# majacinka/crewai-experiments

Experiments with local as well as models available through an api

Repository: https://github.com/majacinka/crewai-experiments
Canonical: https://ross.abutalabs.com/products/crewai-experiments
Language: Python
License Family: other
Last push: 2024-05-05T01:50:11+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 68
- inputs: {"age_days": 963, "days_push": 851, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1017, forks 252 (observed 2026-08-28T04:03:14.615172+00:00)

## What it is
A collection of experiments with the CrewAI multi-agent framework, testing local models via Ollama and API models like GPT-4 and Gemini Pro on tasks such as startup idea evaluation and AI newsletter generation. It documents how well various 7B-13B open models perform at agent tasks including tool use.

## Use cases
- compare local llms for crewai agent tasks
- build an ai newsletter with agents
- evaluate which ollama models handle tool use
- learn crewai multi-agent workflows
- test startup ideas with ai agents
- classify emails with llm agents

## When to choose
- you want a practical comparison of local LLMs on agent workloads
- you are learning CrewAI with concrete example projects
- you want reference code for agent-based newsletter generation

## When to avoid
- you need a production-ready or maintained library
- you need a licensed, supported codebase
- you want guaranteed up-to-date model benchmarks

## Facets
- artifact type: learning-resource
- maturity: experimental
- function: agent-framework, llm-inference, web-scraping, nlp
- domain: artificial-intelligence, large-language-models, tutorials
- platform: python, self-hosted, cross-platform
- tags: crewai, ollama, local-llms, multi-agent, experiments, newsletter-generation, ai-agents

## Member repositories
- majacinka/crewai-experiments (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:14.615172+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 2026-08-30T07:11:13.744997+00:00, confidence not recorded.
  - readme: https://github.com/majacinka/crewai-experiments (fetched 2026-08-28T04:03:14.615172+00:00, sha dc3fe6255604)
- Data as of 2026-08-30T08:39:29.467469+00:00.