - Bun not installed → downloaded prebuilt linux-x64 binary from GitHub releases, extracted with Pyt… - Mock server script had a syntax error (missing RequestHandlerClass argument) → fixed
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
- Installed in 10 minutes.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Unverified | 80.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.09 |
Topics (from GitHub)
codex-harnesscoding-agentdeepseekdeepseek-harnessdsh-pluginmacosswift
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deeptide)Questions
- Does deeptide run?
- deeptide runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test deeptide?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b48688d56c3e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test deeptide?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does deeptide take to install?
- 10 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 deeptide need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing deeptide?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for deeptide?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.