Skip to content

docs: clarify agent and MCP images are pulled from GHCR by default #49

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kellyaa merged 1 commit into from
Jul 30, 2026
Merged

docs: clarify agent and MCP images are pulled from GHCR by default #49

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ The harness exists to robustly exercise agents and validate that the Kagenti pla

## Getting Started

The minimal end-to-end path: stand up a Kagenti cluster, build the agent + MCP images, then deploy and evaluate. Each block here is self-contained — copy the commands you need.
The minimal end-to-end path: stand up a Kagenti cluster, then deploy and evaluate. Agent and MCP images are pulled from GHCR by default — no local build required. Each block here is self-contained — copy the commands you need.

```bash
# 1. Stand up the Kagenti cluster (one-time)
Expand Down Expand Up @@ -64,7 +64,7 @@ The runner follows this execution model for each benchmark session:

## Benchmarks

The runner currently drives three benchmarks via the Exgentic MCP server. Each is a separate MCP image (`./build.sh <name>` from `agent-examples/mcp/exgentic_benchmarks`) and is selected at deploy time with `--benchmark <name>`.
The runner currently drives three benchmarks via the Exgentic MCP server. Each is a separate MCP image, pulled from `ghcr.io/exgentic/exgentic-mcp-<benchmark>:latest`, and is selected at deploy time with `--benchmark <name>`.

| Benchmark | What it tests | Tool surface | Notes |
|-----------|---------------|--------------|-------|
Expand Down