plano

Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

Runssource: GitHubhomepageRustApache-2.0commit 003c36aea896

Rust, Apache-2.0 licensed. The project labels itself: ai gateway, ai gateway support, envoy, envoyproxy, gateway, generative ai, llm gateway and llm inference.

plano runs. An Argusic agent installed it in 15 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Plano native mode starts, health endpoint returns 200, CLI reports version 0.4.36, all Rust and Python tests pass.

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
$0.07 (measured)
recorded runs
1
last tested
stars
7,068
forks
484
open issues
145
watchers
52
size
67 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
15 minutes
Cold machine to finish
21 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
planoai up started native mode; curl localhost:12000/healthz returned 200; planoai down stopped cleanly; 110 Python CLI tests passed; 532 Rust lib tests passed; all cargo builds succeeded
Model tokens used
65,476
Exact commit tested
003c36aea896
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.

**Environment verification results:**
- **Python CLI**: installed via `uv sync`, all 110 pytest tests pass
- **Rust toolchain**: installed via `rustup`, WASM target `wasm32-wasip1` added
- **WASM plugins**: `prompt_gateway.wasm` and `llm_gateway.wasm` build successfully
- **brightstaff binary**: builds successfully
- **Rust lib tests**: 532 pass (231+62+224+11+4), 0 failures, 4 ignored
- **Native mode startup**: `planoai up` downloads Envoy, starts brightstaff + envoy, health endpoin…
- **Model endpoint**: responds with proper error when no providers configured
- **`planoai down`**: cleanly stops all processes
- **JS/TS apps**: install but require Node.js >=20.9.0 (container has 18.19.1) — documented as "Not…
- **Docker**: not available in container
- **No API keys needed** for the core proxy startup — keys only needed for LLM routing which is out…

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 15 minutes, faster than the median of the 4 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 Apache-2.0, as reported by its host.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 5 ai-gateway projects Argusic has installed and timed, plano was the 3rd fastest to reach a running state, and 4 of 5 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.
  • 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 Runner1/3Runs100.000.07

Topics (from GitHub)

ai-gatewayai-gateway-supportenvoyenvoyproxygatewaygenerative-aillm-gatewayllm-inferencellm-proxyllm-routingllmopsllmsopenaipromptproxyproxy-serverrouting

Embed the badge

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

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

Questions

Does plano run?
Yes. plano runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test plano?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 003c36aea896. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test plano?
The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does plano take to install?
15 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 plano need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing plano?
Nothing did, in the recorded run: zero errors between clone and running.
How does plano compare with the alternatives?
Of the 5 ai-gateway projects Argusic has installed and timed, plano was the 3rd fastest to reach a running state, and 4 of 5 reached one at all.
Where is the evidence for plano?
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.

Discussion