GeezerVison

Application · Research · Android · Apple/iOS · Leaderboard plan · MIT licence

Everyone follows our Code of Conduct. Report security concerns privately through the affected repository's security policy; the research repository's security policy describes its process. Do not post credentials, personal data, or vulnerability details in public issues.

Pick Your AI is a web-based builder for assembling a complete AI solution, like a PC build. Start with a workload and deployment mode, then choose models, infrastructure, and optional capabilities. The goal is to help people understand compatibility, costs, and tradeoffs, with evidence behind each recommendation.

PCPartPicker is a functional reference; Pick Your AI develops its own brand, interface, and code.

Model licences, context limits, GPU memory, inference-engine support, hosting availability, retrieval, tool permissions and pricing constrain each other. A model may not fit a GPU; an engine may not support a format; a hosting region may not offer the hardware. We aim to make these relationships and their evidence easier to inspect.

The configurator is intended to guide users through seven tiers. T3 to T5 are optional and can be left out entirely.

	Tier	Focus
	T0 Configuration	Workload / use case and deployment mode (API, managed, self-hosted, hybrid)
	T1 Model Selection	Provider, model, context window
	T2 Infrastructure	Hosting, GPU / compute, inference engine
	T3 Knowledge & Retrieval (optional)	Knowledge base, embeddings, vector database, RAG
	T4 Agents & Integrations (optional)	Agent framework, tools and APIs, MCP servers, memory
	T5 Training & Fine-Tuning (optional)	Training framework, compute, dataset, fine-tuned model
	T6 Deployment & Operations	Guardrails, evaluation, deployment, monitoring, cost estimate

Tiers constrain each other in both directions: models affect GPU requirements, and GPU availability limits model choices. The intended compatibility system re-checks affected selections when a component changes, and never treats unknown compatibility as compatible.

pick-your-ai-website Application, interface, tests, and data integration	pick-your-ai-research Evidence, decision records, catalog and pricing proposals, and shared contracts	pick-your-ai-leaderboard Contributor recognition, metric definitions, and leaderboard delivery planning
pick-your-ai-android Android planning client: scope, contribution guidance, and delivery planning	pick-your-ai-apple Apple/iOS planning client: scope, contribution guidance, and delivery planning	.github Organization profile and community defaults

Application, research and leaderboard work have separate workflows. Funding, grants and sustainability work is coordinated in pick-your-ai-sustainability, tracked in Project 7. The application demonstrates selection with synthetic fixtures. Research gathers sourced facts, dated prices and proposed compatibility rules under a versioned shared contract. Merged research does not automatically become production catalog data.

The mobile repositories are early-stage and unreleased. Android has a Kotlin/JVM core and an unsigned debug diagnostic; Apple/iOS has an unsigned SwiftUI app with local drafts. Neither has a signed installable product, production backend or release yet.

The contributor leaderboard project and its delivery program plan public, source-linked recognition across pull requests, code changes, reviews, issues, triage, documentation, research, and maintenance. The plan defines 98 metrics, 20 epics, 112 work packages and 474 implementation checklist tasks. These are planned capabilities, not a deployed leaderboard. Metric availability, historical coverage, and limitations must be visible, and lines of code do not establish contribution quality.

The leaderboard repository owns its metric definitions, delivery workflow, and correction process. Existing repository contribution and review rules continue to determine whether work is accepted.