forge

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

Runssource: GitHubPythonMITcommit 236deda3a80f

Python, MIT licensed. The project labels itself: agentic ai, agentic workflow, agents, function calling, llama cpp, llamafile, llm and ollama.

forge runs. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

forge-guardrails 0.9.5 installed with dev dependencies; 1571 unit tests pass; core, proxy, guardrails, and client modules all import cleanly.

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
$0.02 (measured)
recorded runs
2
last tested
stars
2,250
forks
173
open issues
3
watchers
14
size
5 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.

Install time
3 minutes
Cold machine to finish
6 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
Model tokens used
28,042
Exact commit tested
236deda3a80f
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.

How the result was proved
runs before 2026-09-07 did not record the command used to check the result
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.

exec
/bin/sh -lc 'cd /work/repo && /home/runner/forge-venv/bin/python -m pytest tests/unit/ --tb=no -q 2…
 succeeded in 7078ms:
........................................................................ [ 87%]
........................................................................ [ 91%]
........................................................................ [ 96%]
...........................................................              [100%]
1571 passed in 6.36s
All 1571 unit tests pass. The project is a Python library for LLM tool-calling guardrails — it does…
tokens used
28,042
All 1571 unit tests pass. The project is a Python library for LLM tool-calling guardrails — it does…

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 3 minutes, faster than the median of the 7 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • 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 8 agentic-ai projects Argusic has installed and timed, forge was the 3rd fastest to reach a running state, and 5 of 8 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.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner1/3Runs100.000.02
Argusic Runner2/3Unverified80.000.01

Topics (from GitHub)

agentic-aiagentic-workflowagentsfunction-callingllama-cppllamafilellmollamapythonself-hostedtool-calling

Embed the badge

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

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

Questions

Does forge run?
Yes. forge runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test forge?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 236deda3a80f. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test forge?
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 forge 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 forge need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing forge?
Nothing did, in the recorded run: zero errors between clone and running.
How does forge compare with the alternatives?
Of the 8 agentic-ai projects Argusic has installed and timed, forge was the 3rd fastest to reach a running state, and 5 of 8 reached one at all.
Where is the evidence for forge?
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