Developers & AI Agents

Everything on talogen.dev — Tal Ogen's portfolio — is machine-readable. This page is the developer portal: the REST API, the OpenAPI spec, the MCP server, authentication (there is none to set up), rate limits, and the versioning policy. The markdown twin of this page is at /developers/llms.txt.

Quickstart

# Who is Tal Ogen? (JSON profile)
curl https://talogen.dev/api/v1/profile

# All projects, or one in full detail
curl https://talogen.dev/api/v1/projects
curl https://talogen.dev/api/v1/projects/human-for-ai

# Hiring facts: availability, target roles, location
curl https://talogen.dev/api/v1/candidate

REST API

Endpoint	Returns
`GET /api/v1`	Endpoint directory
`GET /api/v1/profile`	Profile: headline, summary, contact, skills, strengths
`GET /api/v1/projects`	Project summaries (`?tag=`, `?flagship=true`)
`GET /api/v1/projects/{id}`	Full problem → solution → result detail
`GET /api/v1/agents`	Autonomous-agent summaries (`?tag=`)
`GET /api/v1/candidate`	Machine-readable hiring facts

The full contract lives in the OpenAPI 3.1 spec at /openapi.json — every operation has an operationId, typed schemas, and documented errors. Errors are structured JSON: {"error": {"code", "message", "hint"}}; a 404 on an unknown id lists every valid id in the hint.

MCP server

The same data plus a write action, over Model Context Protocol (streamable HTTP, stateless): endpoint https://talogen.dev/mcp, discovery at /.well-known/mcp, server card at /.well-known/mcp/server-card.json. Tools: get_profile, list_projects, list_agents, get_project, and contact_recruiter — the only write action anywhere, which delivers your message to a human who replies to your reply_to address.

{
  "mcpServers": {
    "tal-ogen-portfolio": { "type": "http", "url": "https://talogen.dev/mcp" }
  }
}

Authentication

None. No API keys, no OAuth, no registration — see /auth.md for the full walkthrough in the agent-auth structure. You will never receive a 401 or 403.

Rate limits & sandbox

No enforced quota at the API layer; responses are CDN-edge-cached (Cache-Control: s-maxage), so reads are cheap — please keep automated traffic reasonable. Because every read endpoint is public and side-effect-free, the live API is its own sandbox: nothing you GET can change state. The one write action, contact_recruiter, delivers real messages and is rate-limited and deduplicated by the receiving platform; don't use it for testing.

Versioning & deprecation policy

The /api/v1 prefix is stable. Additive changes (new fields, new endpoints) ship without a version bump.
Any breaking change ships as /api/v2; /api/v1 then keeps working for at least 90 days.
Deprecated versions announce their end date with RFC 8594 Sunset headers and a notice here.

Discovery & data surfaces

/llms.txt — one-page overview with when-to-use guidance
/index.md — markdown homepage (also via Accept: text/markdown on /)
/portfolio.json — everything in one request
/.well-known/agent.json — every entry point
/.well-known/candidate.json — hiring facts
/.well-known/ard.json — Agentic Resource Discovery catalog
/.well-known/agent-skills/index.json — agent skills index
/.well-known/api-catalog — RFC 9727 API catalog
/stats — public machine-traffic scoreboard

Source & coding agents

This site is open source: github.com/TALOGEN777/general-portfolio. The repo's AGENTS.md tells AI coding agents how the data pipeline and deploy order work. Questions or issues: /contact.