Swahili agent-task evaluation suite for the East Africa coordination stack — model-agnostic seed benchmark (46 tasks: server routing, term grounding, cascade routing).
Project description
kipimo
Over one hundred million people coordinate their lives in Swahili, yet no benchmark measures whether an AI agent can route their requests correctly — send money, check drought status, find a clinic, verify a worker's credentials. Agents targeting East Africa are evaluated on English tasks and deployed on faith.
kipimo (Swahili: a measure) is a model-agnostic seed benchmark for exactly that gap: 46 tasks across three types, with golds machine-derived from authoritative sources — the coordination-stack registry and the live africa-coord-bus routing table — never from memory.
| Type | n | What it measures | Metric |
|---|---|---|---|
server_routing |
25 | Swahili request → correct stack server (payments, tax, health, land, labour…) | exact |
term_grounding |
14 | Swahili domain term → English meaning | exact (case-insensitive) |
cascade_routing |
7 | Coordination event → which sectors must be notified | set F1 |
Live leaderboard → — score any model in your browser, no keys.
Use it (any model, no API keys)
pip install kipimo
kipimo tasks > tasks.jsonl # feed to your agent however you like
kipimo template > preds.jsonl # fill "prediction": [...] per id
kipimo score preds.jsonl # per-type + overall report
The harness never calls a model — you generate predictions with whatever system you're evaluating; kipimo only scores. Any lab can publish comparable numbers.
Honesty box
- v0.1 is a seed set. 46 tasks establish the format and scoring; breadth comes from contributions.
- Swahili phrasing is simple-register and pending native-speaker review — that is issue #1, and corrections are the most valuable contribution possible.
- Scores measure stack-routing competence, not general Swahili fluency.
- Dataset: CC BY 4.0 (usable by everyone, including commercial labs — that's the point). Harness: MIT.
IP & Collaboration
MIT-licensed harness, CC BY 4.0 data. Feedback via GitHub Issues only — pull requests are not accepted; task corrections and additions via Issues are actively wanted. Full policy: docs/architecture/IP_POLICY.md. Security: see SECURITY.md.
Part of the East Africa coordination stack
- Install & run:
pip install reli-cli && reli list— 33 MCP servers on the official MCP Registry underio.github.gabrielmahia - Evaluate any model on Swahili agent tasks: kipimo · dataset · leaderboard
- Coordinate across servers: africa-coord-bus — offline-first event bus with a built-in Kenya routing table
- Datasets: huggingface.co/gmahia · Docs hub: nairobi-stack
Model-agnostic by design: closed APIs, open-weight models, and small distilled models are all first-class citizens.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kipimo-0.2.0.tar.gz.
File metadata
- Download URL: kipimo-0.2.0.tar.gz
- Upload date:
- Size: 11.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2699cb042c15751366854770f68e6b1e202652264ba0269a569f208360bf7fca
|
|
| MD5 |
019f8288f7a680677de0172a6225e2e6
|
|
| BLAKE2b-256 |
520ab93655e9d6830f7800a62f0d13b9f7b5844842f29e29df3ff8dcdfb97e18
|
File details
Details for the file kipimo-0.2.0-py3-none-any.whl.
File metadata
- Download URL: kipimo-0.2.0-py3-none-any.whl
- Upload date:
- Size: 9.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f43973baa91691c0618f6d5a81559596301fe5f1674d85eff4703d8418d1325a
|
|
| MD5 |
f01c1d5841ace39b68826d3772fcffab
|
|
| BLAKE2b-256 |
90107aaaa135cf088911ca2eebb510362ae561e5804d515d890f06c4b5f5a700
|