piqc is an open-source project built for ML infrastructure engineers.

Yes — piqc is open source under the BUSL-1.1 license and free to use.

What platforms does piqc run on?

piqc runs on the command line. It can also be self-hosted.

Is piqc still maintained?

The GitHub repository shows 41 commits in the last 90 days.

What projects are similar to piqc?

Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and DeFake.

piqc is developed by paralleliq.

Back to the index

piqc

Name: piqc
Author: paralleliq

PyPIInfrastructure

piqc is an open-source fact collector designed for vLLM-based AI/ML inference workloads running on Kubernetes. It gathers telemetry to detect GPU underutilization, idle resources, and misallocated instance types. Built for operators managing large-scale inference fleets, it helps optimize hardware costs and efficiency.

Open SourceBUSL-1.1CLISelf-hosted

Visit PyPI

15stars

1fork

3features

2025since

Overview

3 features

In the LLM eval & observability space, piqc takes a focused approach. It focuses on identifying and quantifying GPU waste, idle capacity, and incorrect resource tiering in large-scale AI inference fleets. It is built as an open-source project for ML infrastructure engineers. The project is open source (BUSL-1.1). It runs on the command line, and it can be self-hosted.

paralleliq builds and maintains piqc, and it first shipped in 2025. Development happens publicly on GitHub with 15 stars and 41 commits in the last 90 days. Key capabilities include GPU Monitoring, Inference Fleet Insights, and Kubernetes Integration.

Summary written by a language model from the project’s public pages.

GPU Monitoring
Inference Fleet Insights
Kubernetes Integration

Built with & integrations

Runs on

CLISelf-hosted

Trust & compliance

License

BUSL-1.1

Verified signals

HTTPSOpen Source GitHub · ★ 15Active maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed31 Jul · 06:31 UTC
piqc verified against its public source
Source: PulseGate · Open

Frequently asked questions about piqc

What does piqc do?: Piqc focuses on identifying and quantifying GPU waste, idle capacity, and incorrect resource tiering in large-scale AI inference fleets. It is catalogued under LLM eval & observability on PulseGate.
Who should use piqc?: piqc is an open-source project built for ML infrastructure engineers.
Is piqc free?: Yes — piqc is open source under the BUSL-1.1 license and free to use.
What platforms does piqc run on?: piqc runs on the command line. It can also be self-hosted.
Is piqc still maintained?: The GitHub repository shows 41 commits in the last 90 days.
What projects are similar to piqc?: Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and DeFake.constraintloop trajectory-judge DeFake
Who develops piqc?: piqc is developed by paralleliq.
How long has piqc been around?: piqc first shipped in 2025.

At a glance

Platforms: Cli
Languages: English
Open source: Yes · ★ 15
License: BUSL-1.1
Built for: ML infrastructure engineers
Model: Open source
Solves: Identifying and quantifying GPU waste, idle capacity, and incorrect resource tiering in large-scale AI inference fleets.

Registered as

GitHub: paralleliq/piqc
PyPI: piqc

Developer

paralleliq

Small team

GitHub

Open source

View on GitHub

Stars: 15
Forks: 1
Open issues: 7
Last commit: 31 Jul 2026
Commits 90d: 41
Contributors: 4
Authorship: Small team
Default branch: main

Live coverage

Identity confidence: Low · 64
Indexed: 31 Jul 2026
Lifecycle: Alive
Last seen: 31 Jul 2026

Identity audit (13)

Slug: piqc-pypi-org
Lifecycle state recorded: 31 Jul 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 31 Jul 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Last updated: 31 Jul 2026
Canonical URL: https://pypi.org/project/piqc

Ship this? Send a correction — no account, and you get a link to follow it.

Also in LLM eval & observability

Same category — not a similarity match