coze-studio
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
Runs with mockssource: GitHubTypeScriptApache-2.0commit fefb05ff27be
TypeScript, Apache-2.0 licensed. The project labels itself: agent, agent platform, ai plugins, chatbot, chatbot framework, coze, coze platform and generative ai.
coze-studio runs, with stand-ins for the services it depends on. An Argusic agent installed it in 28.3 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Go backend builds cleanly and 45 of 50 test packages pass; the 5 failures all require Docker services (MySQL 3306, Redis, MinIO/NSQ) that are not available in this container; Python3 venv with document parser libs (pdfplumber, python-docx, pillow, httpx) is installed; Node v22.14.0 is available but frontend rush build was not invoked
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
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.
- bytedance/sonic v1.15.0/loader links runtime.lastmoduledatap on Go 1.24.05 minutes
- Node 18.19.1 installed but project requires >=213 minutes
- go binary not found in container2 minutes
- NVM shell sourcing fails in sh environment2 minutes
- 5 test packages fail: api/handler/coze, domain/knowledge/service, domain/memory/database/service, domain/workflow/internal/compose/test, infra/rdb/impl/rdb
- Install time
- 28 minutes
- Cold machine to finish
- 29 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- go test -ldflags='-checklinkname=0' -gcflags='all=-N -l' -count=1 ./... in backend/ returned 45 packages ok, 5 fail (all MySQL/Docker-dependent); go build -ldflags='-checklinkname=0' -o /tmp/opencoze main.go in backend/ succeeded producing 232MB binary; python3 scripts/setup/python.sh created venv and installed parser packages
- Model tokens used
- 647,493
- Exact commit tested
- fefb05ff27be
- 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.
=== INSTALL SUCCESS === Go binary built: yes Go tests pass count: 45 packages Go tests fail count: 5 packages (all infra-dependent) Python3 venv: ready Node v22: ready === FAILING PKGS === All 5 fail due to: dial tcp 127.0.0.1:3306 (MySQL not running via Docker) === BINARY === /tmp/opencoze built at 242MB, runs until MinIO/MySQL connection attempt tokens used 647,493
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
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, 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 28.3 minutes to install, slower than the median of the 45 comparable projects Argusic has measured.
Of the 46 agent projects Argusic has installed and timed, coze-studio was the 39th fastest to reach a running state, and 33 of 46 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.12 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.22 |
Topics (from GitHub)
agentagent-platformai-pluginschatbotchatbot-frameworkcozecoze-platformgenerative-aigokouzilow-code-aimultimodel-aino-coderagstudiotypescriptworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/coze-studio)Questions
- Does coze-studio run?
- coze-studio runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 28 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test coze-studio?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit fefb05ff27be. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test coze-studio?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does coze-studio take to install?
- 28.3 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 coze-studio need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing coze-studio?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does coze-studio compare with the alternatives?
- Of the 46 agent projects Argusic has installed and timed, coze-studio was the 39th fastest to reach a running state, and 33 of 46 reached one at all.
- Where is the evidence for coze-studio?
- 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.