Whale

Whale, blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

Runs with mockssource: GitHubhomepageGoMITcommit 676a0a228882

Go, MIT licensed. The project labels itself: coding agent, deepseek, deepseek agent, deepseek cli, deepseek coding agent, go, llm and mcp.

Whale runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Whale v0.0.0 builds from source with Go 1.26.8, all 53 test packages pass, the binary runs and reports its version, and CLI commands including help and exec function correctly (the latter returns the expected missing-API-key error).

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
2
last tested
stars
935
forks
75
open issues
19
watchers
37
size
6 MB
created
last push

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.

Install time
10 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
go run ./cmd/dev test exited 0 with 53 ok results; bin/whale --version returned v0.0.0-20260810160144-676a0a228882+dirty; bin/whale --help printed usage with 8 available commands; bin/whale exec correctly reports missing API key with no crash
Model tokens used
54,680
Exact commit tested
676a0a228882
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.

Error: exit 1
Usage:
  whale exec [prompt] [flags]
Flags:
      --attach stringArray   Attach a local file to the prompt
  -h, --help                 help for exec
      --json                 Emit machine-readable JSON output
      --mode string          Run in a specific mode (agent|ask|plan); overrides the session's saved…
All checks complete. The project builds, passes all 53 test packages, and the binary runs (it corre…
tokens used
54,680
All checks complete. The project builds, passes all 53 test packages, and the binary runs (it corre…

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

  • Nothing broke on the way: zero errors between clone and running.
  • 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.
  • Took 10 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.

Of the 6 coding-agent projects Argusic has installed and timed, Whale was the 4th fastest to reach a running state, and 1 of 6 reached one at all.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.04
Argusic Runner1/3Runs with mocks92.000.07

Topics (from GitHub)

coding-agentdeepseekdeepseek-agentdeepseek-clideepseek-coding-agentgollmmcpskillsterminal

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/Whale.svg)](https://argusic.com/subject/whale)

Questions

Does Whale run?
Whale runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test Whale?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 676a0a228882. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Whale?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Whale 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 Whale need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Whale?
Nothing did, in the recorded run: zero errors between clone and running.
How does Whale compare with the alternatives?
Of the 6 coding-agent projects Argusic has installed and timed, Whale was the 4th fastest to reach a running state, and 1 of 6 reached one at all.
Where is the evidence for Whale?
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.

Discussion