OpenOutreach

Open-source AI agent for B2B lead generation, describe your product, it finds the people who fit, explains why each one does, and emails them from your mailbox. Self-hosted CLI, one install.

Runssource: GitHubhomepagePythonApache-2.0commit 85c9367ed329

Python, Apache-2.0 licensed. The project labels itself: agentic, agentic ai, agentic workflow, ai agents, ai sdr, b2b, cold email and cold outreach.

OpenOutreach runs. An Argusic agent installed it in 22 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The openoutreach package is installed via uv, all 30 tests pass, Django migrations apply cleanly, and the CLI binary runs and reports configuration status.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.02 (measured)
recorded runs
2
last tested
stars
3,735
forks
665
open issues
0
watchers
47
size
16 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 OpenOutreach, 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.

  • pip3 install uv failed: PEP 668 external-managed-environment restriction1 minute
  • make setup failed because uv not in PATH in sh subshell1 minute
Install time
22 minutes
Cold machine to finish
2 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
pytest tests/ exited 0, 30 passed in 0.87s; openoutreach --help printed the CLI overview; manage.py migrate applied 46 migrations; openoutreach status reported incomplete configuration (expected without credentials)
Model tokens used
30,643
Exact commit tested
85c9367ed329
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.

- The CLI binary prints help and reports status correctly
- Two minor environment issues were encountered and resolved
tokens used
30,643
I have all the data I need. Let me compile the final report.
**Summary of findings:**
- `uv tool install openoutreach` installed the package and its dependencies from PyPI successfully
- `uv pip install -e ".[dev]"` installed the dev extras in a local venv
- All 46 Django migrations applied successfully
- All 30 tests pass (via both `pytest` and `make test`)
- The CLI binary prints help and reports status correctly
- Two minor environment issues were encountered and resolved

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 2 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.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 22 minutes to install, slower than the median of the 5 comparable projects Argusic has measured.

Of the 6 agentic projects Argusic has installed and timed, OpenOutreach was the 5th fastest to reach a running state, and 3 of 6 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.02
Argusic Runner1/3Runs100.000.03

Topics (from GitHub)

agenticagentic-aiagentic-workflowai-agentsai-sdrb2bcold-emailcold-outreachemail-automationicplead-generationlead-qualificationllmoutreachprospectingsales-automationsales-engagementsales-intelligencesdrself-hosted

Embed the badge

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

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

Questions

Does OpenOutreach run?
Yes. OpenOutreach runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test OpenOutreach?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 85c9367ed329. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test OpenOutreach?
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 OpenOutreach take to install?
22 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 OpenOutreach need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing OpenOutreach?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does OpenOutreach compare with the alternatives?
Of the 6 agentic projects Argusic has installed and timed, OpenOutreach was the 5th fastest to reach a running state, and 3 of 6 reached one at all.
Where is the evidence for OpenOutreach?
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