Who is clew-custos for?

clew-custos is an open-source project built for AI researchers.

Does clew-custos have a free plan?

Yes — clew-custos is open source under the MIT license and free to use.

What platforms does clew-custos run on?

clew-custos runs on the command line.

Is clew-custos still active?

The GitHub repository shows 135 commits in the last 90 days.

What are alternatives to clew-custos?

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

Is clew-custos open source?

Yes — clew-custos is open source under the MIT license, developed on GitHub.

Back to the index

clew-custos

PyPIInfrastructure

clew-custos is an open-source CLI tool that analyzes traces from multi-agent LLM systems to detect wasteful cycles and inefficiencies. It helps AI researchers and engineers optimize token usage and improve the efficiency of agent-based workflows.

Open SourceMITCLI

Visit PyPI

1star

5features

2026since

Overview

5 features

In the LLM eval & observability space, clew-custos takes a focused approach. It focuses on identifying and reducing inefficiencies in multi-agent LLM workflows by detecting wasteful cycles in traces. clew-custos is an open-source project aimed at AI researchers. clew-custos is open source under the MIT license. It ships for the command line.

clew-custos first shipped in 2026. The project is developed in the open on GitHub with 135 commits in the last 90 days. Among its 5 catalogued features are trace analysis, cycle detection, and LLM observability.

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

Trace analysis
Cycle detection
LLM observability
Token cost tracking
CLI interface

Built with & integrations

AI providers

local_oss

Runs on

CLI

Trust & compliance

License

MIT

Verified signals

HTTPSOpen SourceFree tierGitHub · ★ 1Active maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed19 Jul · 15:00 UTC
clew-custos verified against its public source
Source: PulseGate · Open

Frequently asked questions about clew-custos

What does clew-custos do?: Clew-custos focuses on identifying and reducing inefficiencies in multi-agent LLM workflows by detecting wasteful cycles in traces. It is catalogued under LLM eval & observability on PulseGate.
Who is clew-custos for?: clew-custos is an open-source project built for AI researchers.
Does clew-custos have a free plan?: Yes — clew-custos is open source under the MIT license and free to use.
What platforms does clew-custos run on?: clew-custos runs on the command line.
Is clew-custos still active?: The GitHub repository shows 135 commits in the last 90 days.
What are alternatives to clew-custos?: Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and COHESION.constraintloop trajectory-judge COHESION
How long has clew-custos been around?: clew-custos first shipped in 2026.
Is clew-custos open source?: Yes — clew-custos is open source under the MIT license, developed on GitHub.

At a glance

Platforms: Cli
Languages: English
Open source: Yes · ★ 1
License: MIT
First seen: 19 Jul 2026
Built for: AI researchers
Model: Open source
Solves: Identifying and reducing inefficiencies in multi-agent LLM workflows by detecting wasteful cycles in traces.

Registered as

GitHub: JEONSEWON/Clew-by-Custos
PyPI: clew-custos

Developer

Jeonsewon

Solo developer

GitHub

Open source

View on GitHub

Stars: 1
Forks: 0
Open issues: 0
Last commit: 19 Jul 2026
Commits 90d: 135
Contributors: 1
Authorship: Solo
Default branch: main

Live coverage

Identity confidence: Low · 64
Indexed: 19 Jul 2026
Lifecycle: Unverified
First seen: Jul 2026
Last seen: 19 Jul 2026

Identity audit (12)

Slug: clew-custos-pypi-org
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 19 Jul 2026
Timeline basis: Indexed-at chronology (no inferred launch/funding milestones).
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: 24 Jul 2026
Canonical URL: https://pypi.org/project/clew-custos

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