harness-sdk
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
Runssource: GitHubhomepagePythonApache-2.0commit 15da9dca2cd6
Python, Apache-2.0 licensed. The project labels itself: agent framework, agentic, agentic ai, agents, ai, ai agents, anthropic and autonomous agents.
harness-sdk runs. An Argusic agent installed it in 3 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Python SDK strands-agents v0.1.dev1 and strands-harness v0.0.1.dev1 installed from source, both packages import correctly, and over 2,000 unit tests pass across both packages.
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 55 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.
- test_gather_runs_calls_concurrently flaky timing: expected < 1.1s, took 2.41s in container9 minutes
- test_call_tool_sync_image_content missing tests_integ/resources/yellow.png from repo root5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 68 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- pytest on strands-py: 990+308+321+719+465+53+507+ etc passed; harness-py: 155+13+49+9+13+ etc passed
- Model tokens used
- 150,142
- Exact commit tested
- 15da9dca2cd6
- 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.
- `tests/test_subagent.py` — **49 passed** - `tests/test_telemetry.py` — **9 passed** - `tests/tools/test_web_search.py` — **13 passed** - `tests/test_agent.py` — individual tests all pass (sampled 12+), suite too slow to run in full (e… - `tests/test_memory.py` — passes individually, full module too slow in container **Errors found:** | Error | Fix | Minutes | |-------|-----|---------| | `harness-py` flaky timing test `test_gather_runs_calls_concurrently`: expected <1.1s but containe… | `test_call_tool_sync_image_content` missing `yellow.png` when run from repo root (path relative t… | Some async-heavy test modules (`test_agent.py`, `test_agent_as_tool.py`, `test_agent_delegation.p… TypeScript SDK requires Node 22+ (container has Node 18) — not testable in this environment.
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.
- Ran without a GPU, so it does not need one to start.
- 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
- Took 3 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
- Hit 2 errors during setup, 1 of which were not solved.
Of the 9 agent-framework projects Argusic has installed and timed, harness-sdk was the 6th fastest to reach a running state, and 6 of 9 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.
- A quick evaluation: it was running 3 minutes after the clone.
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 | 90.00 | 0.30 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.54 |
Topics (from GitHub)
agent-frameworkagenticagentic-aiagentsaiai-agentsanthropicautonomous-agentsbedrockgenerative-aiharnessllmllm-agentmcpmulti-agent-systemsopenaipythonsdkstrands-agentstypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/harness-sdk)Questions
- Does harness-sdk run?
- Yes. harness-sdk runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test harness-sdk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 15da9dca2cd6. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test harness-sdk?
- The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does harness-sdk take to install?
- 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 harness-sdk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing harness-sdk?
- 2 things 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 harness-sdk compare with the alternatives?
- Of the 9 agent-framework projects Argusic has installed and timed, harness-sdk was the 6th fastest to reach a running state, and 6 of 9 reached one at all.
- Where is the evidence for harness-sdk?
- 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.