Yes — kipimo is open source under the MIT license and free to use.

What platforms does kipimo run on?

kipimo runs on the command line.

Is kipimo still maintained?

The GitHub repository shows 6 commits in the last 90 days.

What are alternatives to kipimo?

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

kipimo is developed by Gabriel Mahia.

Back to the index

kipimo

Name: kipimo
Author: Gabriel Mahia

PyPIInfrastructure

kipimo provides a model-agnostic evaluation suite for AI agents, focusing on Swahili-language tasks relevant to East Africa. It includes 46 tasks such as server routing and term grounding, enabling researchers and developers to benchmark agent performance in regional contexts.

Open SourceMITCLI

Visit PyPI

Overview

5 features

kipimo is a LLM eval & observability project. It focuses on evaluating and benchmarking AI agent tasks in Swahili for East African coordination stacks. It is built as an open-source project for AI researchers and developers working with Swahili or East African agent systems. The project is open source (MIT). kipimo is available on the command line.

It is developed by Gabriel Mahia, and it first shipped in 2026. The project is developed in the open on GitHub with 6 commits in the last 90 days. Among its 5 catalogued features are task evaluation, swahili support, and benchmark suite.

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

Task evaluation
Swahili support
Benchmark suite
Model-agnostic
CLI interface

Built with & integrations

Runs on

CLI

Trust & compliance

License

MIT

Verified signals

HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed5 Jul · 02:37 UTC
kipimo verified against its public source
Source: PulseGate · Open

Frequently asked questions about kipimo

What does kipimo do?: Kipimo focuses on evaluating and benchmarking AI agent tasks in Swahili for East African coordination stacks. It is catalogued under LLM eval & observability on PulseGate.
Who is kipimo for?: kipimo is an open-source project built for AI researchers and developers working with Swahili or East African agent systems.
Is kipimo free?: Yes — kipimo is open source under the MIT license and free to use.
What platforms does kipimo run on?: kipimo runs on the command line.
Is kipimo still maintained?: The GitHub repository shows 6 commits in the last 90 days.
What are alternatives to kipimo?: Similar projects tracked by PulseGate include constraintloop, trajectory-judge, and COHESION.constraintloop trajectory-judge COHESION
Who makes kipimo?: kipimo is developed by Gabriel Mahia.
When did kipimo launch?: kipimo first shipped in 2026.

At a glance

Platforms: Cli
Languages: English
Open source: Yes (GitHub)
License: MIT
First seen: 5 Jul 2026
Built for: AI researchers and developers working with Swahili or East African agent systems
Model: Open source
Solves: Evaluating and benchmarking AI agent tasks in Swahili for East African coordination stacks.

Registered as

GitHub: gabrielmahia/kipimo
PyPI: kipimo

Developer

Gabriel Mahia

Solo developer

GitHub

Open source

View on GitHub

Stars: 0
Forks: 0
Open issues: 0
Last commit: 5 Jul 2026
Commits 90d: 6
Contributors: 1
Authorship: Solo
Default branch: main

Live coverage

Identity confidence: Low · 64
Indexed: 5 Jul 2026
Lifecycle: Unverified
First seen: Jul 2026
Last seen: 5 Jul 2026

Identity audit (12)

Slug: kipimo-pypi-org
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 5 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: 18 Jul 2026
Canonical URL: https://pypi.org/project/kipimo

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