agent-engineering vs Umtri
agent-engineering is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑24.
agent-engineering is a plugin bundle for AI coding tools published by Andrew Novykov. No marketplace we read lists it any more. Umtri is an MCP server published by umtri.io. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-27. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  Umtri | |
|---|---|---|
| Community marketplace endorphin-ai/hasbrains-agent-kit | Removed on 2026-10-24 Version: 1.3.0 Forks (GitHub): 1 Stars (GitHub): 9 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.5.3 Downloads/month (npm): 2 411 Downloads/week (npm): 25 Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | agent-engineeringno longer listed · | Umtri |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 1 |
| Stars (GitHub) (differs) | 9 | 0 |
| Forks (GitHub) (differs) | 1 | 0 |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (mcp.umtri.io) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Parts of the bundle (differs) | 8 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/endorphin-ai/hasbrains-agent-kit | github.com/bepuljang/umtri-mcp |
| Changes in the last 7 days (differs) | 2 | 0 |
| First seen (differs) | 2026-10-17 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 5 days ago |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of agent-engineering
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
AI Agent Harness Engineering: bootstrap, audit, and evolve a reliable 6-layer agent harness for any project. Generates AGENTS.md, hooks (type-check, .env protection, auto-format…
-
Universal multi-agent project harness for Claude Code — run any project through a structured AI team from discovery to release.
-
Spec-driven workflow for AI coding agents: PRD, plan, check, and archive features using tracer-bullet vertical slices.
-
karimo-harness-engineering-agent-orchestration
Harness engineering framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and…
-
The PIV loop (plan, implement, validate, review, commit, PR) plus priming, planning, worktrees, and the meta-skills for building your own AI Layer.
-
Architecture, engineering delivery, development discipline, debugging, review, and AI and automation systems.
What each says it does
agent-engineering
Engineering discipline for AI agent systems — four always-on principles, test-driven development, verification-before-completion, system-architecture playbooks, a scope-disciplined product manager, docs/-native project management, and Claude Code → GitHub Copilot agent conversion.
Umtri
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
How to run each
agent-engineering
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Umtri As a remote MCP server
claude mcp add --transport http umtri https://mcp.umtri.ioRequires: UMTRI_API_TOKEN (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only Umtri has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of agent-engineering publish no settings it asks for, so we do not compare settings.
What it can do: agent-engineering · What it can do: Umtri · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.