feat(eve): Getting Started with Eve on Runpod — self-hosted LLM agent + web UI#19
Open
TimPietruskyRunPod wants to merge 4 commits into
Open
feat(eve): Getting Started with Eve on Runpod — self-hosted LLM agent + web UI#19TimPietruskyRunPod wants to merge 4 commits into
TimPietruskyRunPod wants to merge 4 commits into
Conversation
…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
…-name mismatch); add /models verify step
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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-FP8on vLLM, OpenAI-compatible), with agenerate_imagetool backed by a Runpod image model, behind a Next.js web chat UI.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 theeveandrunpodctlskills. 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/—defineAgentusing@runpod/ai-sdk-provider(brain = self-deployed endpoint),generate_imagetool, 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:MODEL_NAME(usesOPENAI_SERVED_MODEL_NAME_OVERRIDE; see Served model name becomes snapshot path when HF cache dir is lowercased (MODEL_NAME 404 regression, FDE-174) runpod-workers/worker-vllm#310),qwen3_xmltool-call parser for Qwen3.6,modelContextWindowTokensfor a custom (non-gateway) model,public/generated/,README.md(folder landing doc) +.env.example.Verified
npm ci+npm run typecheckpass (Node 24); example is self-contained.generate_image→ image rendered inline.node_modules, or build artifacts committed;.env.exampleis the only env file tracked.Also adds the
eveentry to the rootexamples/README.md.