# VRSEN/OpenSwarm

Claude code for everything except coding

Repository: https://github.com/VRSEN/OpenSwarm
Canonical: https://ross.abutalabs.com/products/openswarm
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-26T02:31:48+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 94, release rhythm 93, longevity 10
- inputs: {"age_days": 144, "days_push": 39, "days_rel": 46, "gap_med": 0.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2854, forks 671 (observed 2026-08-28T04:07:25.716819+00:00)

## What it is
OpenSwarm is an open-source multi-agent system built on Agency Swarm that turns a single terminal prompt into complete deliverables like slide decks, research reports, data visualizations, documents, images, and videos. It coordinates eight specialized agents (orchestrator, deep research, data analyst, virtual assistant, etc.) with optional integrations to 10,000+ external services via Composio.

## Use cases
- generate investor pitch decks from a single prompt
- run deep web research with citations
- analyze data and produce quarterly reports with charts
- create marketing campaign documents and creative assets
- automate writing, scheduling, and messaging tasks
- generate product launch videos with animations

## When to choose
- you want one-prompt generation of polished deliverables from the terminal
- you prefer a fully open-source, forkable multi-agent system
- you need specialized agents coordinated by an orchestrator rather than one generalist
- you want external service integrations like Gmail, Slack, and GitHub

## When to avoid
- you need a coding assistant - this explicitly targets non-coding tasks
- you require a graphical UI rather than a terminal workflow
- you need guaranteed output quality without reviewing agent-generated content
- you want a lightweight single-agent tool instead of a multi-agent setup

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, data-visualization, nlp, cli
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: multi-agent, orchestration, claude-code-alternative, content-generation, deep-research, agency-swarm, terminal-app, ai-agents, automation, command-line

## Member repositories
- VRSEN/OpenSwarm (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:25.716819+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 2026-08-30T07:36:45.041454+00:00, confidence not recorded.
  - readme: https://github.com/VRSEN/OpenSwarm (fetched 2026-08-28T04:07:25.716819+00:00, sha 0fcc46af6ef6)
- Data as of 2026-08-30T08:39:29.467469+00:00.