VitaeContext

Keep your career context. Reuse it across AI.

VitaeContext gives AI agents a private, reusable source of truth about a person's career, then provides focused skills and a Model Context Protocol (MCP) server for turning that context into grounded professional work.

Website • Repository • npm Package • Why • How it works • MCP Server • VitaeGraph

---

Role and Ownership

I co-created and maintain VitaeContext (formerly AgentKit SEO) with Elia Innocenti.

My work focuses on:

• Context Routing & Architecture: The core engine, validation gates, and export layer that turns raw career material into an evidence-bounded source of truth.
• Model Context Protocol (MCP) Server: The native stateless MCP server implementation allowing coding assistants (Claude Code, Cursor, Windsurf, Roo Code, Antigravity, IBM Bob, Grok) to query career facts and VitaeGraph without repo duplication.
• VitaeGraph: The hierarchical Markdown knowledge graph and progressive retrieval architecture for complex career records.
• Provider Adapters: Provider-specific skill packaging that lets tools such as Codex, Claude Code, Gemini CLI, Antigravity, and OpenCode load focused instructions.

---

Why VitaeContext

Formerly AgentKit SEO. The project grew beyond profile SEO into reusable career context for grounded AI work. The deprecated agentkit-seo command remains available as a compatibility alias and forwards to the VitaeContext CLI.

Every new AI chat starts with the same problem: the agent does not know which career facts are current, which claims have evidence, what role is being targeted, or how the output should change for each platform.

The usual result is repeated explanation, inconsistent profiles, generic writing, and occasionally invented claims.

VitaeContext applies the familiar AGENTS.md and CLAUDE.md pattern to professional identity. Its Context Builder skill turns a user's raw career material into a private Markdown source of truth called a Career Context file. Focused skills then adapt that file for LinkedIn, GitHub, CV/ATS, web portfolios, and X/Twitter.

The goal is simple:

• Explain professional context once instead of rebuilding it in every chat.
• Keep facts, goals, constraints, proof links, and claims to avoid in one reusable file.
• Adapt the same evidence to each platform without turning positioning into invention.
• Reuse the workflow across supported AI coding agents via standard Agent Skills or a stateless MCP server.

The context layer before career automation

Many tools can draft a CV, tailor an application, write a message, or automate a career workflow. Those tools can only work from the career information they receive. When that input is scattered, stale, incomplete, or overstated, the same problems travel through the rest of the workflow.

VitaeContext sits one logical layer before those systems. It helps create and maintain the private, evidence-bounded Career Context file that an agent, CV builder, application workflow, or other career tool can use as its starting point.

---

How it works

1. Gather the raw material. Start with CVs, profile sections, GitHub and portfolio links, exports, screenshots, and project notes.
2. Create the Career Context file with VitaeContext. Give the raw material to an AI agent and invoke vitaecontext-build. The skill guides the agent in organizing the material into one private Markdown file containing verified facts, stated goals, constraints, proof links, and evidence boundaries.
3. Load one focused skill or query via MCP. Use the LinkedIn, GitHub, CV/ATS, web portfolio, or X/Twitter module for the surface being improved.
4. Produce grounded work. Get an audit, rewrite, patch proposal, or action plan based on the supplied context and platform guidance.

---

Model Context Protocol (MCP) Server

VitaeContext provides a native, stateless MCP server over stdio using standard JSON-RPC 2.0. Any AI client supporting MCP can query your career context directly:

{
  "mcpServers": {
    "vitaecontext": {
      "command": "npx",
      "args": ["-y", "vitaecontext-mcp"]
    }
  }
}

Exposed resources, tools, and prompts include:

• career-context://current and vitaegraph://index
• get_career_context, search_vitaegraph, and validate_context
• Built-in prompts for CV tailoring, LinkedIn profile audit, and portfolio optimization

---

VitaeGraph: Structured Career Memory

VitaeGraph is VitaeContext's deeper structured-memory layer. Use the Career Context file for compact, repeated facts and quick grounded drafts. Use VitaeGraph when an agent needs detailed records for projects, roles, degrees, courses, thesis work, certifications, awards, publications, and the relationships between them.

---

Modules and Skills

VitaeContext ships one compact-context module, VitaeGraph, and five platform modules, coordinated by the root routing skill:

---

Agentic AI & Security Relevance

VitaeContext is directly connected to agentic AI systems engineering and security:

• Context as a Control Surface: It treats context, prompt boundaries, constraints, verified facts, and tool instructions as control surfaces.
• Evidence Boundaries: Prevents hallucination and overstatement by enforcing strict provenance and labeling.
• Safe Multi-Provider Tooling: Provides deterministic local-first execution across Claude Code, Codex, Gemini CLI, Antigravity, OpenCode, Cursor, and Windsurf.

---

Public Links & Proof

• Website: https://vitaecontext.github.io/
• Repository: https://github.com/vitaecontext/vitaecontext
• npm Package: https://www.npmjs.com/package/vitaecontext