Early access · Summer 2026
Joseki WrapperHub is a registry for LLM behavior packages — prompts, fine-tunes, adapters, evals, and safety policies in one reusable format. Trust through community.
What it looks like
Joseki:WrapperHub becomes the place where I can find a Prompt for legal analysis and the Data Pack of 2026 tax code changes, and I can see that 500 other lawyers verified it worked this morning.
Prompt
A reviewed PromptSpec for the task — inputs, outputs, examples, compatible models.
Data Pack
A scoped dataset bundled alongside the prompt. Versioned, hashed, and licensed like code.
Liveness
Recency-weighted Works/Broken reports from real users — per model, updated in real time.
The problem
Teams need reusable, testable, portable behavior across models, apps, and organizations. But today, prompts live in docs. Fine-tune configs sit in notebooks. Eval suites are buried in repos. Safety rules exist only in vendor dashboards.
Every model switch means rebuilding from scratch. Every handoff means copying prompts into Slack. Every audit means digging through git history. There is no standard way to package, version, or share the full behavior of an LLM deployment.
The solution
Joseki WrapperHub lets you create Behavior Packages — versioned bundles that capture everything about how an LLM should behave.
What you can build
Core
Reusable prompts with examples, metadata, and version history. Stop copying prompts between projects — install them.
Training
Portable training recipes for closed and open model providers. One recipe, any backend. Reproducible by default.
Adapters
Share LoRA adapters with compatible model manifests, artifact hashes, and runtime instructions.
Quality
Validate packages with prompt-injection scans, license checks, and provenance tracking.
Live signal
Forget stale "Last Updated" timestamps. Every wrapper carries a Liveness Score — a recency-weighted aggregate of "Works" and "Broken" reports from real users, broken down per model. You see which models a prompt is alive on, and which ones broke this morning.
gpt-4o
97/100
342 works · 3 broken
claude-3.5-sonnet
48/100
51 works · 62 broken
llama-3.3-70b
12/100
4 works · 28 broken
Creators who maintain their wrappers earn reputation. Reputation compounds into a Go-style kyu / dan rank, the same way Stack Overflow rewards consistent contributors.
For developers
Install, inspect, and evaluate behavior packages before using them in production.
$joseki install customer-support-classifier$joseki inspect customer-support-classifier$joseki eval customer-support-classifier
Built for trust
Joseki is built for teams that care about security, repeatability, and trust. Every package carries its own evidence trail.
Pricing
Joseki is freemium. Public Behavior Packages are free forever. Premium unlocks private vaults for teams, larger data packs, and priority eval runs. Sponsored wrappers open up once we hit critical mass on the open side.
Free
$0
Public wrappers, votes, Liveness reports, kyu/dan rank.
Premium
$24 / mo
Private vaults, 5GB data packs, priority eval runs, verified badge.
Sponsored
By request
Featured slot on the registry, once we cross 5k monthly reviewers.
Stay in the loop
We'll let you know when new features, wrappers, and eval tools ship — no spam.