Self-hosted alternatives to core
5 self-hosted AI Skills apps to use instead, best rated first.
Top picks
- C

claude-to-deerflow
Launchclaude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code
Self-hosted
- O

open-notebook
Launchopen-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O
Self-hosted
- R

Reactive Resume
LaunchReactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish
Open sourceSelf-hosted
- S

self-hosted-funnel-launch
LaunchSelf-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a
Self-hosted
- G

get-convex/convex-backend
LaunchConvex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca
Self-hosted
About core

core
Core package for defining schemas, catalogs
core is the foundation package of json-render, which works with specs that are JSON output from an AI and conform to a schema. It provides the building blocks for defining that structure. A schema defines the structure of specs and catalogs, and you create one with defineSchema. A catalog maps component and action names to their definitions, and you build one with defineCatalog. A spec is the JSON an AI produces that matches the schema. SpecStream is a JSONL streaming format for building a spec progressively as its pieces arrive. The package also covers AI prompt generation from a catalog. It includes two experimental decision-model composition APIs, experimental_composeSpec and experimental_createEvaluator, which the project says are unreleased. Until they are published, they should be used from a source build, and experimental exports and Experimental_ types can change in any release, so you should pin exact versions once they ship. The skill is for work with @json-render/core, and it is installed with npx skills from the vercel-labs/json-render repository. Its security audits all pass.
- Price
- Free
- Made by
- vercel-labs
- Category
- AI Skills
- Website
- github.com/vercel-labs/json-render/core