harmonist
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
Runssource: GitHubhomepagePythonMITcommit 6fd5941cce8c
Python, MIT licensed. The project labels itself: agent framework, agent system, ai agents, claude code, cursor ide, llm, multi agent framework and orchestration.
harmonist runs. An Argusic agent installed it in 30 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Harmonist pack integrates and enforces the agent protocol pipeline on Python 3.12, all 373 test assertions passed across 22 shell/Python test suites covering integration, hooks, upgrade, memory, telemetry, supply-chain, regression, and cross-platform paths; the sole gap is lsof(1) missing from the container, blocking 4 webhook-live-send scenarios
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.
- lsof not installed: test_telemetry_webhook.sh could not run its live-POST/retry scenarios (4 of 7 scenarios skipped)5 minutes
- Install time
- 30 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- python3 agents/scripts/smoke_test.py --json returned 2 scenarios, 7/7 steps passing; 373 test assertions across 22 test suites passed (integrate/deintegrate, upgrade, install_extras, supply_chain, smoke_test, memory, telemetry, git_hooks, run_regression, repomap, freshness, rules_conflicts, check_pack_health, and more)
- Model tokens used
- 48,432
- Exact commit tested
- 6fd5941cce8c
- 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.
# memory_privacy: 19, merge_agents_md: 15, extract_essentials: 9, freshness: 14 # verify_integration: 20, upgrade: 33, install_extras: 37, supply_chain: 23 # project_context: 17, repomap: 13, detect_regression: 20, onboard: 11 # rules_conflicts: 14, run_regression: 15, git_hooks: 7, telemetry: 19 # cross_platform: 17, checklist: 4 # Total = 373 (webhook's live tests couldn't complete due to missing lsof) \"" in /work/repo succeeded in 0ms: 2026-10-04T01:25:17.591577Z ERROR codex_core::session: failed to record rollout items: thread 01a10… 2026-10-04T01:25:17.591616Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 48,432
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 1 error 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 MIT, as reported by its host.
What did not, or is not known
- Took 30 minutes to install, slower than the median of the 13 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 14 agent-framework projects Argusic has installed and timed, harmonist was the 13th fastest to reach a running state, and 8 of 14 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)
agent-frameworkagent-systemai-agentsclaude-codecursor-idellmmulti-agent-frameworkorchestrationprompt-engineeringpython
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/harmonist)Questions
- Does harmonist run?
- Yes. harmonist runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test harmonist?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6fd5941cce8c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test harmonist?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does harmonist take to install?
- 30 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 harmonist need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing harmonist?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does harmonist compare with the alternatives?
- Of the 14 agent-framework projects Argusic has installed and timed, harmonist was the 13th fastest to reach a running state, and 8 of 14 reached one at all.
- Where is the evidence for harmonist?
- 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.