parlant
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit ea737442b8ae
Python, Apache-2.0 licensed. The project labels itself: ai agents, ai alignment, customer service, customer success, gemini, genai, hacktoberfest and llama3.
parlant runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
Parlant v3.3.1 installs, imports, its server launches and responds on port 8800, and 113 of 115 non-engine tests pass when backed by the mock Emcie NLP server.
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 85.3 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.
- Emcie API key required as default NLP service5 minutes
- Missing chromadb module in prepare_migration.py at module level1 minute
- parlant CLI (client) cannot import JourneyTriggerUpdateParams from installed parlant-client v3.2.0
- Install time
- 5 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- pytest test suite: 113 passed, 2 failed across 12 test files. Server: 'parlant-server run --port 8800' with OPENAI_API_KEY=sk-fake printed 'Server is ready for some serious action' and responded 307 on root URL.
- Model tokens used
- 601,822
- Exact commit tested
- ea737442b8ae
- 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.
- test_context_variables: 13/13 Total: 113/115 passed (2 expected mock-limitation failures) Issues discovered/fixed: - Missing chromadb (installed as fix) - parlant CLI has version mismatch with parlant-client package - Server requires OPENAI_API_KEY (real credential) or runs via parlant-server 2026-09-26T02:00:10.102987Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… 2026-09-26T02:00:10.103033Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… 2026-09-26T02:00:10.103058Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… 2026-09-26T02:00:10.103067Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… tokens used 601,822
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
- Installed in 5 minutes.
- Licensed Apache-2.0, as reported by its host.
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.
- Hit 3 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 20 ai-agents projects Argusic has installed and timed, parlant was the 10th fastest to reach a running state, and 12 of 20 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 85.33 | 0.17 |
Topics (from GitHub)
ai-agentsai-alignmentcustomer-servicecustomer-successgeminigenaihacktoberfestllama3llmopenaipython
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/parlant)Questions
- Does parlant run?
- parlant 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 parlant?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ea737442b8ae. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test parlant?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does parlant 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 parlant need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing parlant?
- 3 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 parlant compare with the alternatives?
- Of the 20 ai-agents projects Argusic has installed and timed, parlant was the 10th fastest to reach a running state, and 12 of 20 reached one at all.
- Where is the evidence for parlant?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.