--- title: "agent-starter-pack vs selfhost-ai" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/googlecloudplatform-agent-starter-pack-vs-kossakovsky-selfhost-ai" tools: ["googlecloudplatform-agent-starter-pack", "kossakovsky-selfhost-ai"] --- # agent-starter-pack vs selfhost-ai *GraphCanon updated Jul 12, 2026* ## Verdict Pick agent-starter-pack when agent-starter-pack is primarily Python; selfhost-ai is Shell; pick selfhost-ai when selfhost-ai is primarily Shell; agent-starter-pack is Python. [agent-starter-pack](http://goo.gle/agents-cli) reports 6.5k GitHub stars, 1.5k forks, and 48 open issues, last pushed Jul 10, 2026. [selfhost-ai](https://github.com/kossakovsky/selfhost-ai#readme) has 897 stars, 228 forks, and 0 open issues, last pushed Jul 9, 2026. Figures are from public GitHub metadata via [agent-starter-pack's repository](https://github.com/GoogleCloudPlatform/agent-starter-pack) and [selfhost-ai's repository](https://github.com/kossakovsky/selfhost-ai). | | [agent-starter-pack](/tools/googlecloudplatform-agent-starter-pack.md) | [selfhost-ai](/tools/kossakovsky-selfhost-ai.md) | | --- | --- | --- | | Tagline | Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability. | 🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative. | | Stars | 6,514 | 897 | | Forks | 1,496 | 228 | | Open issues | 48 | 0 | | Language | Python | Shell | | Adopt for | agent-starter-pack is a specialized toolset for deploying AI agents on the Google Cloud Platform with built-in CI/CD, evaluation tools, and observability features. | - | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | LLM Frameworks, AI Agents, Inference & Serving | LLM Frameworks, AI Agents, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-starter-pack](/tools/googlecloudplatform-agent-starter-pack.md) | [selfhost-ai](/tools/kossakovsky-selfhost-ai.md) | | --- | --- | --- | | Days since push | 0d | 1d | | Open issues (now) | 48 | 0 | | Owner type | Organization | User | | Full report | [trust report](/tools/googlecloudplatform-agent-starter-pack/trust.md) | [trust report](/tools/kossakovsky-selfhost-ai/trust.md) | ## Decision facts: agent-starter-pack - **Requirements:** Requires additional software installation: Google Cloud SDK, Terraform for deployment, Make for development tasks. - **Adopt for:** agent-starter-pack is a specialized toolset for deploying AI agents on the Google Cloud Platform with built-in CI/CD, evaluation tools, and observability features. ## Choose when ### Choose agent-starter-pack if… - agent-starter-pack is primarily Python; selfhost-ai is Shell. - Requirements: Requires additional software installation: Google Cloud SDK, Terraform for deployment, Make for development tasks.. - Tags unique to agent-starter-pack: llmops, agents, gemini, observability. - Also covers Inference & Serving. - When you require production-ready templates specifically adapted for deployment to Google Cloud. ### Choose selfhost-ai if… - selfhost-ai is primarily Shell; agent-starter-pack is Python. - Tags unique to selfhost-ai: homelab, dify, ai, docker. - Also covers Vector Databases. ## When NOT to use agent-starter-pack - If you are using another cloud provider (e.g., AWS, Azure) and do not plan on moving your operations to Google Cloud. - When your team lacks familiarity with Python 3.10+ or does not wish to install and manage dependencies such as the Google Cloud SDK locally. ## When NOT to use selfhost-ai - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## Common questions ### What is the difference between agent-starter-pack and selfhost-ai? agent-starter-pack: Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.. selfhost-ai: 🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-starter-pack over selfhost-ai? Choose agent-starter-pack over selfhost-ai when agent-starter-pack is primarily Python; selfhost-ai is Shell; Requirements: Requires additional software installation: Google Cloud SDK, Terraform for deployment, Make for development tasks.; Tags unique to agent-starter-pack: llmops, agents, gemini, observability; Also covers Inference & Serving; When you require production-ready templates specifically adapted for deployment to Google Cloud. ### When should I choose selfhost-ai over agent-starter-pack? Choose selfhost-ai over agent-starter-pack when selfhost-ai is primarily Shell; agent-starter-pack is Python; Tags unique to selfhost-ai: homelab, dify, ai, docker; Also covers Vector Databases. ### When should I avoid agent-starter-pack? If you are using another cloud provider (e.g., AWS, Azure) and do not plan on moving your operations to Google Cloud. When your team lacks familiarity with Python 3.10+ or does not wish to install and manage dependencies such as the Google Cloud SDK locally. ### When should I avoid selfhost-ai? LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### Is agent-starter-pack or selfhost-ai more popular on GitHub? agent-starter-pack has more GitHub stars (6,514 vs 897). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-starter-pack and selfhost-ai open source? Yes - both are open-source projects on GitHub (agent-starter-pack: Apache-2.0, selfhost-ai: Apache-2.0). ### Where can I find alternatives to agent-starter-pack or selfhost-ai? GraphCanon lists graph-backed alternatives at [agent-starter-pack alternatives](/tools/googlecloudplatform-agent-starter-pack/alternatives) and [selfhost-ai alternatives](/tools/kossakovsky-selfhost-ai/alternatives) ([agent-starter-pack markdown twin](/tools/googlecloudplatform-agent-starter-pack/alternatives.md), [selfhost-ai markdown twin](/tools/kossakovsky-selfhost-ai/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/googlecloudplatform-agent-starter-pack-vs-kossakovsky-selfhost-ai.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-starter-pack or selfhost-ai? agent-starter-pack: Very active. selfhost-ai: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agent-starter-pack and selfhost-ai? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-starter-pack trust report](/tools/googlecloudplatform-agent-starter-pack/trust); [selfhost-ai trust report](/tools/kossakovsky-selfhost-ai/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=googlecloudplatform-agent-starter-pack`](/api/graphcanon/graph?tool=googlecloudplatform-agent-starter-pack) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_