Patter

Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines, Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.

Runs with mockssource: GitHubhomepagePythonMITcommit f01875136816

Python, MIT licensed. The project labels itself: ai agent, ai phone agent, hermes agent, llm, mastra, open source, openai and openclaw.

Patter runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Python SDK installs and runs 3037 passing tests. TypeScript SDK installs, compiles with zero errors, builds, and all test files pass. Python CLI responds with usage text. Two code bugs (SSRF IPv4-mapped blocking, mtime tiebreaker) and one tooling issue (vitest/vite version mismatch) were diagnosed and fixed.

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 71 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
71 / 100
cost of the verifying run
$0.29 (measured)
recorded runs
2
last tested
stars
1,087
forks
128
open issues
11
watchers
6
size
13 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 Patter, 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.

  • SSRF is_internal_ip() incorrectly blocks IPv4-mapped public addresses like ::ffff:8.8.8.8 due to is_reserved on the IPv6 wrapper range10 minutes
  • TypeScript tests fail with ERR_REQUIRE_ESM on Node 18 because vitest@3 bundles vite@7 requiring ESM8 minutes
  • Python test_hermes_cli function _find_call_dir mtime tiebreaker fails when two dirs share the same filesystem timestamp2 minutes
Install time
5 minutes
Cold machine to finish
41 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
Python: 'pytest tests/ -q' exited 0, 3037 passed, 17 skipped. TypeScript: 'vitest run' across all test files, 0 failures. TypeScript: 'tsc --noEmit' exited 0. Python CLI: getpatter --help returns usage.
Model tokens used
536,763
Exact commit tested
f01875136816
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

tokens used
536,763
All done! Here's the final result:
**Python SDK**: 3037 tests passed, 17 skipped, 2 xfailed (100% of run tests)
**TypeScript SDK**: All test files pass (ran in multiple batches to avoid OOM, every file reported …
**TypeScript**: compiles with zero errors (`tsc --noEmit`), builds to `dist/`
**Python CLI**: responds to `--help` correctly
**Pre-commit**: passes clean
**Errors found & fixed:**
1. **SSRF IPv4-mapped false positive** — `is_internal_ip()` flagged `::ffff:8.8.8.8` as internal be…
2. **`_find_call_dir` mtime tiebreaker** — Two test directories created within the same filesystem …
3. **vitest version incompatibility** — Node 18 couldn't run vitest@3. Downgraded to [email protected], pl…

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

  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 5 minutes to install, slower than the median of the 83 comparable projects Argusic has measured.

Of the 84 ai-agent projects Argusic has installed and timed, Patter was the 45th fastest to reach a running state, and 58 of 84 reached one at all.

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 Runner2/3Runs with mocks92.000.29
Argusic Runner1/3Did not run50.000.17

Topics (from GitHub)

ai-agentai-phone-agenthermes-agentllmmastraopen-sourceopenaiopenclawpythonrealtime-apisdkspeech-to-texttelnyxtext-to-speechtwiliotypescriptvapi-alternativevoice-agentvoice-aivoicebot

Embed the badge

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

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

Questions

Does Patter run?
Patter runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test Patter?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit f01875136816. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Patter?
The run that produced this verdict cost $0.29: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Patter take to install?
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 Patter need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Patter?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does Patter compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, Patter was the 45th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for Patter?
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