What is nimble-triage?

A Python package and CLI that pipes your logs through a local decision model: Nimble, served by Ollama, labels every entry with a severity, a category and a needs-attention flag. By default nothing leaves your machine.

Does nimble-triage need an API key or paid account?

No. In the default full mode the judgments come from Nimble through Ollama's /v1/systemone endpoint on your own machine, and the README states no API key is required. You do need the roughly 9 GB model download and probably 16 GB of RAM.

What do the scores and symbols in the output mean?

The number is the model's attention score, a ! marks entries meeting the attention threshold, and a ? marks severity confidence below 0.6. The README says scores rank entries but should not be read as calibrated guarantees.

How do I run nimble-triage on a log file?

Install the package, then run the documented command nimble-triage --format pretty app.log. The digest shows that invocation and its pretty table output, but the excerpt stops inside the requirements section, so install details are not captured here.

What exactly does each log entry get?

Three things: a severity, a category such as auth, network, database or application, and a needs-attention flag, computed in a single pass. The sample run labels five entries and reports that two need attention.

Does nimble-triage send my logs to the cloud?

Not by default: the README says logs are sent only to Ollama running on your own machine. Nothing in the captured text documents any remote backend, so treat it as a local-only tool.

Who built nimble-triage and what shape is the project in?

It is a MIT-licensed Python project by GauravGupta035, created 2026-10-02 and last pushed 2026-10-15, with zero stars when the sweep ran. It was found through the GitHub topic systemone.

Jev directory

CommunityJev Tools & CLIs

Nimble Triage

A Python CLI that pipes log files through a local decision model: Nimble, served by Ollama, gives every entry a severity, a category and a needs-attention flag, computed entirely on your own machine.

See highlights Open github.com

Stars: 0
Language: Python
License: MIT
Reading time: 2 min
Published by: Community
Author: GauravGupta035
Last verified: Oct 2026

GauravGupta035/nimble-triage

User repository on GitHub

View on GitHub

A PyPi package to pipe your logs through a local decision model (Ollama's Nimble): severity, category and needs-attention for every entry, computed on your machine.

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity github cli observability

Works forJev for Classification Jev for Scoring

Used inJev for Software & DevTools

Languages: Python
Platforms: CLI
Capabilities: Open sourceRuns locally

Highlights

Runs Nimble through Ollama's /v1/systemone endpoint, so no API key is required and logs stay on your machine by default.
Every log entry gets a severity, a category and a needs-attention flag; the pretty output marks attention with ! and low severity confidence with ?.
The sample run labels 5 entries and reports 2 needing attention, with per-entry attention scores from 0.05 up to 1.00.
Requires Python 3.10+, Ollama 0.35.0+ (the first release with /v1/systemone) and the roughly 9 GB Nimble model; 16 GB of RAM is recommended.
MIT licensed, created 2026-10-02 and last pushed 2026-10-15, with zero stars at sweep time.

Quickstart

bash

nimble-triage --format pretty app.log

Watch out

README and GitHub metadata reviewed 2026-10-17; the excerpt truncates inside the Nimble download step, so the rest of setup and any accuracy claims are not evidenced. The README itself says attention scores rank entries but are not calibrated guarantees.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Nimble Triage

Highlights

Quickstart

Questions about this entry

What is nimble-triage?

Does nimble-triage need an API key or paid account?

What do the scores and symbols in the output mean?

How do I run nimble-triage on a log file?

What exactly does each log entry get?

Does nimble-triage send my logs to the cloud?

Who built nimble-triage and what shape is the project in?

More Jev resources like this

From the Jev guides

From the Jev AI model community