conductor
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
Runssource: GitHubhomepageJavaApache-2.0commit da325130588f
Java, Apache-2.0 licensed. The project labels itself: distributed systems, durable execution, grpc, java, javascript, microservice orchestration, orchestration engine and orchestrator.
conductor runs. An Argusic agent installed it in 28 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Conductor server runs on port 8080 with SQLite backend, listens on /api, answers health checks, registers and executes workflows, and all 1,365 non-Docker-dependent tests pass across core, common, rest, grpc, grpc-server, grpc-client, server, and sqlite-persistence modules.
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.
- 2 failing tests in conductor-ai module: MongoVectorDBTest and JDBCEndToEndTest require Docker, which is unavailable in this container.3 minutes
- Java 21 not installed in container. No package manager access (no root).2 minutes
- npm install -g failed: EACCES writing to /usr/local/lib/node_modules (no root).1 minute
- conductor workflow create failed: no server configured (CONDUCTOR_SERVER_URL not set by conductor server start).1 minute
- Install time
- 28 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- curl -s http://localhost:8080/api/health returned {'healthy':true}; conductor workflow create workflow.json succeeded; conductor workflow start -w hello_workflow --sync returned real JSON output; ./gradlew :conductor-core:test :conductor-common:test :conductor-rest:test :conductor-grpc:test :conductor-grpc-server:test :conductor-grpc-client:test :conductor-sqlite-persistence:test :conductor-server:test passed 1365 tests with 0 failures
- Model tokens used
- 235,118
- Exact commit tested
- da325130588f
- 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.
m = re.search(r'testsuite.*?tests=\\\"(\\d+)\\\".*?failures=\\\"(\\d+)\\\"', c)
if m:
total_tests += int(m.group(1))
total_failures += int(m.group(2))
print(f'Total tests: {total_tests}, Total failures: {total_failures}')
\"" in /work/repo
succeeded in 0ms:
Total tests: 1365, Total failures: 0
All clean — 1,365 tests across the core modules passed with zero failures. Let me compile the final…
tokens used
235,118
All clean — 1,365 tests across the core modules passed with zero failures. Let me compile the final…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.
- Installed in 28 minutes.
- Recovered from all 4 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
Topics (from GitHub)
distributed-systemsdurable-executiongrpcjavajavascriptmicroservice-orchestrationorchestration-engineorchestratorreactjsspring-bootworkflow-automationworkflow-engineworkflow-managementworkflows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/conductor)Questions
- Does conductor run?
- Yes. conductor runs. Argusic installed and launched it on a clean machine in 28 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test conductor?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit da325130588f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test conductor?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does conductor take to install?
- 28 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 conductor need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing conductor?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for conductor?
- 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.