Self-hosted alternatives to caveman-discover
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 caveman-discover

caveman-discover
Find and label every LLM workflow in the repository
caveman-discover is an operator-run agent skill from the caveman project that finds and labels every LLM workflow in a repository, so that Caveman Cloud can group spending by workflow instead of putting all unlabeled traffic in one bucket. A workflow is a job the code performs, such as answering a support ticket, building a nightly digest or running an eval suite, and not a technology. The skill inventories the repository's workflows, gives them clear names, and wires labels into the gateway requests, then checks that nothing has broken. The process is cautious. The skill first proposes a labeling table and waits for the user's approval before it changes any code, and the change goes through the user's normal review. It is designed to be idempotent, so re-running it on a repository that is already labeled should change nothing. It also says that telemetry, such as an unlabeled-traffic observation, does not select a call site or authorize an edit, so the agent must inventory the repository on its own. The skill suits teams that make LLM calls in their code and use Caveman Cloud to track spending.
- Price
- Free
- Made by
- juliusbrussee
- Category
- AI Skills
- Website
- github.com/juliusbrussee/caveman/caveman-discover