VitaeContext plugin
VitaeContext keeps career facts in private Markdown and gives agents skills and an MCP server for CVs and profiles
- 90 ★ on the repository
- Last commit
Extended access
Why this level
- Keeps personal career data in local files read by the agent and the MCP server from any of your repositories
- The installer writes files into several agents' skill directories and runs `npx`
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/vitaecontextDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Keeps personal career data in local files read by the agent and the MCP server from any of your repositories
- The installer writes files into several agents' skill directories and runs `npx`
This is third-party code. Review the repository files before installing.
What it does
The kit makes career context reusable across AI tools. The `vitaecontext-build` skill turns a CV, LinkedIn sections, GitHub links and project notes into a private Markdown file of grounded facts: current facts, evidence, target role and platform rules. The agent relies on it and does not invent achievements. `npx vitaecontext context validate` checks the file structure and `context summary --for github` prepares a short packet for a task. For deep structured memory there is VitaeGraph, a hierarchy of records on experience, projects, education, awards and publications where Markdown stays canonical and JSON indexes are rebuilt. A stateless MCP server (`npx -y vitaecontext mcp`, protocol 2024-11-05) reads the chosen context from any repository. Install with `npx vitaecontext install --provider <name>` for Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode and others.
Who it is for. People who regularly ask an agent for CVs, LinkedIn and GitHub profiles, letters and project descriptions and do not want to re-explain their career in every chat.
Good fit when
- An agent writes a LinkedIn profile and the facts about your roles and dates must come from one verified file
- A CV must be tailored to a vacancy and mismatches in dates and titles are unacceptable
- You need a structured achievements base with evidence for a performance review
- Career context must be available to agents in every repository through MCP, with no file copying
Not a fit when
- You want to find a job: the tool stores your data but does not search vacancies or send applications
- Local storage of personal data in Markdown files does not suit you
- You need a ready CV template with layout: the project builds context and not formatting
Example request
Use vitaecontext-build to create my Career Context file from my CV and GitHub profileLimitations
- The context file holds personal data. It lives in `~/.vitaecontext/` by default and should be kept private and kept out of public repositories.
- Validation fails while the template placeholders remain, and they must be replaced with real data.
- Installation goes one provider at a time, each with its own directory and invocation.
- The deprecated `agentkit-seo` command still works as an alias; the project was formerly AgentKit SEO and changes fast.
How to disable. Remove the skill folders for your provider by hand, then drop the `vitaecontext` entry from your MCP configuration. Delete personal files in `~/.vitaecontext/` separately.
FAQ
How do I install VitaeContext?
Run `npx vitaecontext install --provider codex` or with another provider name: claude-code, gemini-cli, cursor, windsurf, opencode. Then `npx vitaecontext doctor` checks the install.
Where is my data stored?
Locally, by default in `~/.vitaecontext/<name>-career-context.md` and a `vitaegraph` folder. The project states local-first storage; data goes anywhere only if you hand it to an agent.
How does VitaeGraph differ from the context file?
The context file is compact and serves quick grounded drafts. VitaeGraph stores detailed hierarchical records on experience, projects and publications when an agent needs depth.
How do I connect the MCP server?
Add an entry to the client config with the `npx` command and arguments `-y`, `vitaecontext`, `mcp`. Examples for Claude Desktop, Claude Code, Cursor, Windsurf and Roo Code are in `mcp/config-examples`.
What is AgentKit SEO?
The project's former name. It grew from profile SEO into a career context layer, and the old `agentkit-seo` command forwards to the VitaeContext CLI.
Discussion
No questions or reviews yet.
Related
PluginsAn MCP server and Mac app that keeps one local index of repos, agent sessions and tickets, with semantic search and work threads
A macOS menu bar app writes the text of your focused windows into markdown, and its MCP server serves that record to agents
Personal agent context in plain Markdown files you own, plus an onboarding skill built on a short interview
Personal Markdown wiki on your disk: the agent reads your sources, merges them into context.md and writes only after you approve.
A Claude Code plugin that builds a knowledge system of markdown files from a conversation with you: folder structure, note templates, a processing pipeline and
A CLI that builds a local notes index with catalyst questions so the agent finds material faster than plain grep search
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| VitaeContext (this card) | no | 90 | |
| Resume Skills | no | 3,153 | a set of skills for CVs and job applications, while this project stores verified career facts and serves them to different agents through MCP |
| career-ops | no | 82,101 | runs a job search with vacancy scoring and an application tracker, while this project builds a private career fact base |
README in short
The README presents VitaeContext as a career context layer: the repeated-explanation problem, three modules, a quick start with commands and an MCP server with a config sample. It then explains VitaeGraph, a provider table with install directories and documentation links.