# lastmile-ai/aiconfig

AIConfig is a config-based framework to build generative AI applications.

Repository: https://github.com/lastmile-ai/aiconfig
Canonical: https://ross.abutalabs.com/products/aiconfig
Homepage: https://aiconfig.lastmileai.dev
Language: Python
License: MIT
License Family: permissive
Topics: ai, developer-tools, generative-ai, llm, llm-ops
Last push: 2026-02-10T02:57:20+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 8, longevity 78
- inputs: {"age_days": 1097, "days_push": 204, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1087, forks 91 (observed 2026-08-28T04:03:32.348590+00:00)

## What it is
AIConfig is an open-source framework that manages generative AI prompts, models, and model parameters as JSON-serializable configs, separating AI behavior from application code. It includes Python and Node SDKs plus a VS Code editor extension for prototyping, versioning, and evaluating AI prompts.

## Use cases
- manage llm prompts as version-controlled config files
- separate prompt engineering from application code
- prototype and edit ai prompts in vs code
- evaluate and monitor generative ai model parameters
- build production generative ai applications with python or node
- share and iterate on prompt configs across a team

## When to choose
- you want prompts and model parameters version controlled separately from code
- you build llm apps in Python or Node.js and need a config-driven workflow
- you want a visual editor for iterating on prompts
- you need reproducible, evaluable generative AI behavior

## When to avoid
- you need a full llm observability or tracing platform rather than prompt config management
- your app uses a single hardcoded prompt and simple calls
- you need fine-grained agent orchestration beyond prompt/model config
- you work outside Python and Node.js ecosystems

## Facets
- artifact type: framework
- maturity: active
- function: prompt-engineering, llm-inference, configuration-management, developer-tools, sdk
- domain: large-language-models, developer-tools, artificial-intelligence
- platform: python, cross-platform, editor-plugin
- tags: llm-ops, prompt-management, config-as-code, generative-ai, vscode-extension, version-control, automation, nodejs

## Member repositories
- lastmile-ai/aiconfig (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.348590+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:28.163073+00:00, confidence not recorded.
  - readme: https://github.com/lastmile-ai/aiconfig (fetched 2026-08-28T04:03:32.348590+00:00, sha 46aed5fa0531)
- Data as of 2026-08-30T08:39:29.467469+00:00.