Self-hosted alternatives to cavecrew
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 cavecrew

cavecrew
Delegate code tasks to compressed subagents
cavecrew is an agent skill from the caveman project for delegating code tasks to compressed subagents, which the project says shrink the context used by each delegation by about 60 percent. It provides three preset subagents. cavecrew-investigator locates symbols and definitions and answers questions such as where something is defined, what calls it, or where a value is used. cavecrew-builder makes surgical edits to one or two files when the scope is obvious. cavecrew-reviewer audits a diff, a branch or a file for bugs. The presets answer in a compressed voice, so a result comes back as a short path and line table rather than prose. The skill explains why this matters: subagent tool results are injected into the main context verbatim, so a long prose answer costs main-context budget every time. A decision guide tells the agent when to use each preset. For a new feature across three or more files or a cross-cutting refactor it recommends the main thread, and for a deep review with rationale and alternatives it recommends the ordinary code reviewer. The skill suits developers who run long agent sessions and want to keep their context from running out.
- Price
- Free
- Made by
- juliusbrussee
- Category
- AI Skills
- Website
- github.com/juliusbrussee/caveman/cavecrew