Flagged: reads sensitive env vars. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by cairn-dev · Agent Tool · ★ 214
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is cairn safe to install? View the security audit →
Github-integrated background agents, automating end-to-end software engineering, fully open source. 🚀 Quick Start 🤝 Contributing 🪨 What is Cairn? Cairn is a simple open-source background-agent system for coding, built in the style of a product management tool. Think Codex, Jules, or Cursor Background Agents, but open sourced! You can run Cairn locally, connect it to your github repos and use your favorite LLM to execute fullstack tasks, 100% in the
| Stars | 214 |
| Forks | 23 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72.3633650234523/100 |
| Open Issues | 21 |
| Last Updated | 2025-07-02 |
| Created | 2025-05-23 |
| Platforms | python |
| Est. Tokens | ~3944k |
Looking for a cairn alternative? If you're comparing cairn with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows acr
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions
A list of open-source AI projects you can use to generate income easily.
Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth,
Explore other popular agent tool tools:
cairn is A background agent system for automating end-to-end software engineering tasks, direct from your github repos.. It is categorized as a Agent Tool with 214 GitHub stars.
cairn is primarily written in Python. It covers topics such as ai-agents, ai-tools, background-agent.
You can find installation instructions and usage details in the cairn GitHub repository at github.com/cairn-dev/cairn. The project has 214 stars and 23 forks, indicating an active community.
cairn is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to cairn on Agent Skills Hub include Agentfy, web-agent-protocol, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: