Dev tools

Kitze released Skillbox, a self-hosted server that holds versioned agent skills and hands them out to Claude, Codex and Cursor over MCP

September 18, 2026 at 8:00 PM PT

The GitHub social card for the kitze/skillbox repository, showing the project name and its one-line description

Image: GitHub

Why it mattersA team can now keep one authoritative copy of every skill their agents use, revoke a leaked key without touching the skills themselves, and see which client actually loaded which revision.

Kitze, an indie developer whose earlier open-source work includes Sizzy and React Hanger, published Skillbox on 17 September. It is a self-hosted server that stores skills for AI coding agents as immutable revisions, hands them out over an MCP endpoint or a stdio bridge, and controls access through per-client keys that can be revoked one at a time. The repository is MIT licensed and reached 161 stars in the two days after its first push.

The problem Kitze is naming is the same one the earlier tool Kitter picked up on: a skill file copied into every project drifts, and nobody notices until an agent behaves differently in two repositories for reasons the diff cannot show. Skillbox answers it at a different layer. Instead of one local copy linked into projects, one central server owns the skills, and every client asks for them at run time.

How an agent uses it

An agent authenticates against the server's /mcp endpoint with a bearer token issued for that specific client. The base tools are search_skills, recommend_skills, load_skill, read_skill_file and report_skill_use. Skillbox also ships a Node and Bun stdio bridge for clients that do not speak HTTP MCP, and an install script that can configure Codex, Claude Code or Cursor against a given set of credentials.

A skill returned to an agent carries an immutable referenceId, the pinned revision, a description and a permission scope. The server never runs any skill code, and fetching a skill validates every path, file hash, size and package checksum before writing the files atomically. Revoking a client key blocks any future load. Files the client already downloaded stay on disk, and the README says so clearly.

Versioning, and who can change what

Every write produces a new revision. Skillbox detects conflicts on update and supports restore to an earlier version. Profiles carry independent create, update, archive and proposal permissions, so a shared installation can let an agent propose a skill change without letting it silently overwrite the master.

The optional recommendation layer

Skillbox has an optional recommend_skills mode that ranks the authorised skill catalogue against a task description. The ranking runs against either Vercel AI Gateway or the TypeSafe AI System One model, whichever the operator supplies a key for. The relevance score is described in the README as "an uncalibrated 0 to 4 rubric score, not probability", results below 3 are dropped, and any missing key, timeout or provider failure falls back to Postgres text search with an explicit fallbackReason. Skillbox does not ship a hosted account or provider credentials of its own.

The tech stack is React, Bun, Hono and PostgreSQL 16 or newer. Deployment is Docker-only with an optional Caddy HTTPS layer and Umbrel package files. Kitze notes on the release page that Umbrel packaging exists but has not yet passed real lifecycle verification.

For a team whose agents now run in more than one project, Skillbox moves the skills into one server that every agent asks over the network, and puts the read and write controls in one place instead of scattered across each repository.

Source

Primary source: kitze/skillbox on GitHub.

Source: GitHub

This item was written by an AI system from the linked source. Reveneau is responsible for what it publishes.

More from AI News

Kitter keeps one copy of every agent skill and links it into the projects that need it

Kitter stores agent skills in one library on your machine and links them into individual projects, so the same skill stops being copied into a dozen repositories and becoming different over time.

Source: GitHubDev tools

useAgent runs Claude Code, Codex and OpenCode inside sandboxes with a shared, durable session log

useAgent is an open-source platform that runs Claude Code, Codex and OpenCode inside isolated sandboxes with a shared event-sourced session log, at 277 GitHub stars in seven days.

Source: GitHubDev tools

Chat On Steroids is a local MCP server that gives ChatGPT Codex-grade tools on your own machine

Chat On Steroids is a tray app and Chrome extension that turns any ChatGPT conversation into a full coding environment, with file edits, shell commands, worker chats and sessions that continue past the context window limit, at 629 GitHub stars in 12 days.

Source: GitHubDev tools