--- title: "selfhost-ai vs promptfoo" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kossakovsky-selfhost-ai-vs-promptfoo-promptfoo" tools: ["kossakovsky-selfhost-ai", "promptfoo-promptfoo"] --- # selfhost-ai vs promptfoo *GraphCanon updated Jul 12, 2026* ## Verdict Pick selfhost-ai when selfhost-ai is primarily Shell; promptfoo is TypeScript; pick promptfoo when promptfoo is primarily TypeScript; selfhost-ai is Shell. [selfhost-ai](https://github.com/kossakovsky/selfhost-ai#readme) reports 897 GitHub stars, 228 forks, and 0 open issues, last pushed Jul 9, 2026. [promptfoo](https://promptfoo.dev) has 23k stars, 2.1k forks, and 413 open issues, last pushed Jul 11, 2026. Figures are from public GitHub metadata via [selfhost-ai's repository](https://github.com/kossakovsky/selfhost-ai) and [promptfoo's repository](https://github.com/promptfoo/promptfoo). | | [selfhost-ai](/tools/kossakovsky-selfhost-ai.md) | [promptfoo](/tools/promptfoo-promptfoo.md) | | --- | --- | --- | | Tagline | 🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative. | Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line | | Stars | 897 | 23,155 | | Forks | 228 | 2,071 | | Open issues | 0 | 413 | | Language | Shell | TypeScript | | Adopt for | - | Promptfoo is a specialized tool for evaluating and testing AI-generated outputs like prompts, agents, and RAGs (Retrieval-Augmented Generation) through methods such as red teaming, pentesting, and vulnerability scanning. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Promptfoo uses an MIT license which allows free use, modification, distribution, and commercial exploitation under the condition that appropriate attribution is given to the original authors. | | Categories | AI Agents, LLM Frameworks, Vector Databases | AI Agents, LLM Frameworks, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [selfhost-ai](/tools/kossakovsky-selfhost-ai.md) | [promptfoo](/tools/promptfoo-promptfoo.md) | | --- | --- | --- | | Days since push | 1d | 0d | | Open issues (now) | 0 | 413 | | Owner type | User | Organization | | Full report | [trust report](/tools/kossakovsky-selfhost-ai/trust.md) | [trust report](/tools/promptfoo-promptfoo/trust.md) | ## Decision facts: promptfoo - **Pricing:** freemium - The basic version of Promptfoo is freely available due to its open-source nature under MIT licensing. Advanced features may require a paid plan from future commercial offerings. - **Requirements:** Requires TypeScript runtime and relevant node.js or deno setup to run.; May need additional configuration for CI/CD integration, depending on the build ecosystem. - **Adopt for:** Promptfoo is a specialized tool for evaluating and testing AI-generated outputs like prompts, agents, and RAGs (Retrieval-Augmented Generation) through methods such as red teaming, pentesting, and vulnerability scanning. - **License detail:** Promptfoo uses an MIT license which allows free use, modification, distribution, and commercial exploitation under the condition that appropriate attribution is given to the original authors. ## Choose when ### Choose selfhost-ai if… - selfhost-ai is primarily Shell; promptfoo is TypeScript. - License: selfhost-ai is Apache-2.0, promptfoo is MIT. - Tags unique to selfhost-ai: ai, ai-agents, automation, chatgpt-alternative. ### Choose promptfoo if… - promptfoo is primarily TypeScript; selfhost-ai is Shell. - License: promptfoo is MIT, selfhost-ai is Apache-2.0. - Pricing: The basic version of Promptfoo is freely available due to its open-source nature under MIT licensing. Advanced features may require a paid plan from future commercial offerings.. - Requirements: Requires TypeScript runtime and relevant node.js or deno setup to run.; May need additional configuration for CI/CD integration, depending on the build ecosystem.. - Tags unique to promptfoo: ci, ci-cd, cicd, evaluation. - promptfoo ships Docker support for self-hosted deployment. - When you need to assess the robustness of your RAG systems against potential vulnerabilities. ## When NOT to use selfhost-ai - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## When NOT to use promptfoo - When you are specifically looking for general-purpose evaluation tools that do not have the focused depth on security and vulnerability provided by Promptfoo. - If your workflow or project cannot support TypeScript, as this tool is built in TypeScript and might require additional setup for non-TypeScript environments. ## Common questions ### What is the difference between selfhost-ai and promptfoo? selfhost-ai: 🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.. promptfoo: Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line . See the comparison table for live GitHub stats and shared categories. ### When should I choose selfhost-ai over promptfoo? Choose selfhost-ai over promptfoo when selfhost-ai is primarily Shell; promptfoo is TypeScript; License: selfhost-ai is Apache-2.0, promptfoo is MIT; Tags unique to selfhost-ai: ai, ai-agents, automation, chatgpt-alternative. ### When should I choose promptfoo over selfhost-ai? Choose promptfoo over selfhost-ai when promptfoo is primarily TypeScript; selfhost-ai is Shell; License: promptfoo is MIT, selfhost-ai is Apache-2.0; Pricing: The basic version of Promptfoo is freely available due to its open-source nature under MIT licensing. Advanced features may require a paid plan from future commercial offerings.; Requirements: Requires TypeScript runtime and relevant node.js or deno setup to run.; May need additional configuration for CI/CD integration, depending on the build ecosystem.; Tags unique to promptfoo: ci, ci-cd, cicd, evaluation; promptfoo ships Docker support for self-hosted deployment; When you need to assess the robustness of your RAG systems against potential vulnerabilities. ### When should I avoid selfhost-ai? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### When should I avoid promptfoo? When you are specifically looking for general-purpose evaluation tools that do not have the focused depth on security and vulnerability provided by Promptfoo. If your workflow or project cannot support TypeScript, as this tool is built in TypeScript and might require additional setup for non-TypeScript environments. ### Is selfhost-ai or promptfoo more popular on GitHub? promptfoo has more GitHub stars (23,155 vs 897). Stars measure visibility, not whether either tool fits your constraints. ### Are selfhost-ai and promptfoo open source? Yes - both are open-source projects on GitHub (selfhost-ai: Apache-2.0, promptfoo: MIT). ### Where can I find alternatives to selfhost-ai or promptfoo? GraphCanon lists graph-backed alternatives at [selfhost-ai alternatives](/tools/kossakovsky-selfhost-ai/alternatives) and [promptfoo alternatives](/tools/promptfoo-promptfoo/alternatives) ([selfhost-ai markdown twin](/tools/kossakovsky-selfhost-ai/alternatives.md), [promptfoo markdown twin](/tools/promptfoo-promptfoo/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/kossakovsky-selfhost-ai-vs-promptfoo-promptfoo.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, selfhost-ai or promptfoo? selfhost-ai: Very active. promptfoo: 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 selfhost-ai and promptfoo? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [selfhost-ai trust report](/tools/kossakovsky-selfhost-ai/trust); [promptfoo trust report](/tools/promptfoo-promptfoo/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kossakovsky-selfhost-ai`](/api/graphcanon/graph?tool=kossakovsky-selfhost-ai) - 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/_