trueforge

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

Runssource: GitHubhomepageTypeScriptMITcommit 0fe346a7cb09

TypeScript, MIT licensed. The project labels itself: agent, agentic ai, agents, harness and harness engineering.

trueforge runs. An Argusic agent installed it in 2.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

pnpm install and pnpm build succeed, the TrueForge server boots on port 8790 in standalone mode with healthz (200), UI (200), OpenAPI docs (200), and catalog/sessions API endpoints (200) all responding correctly, and all 2845 tests pass across all 5 workspace 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 90 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
90 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
2
last tested
stars
6,491
forks
561
open issues
115
watchers
21
size
50 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.

Time lost to each failure while testing trueforge, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Node.js v18.19.1 detected, project requires >=22.14.00.5 minutes
Install time
3 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
pnpm test exited 0 (2845 passed, 1 skipped, 0 failed); curl 127.0.0.1:8790/healthz returned 200; curl 127.0.0.1:8790/ returned 200 with app shell; curl /api/v1/catalogs/model-providers returned 200 with catalog JSON; curl /api/v1/sessions returned 200 with empty data
Model tokens used
114,702
Exact commit tested
0fe346a7cb09
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.

- `curl 127.0.0.1:8790/api/v1/catalogs/model-providers` → **200** (returned catalog JSON)
- `curl 127.0.0.1:8790/api/v1/sessions` → **200** (returned `{"data":[],"pagination":...}`)
**Tests**: Full `pnpm test` passed (all packages, exit 0):
- `@truefoundry/trueforge-core`: 49 suites, 469 passed, 1 skipped
- `@truefoundry/trueforge-assistant-ui-runtime`: 22 files, 198 passed
- `@truefoundry/trueforge-ui`: 202 files, 1551 passed
- `@truefoundry/trueforge`: 68 suites, 609 passed
- `frontend`: 6 suites, 18 passed
Total: **2845 passed**, 1 skipped, 0 failed.
**Warnings (not errors)**:
- Local sandbox feature unavailable (bubblewrap, socat not installed) — expected in containers with…
- Sentry not configured — expected in local development.

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 2.5 minutes, faster than the median of the 137 comparable projects Argusic has measured.
  • 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.
  • Measured 2 times, so the result is not a one-off.

Of the 138 agent projects Argusic has installed and timed, trueforge was the 39th fastest to reach a running state, and 92 of 138 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 2.5 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.04
Argusic Runner1/3Runs80.000.12

Topics (from GitHub)

agentagentic-aiagentsharnessharness-engineering

Embed the badge

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

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

Questions

Does trueforge run?
Yes. trueforge runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test trueforge?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0fe346a7cb09. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test trueforge?
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 trueforge take to install?
2.5 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 trueforge need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing trueforge?
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 trueforge compare with the alternatives?
Of the 138 agent projects Argusic has installed and timed, trueforge was the 39th fastest to reach a running state, and 92 of 138 reached one at all.
Where is the evidence for trueforge?
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