# ColeMurray/background-agents

An open-source background agents coding system

Repository: https://github.com/ColeMurray/background-agents
Canonical: https://ross.abutalabs.com/products/background-agents
Homepage: https://backgroundagents.dev
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-26T21:49:20+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 15
- inputs: {"age_days": 220, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2683, forks 393 (observed 2026-08-28T04:07:10.089464+00:00)

## What it is
An open-source, self-hostable background coding agent system (Open-Inspect) inspired by Ramp's Inspect, where AI agents work on tasks in sandboxed dev environments and turn requests from Slack, GitHub, Linear, or web UI into pull requests. It supports multiple AI models, scheduled/cron triggers, parallel sub-task sandboxes, and real-time multiplayer sessions, designed for single-tenant deployment by trusted teams.

## Use cases
- turn slack messages into pull requests automatically
- run coding agents in the background on scheduled tasks
- let non-engineers like PMs and designers ship code changes
- spawn parallel AI coding agents on separate tasks
- self-host a background coding agent for my team
- create PRs from linear issues automatically
- collaborate with teammates in a live agent coding session

## When to choose
- your team wants an open-source, self-hosted alternative to hosted background coding agents
- you want non-engineers to submit code changes as reviewable PRs
- you need agents triggered from Slack, GitHub, Linear, webhooks, or cron schedules
- you want to use your own AI model subscriptions (Claude, Codex, Grok)

## When to avoid
- you need multi-tenant deployment with per-user repository access control - the security model explicitly assumes all users are trusted
- you want a fully managed SaaS with zero infrastructure to run
- your organization requires strict per-user permission validation before agent sessions access repositories

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, webhook, developer-tools
- domain: developer-tools, large-language-models, self-hosted
- platform: self-hosted
- tags: background-agents, coding-agent, slack-integration, github-app, linear-integration, multiplayer-sessions, sandboxed-environments, pull-request-automation, single-tenant, ai-agents, automation, web-server, docker, nodejs, typescript

## Member repositories
- ColeMurray/background-agents (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.089464+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 2026-08-30T02:17:52.078283+00:00, confidence not recorded.
  - readme: https://github.com/ColeMurray/background-agents (fetched 2026-08-28T04:07:10.089464+00:00, sha 04e190f1738d)
  - homepage: https://backgroundagents.dev (fetched 2026-08-29T10:00:20.450958+00:00, sha ac442b8d12c9)
- Data as of 2026-08-30T08:39:29.467469+00:00.