# Runfusion/Fusion

Your Software Factory - build faster and better with multi node agents that work 24/7

Repository: https://github.com/Runfusion/Fusion
Canonical: https://ross.abutalabs.com/products/runfusion-fusion
Homepage: http://runfusion.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent, agentic-workflow, agents, llm, orchestration-framework
Last push: 2026-09-02T22:28:44+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 100, longevity 10
- inputs: {"age_days": 143, "days_push": 0, "days_rel": 1, "gap_med": 0, "n_releases_24m": 58}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1193, forks 149 (observed 2026-09-03T02:15:08.061739+00:00)

## What it is
Fusion is an open-source multi-agent orchestrator that acts as a 'software factory': AI agents plan, build, review, and ship code from plain-language task descriptions. It coordinates tasks, agents, git worktrees, and multiple LLM models (local or cloud) across multiple machines via a shared kanban dashboard.

## Use cases
- orchestrate multiple AI coding agents to implement features automatically
- turn plain-language task descriptions into specs and production code
- run agent fleets across laptop, server, and cloud VMs with shared state
- route tasks to different LLM models with cheap-tier routing and fallback
- review AI-generated code in isolated git worktrees before merging

## When to choose
- you want autonomous multi-agent coding pipelines with human approval gates
- you need to coordinate AI agents across multiple machines or nodes
- you want model-agnostic orchestration supporting Anthropic, OpenAI, Ollama, and ACP agents

## When to avoid
- you need a mature, battle-tested tool for critical production workflows
- you prefer fully manual coding without AI agent automation
- you need Windows support or a stable release rather than an early preview

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, llm-inference, workflow-automation, developer-tools
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: multi-agent-orchestration, software-factory, git-worktrees, kanban-dashboard, model-router, acp-agents, ai-agents, automation, nodejs, macos, linux, docker

## Member repositories
- Runfusion/Fusion (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:08.061739+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 2026-08-30T06:31:46.697532+00:00, confidence not recorded.
  - readme: https://github.com/Runfusion/Fusion (fetched 2026-09-03T02:15:08.061739+00:00, sha 3db56522d14d)
  - homepage: http://runfusion.ai (fetched 2026-08-29T12:36:31.510918+00:00, sha 1e34c0a2b2cf)
- Data as of 2026-08-30T08:39:29.467469+00:00.