Skip to content

feat(eve): Getting Started with Eve on Runpod — self-hosted LLM agent + web UI#19

Open
TimPietruskyRunPod wants to merge 4 commits into
mainfrom
feat/eve-getting-started-example
Open

feat(eve): Getting Started with Eve on Runpod — self-hosted LLM agent + web UI#19
TimPietruskyRunPod wants to merge 4 commits into
mainfrom
feat/eve-getting-started-example

Conversation

@TimPietruskyRunPod

Copy link
Copy Markdown
Member

Getting Started with Eve on Runpod

Adds a new eve/ example: an image-generating AI agent built with Eve whose brain is an open LLM self-hosted on Runpod Serverless (Qwen/Qwen3.6-27B-FP8 on vLLM, OpenAI-compatible), with a generate_image tool backed by a Runpod image model, behind a Next.js web chat UI.

Browser ─ Next.js chat UI ─ Eve agent
                              ├─ brain: self-deployed Qwen3.6-27B-FP8 (Runpod Serverless, vLLM)
                              └─ tool:  generate_image → Runpod image model

Agent-first

The setup is encoded as an agent runbook in eve/getting-started/AGENTS.md, written to be executed by an AI coding agent (e.g. Claude Code) using the eve and runpodctl skills. Open the folder, say "read AGENTS.md and get this running", and the agent deploys the vLLM endpoint, wires it in, starts the UI, and verifies the full chain against the runbook's Checks section. It also works as a normal step-by-step guide.

What's included

  • agent/defineAgent using @runpod/ai-sdk-provider (brain = self-deployed endpoint), generate_image tool, instructions, web channel.
  • app/, components/, lib/ — the Next.js chat UI.
  • AGENTS.md — deploy runbook + a Checks section capturing the non-obvious gotchas found while building this:
  • README.md (folder landing doc) + .env.example.

Verified

  • Fresh npm ci + npm run typecheck pass (Node 24); example is self-contained.
  • End-to-end confirmed: web UI → agent on the self-deployed Qwen3.6-27B-FP8 endpoint → generate_image → image rendered inline.
  • No secrets, endpoint ids, node_modules, or build artifacts committed; .env.example is the only env file tracked.

Also adds the eve entry to the root examples/README.md.

…F token

- Remove AGENTS.md/CLAUDE.md; fold a concise how-to into getting-started/README.md (no agent-first framing)
- Deploy via runpodctl --model-reference (v2.6.0+) so the model is cached once and served under MODEL_NAME (no OPENAI_SERVED_MODEL_NAME_OVERRIDE)
- Drop HF_TOKEN (model is ungated)
- Trim eve/README.md to a short index
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant