网页
综合
更新时间 2026-11-16 16:45:33
HF26 DEV Challenge Hub - DEV Challenges - DEV Community
自动蜘蛛
dev.to
正文约 5999 字
Five challenges, one prompt, a new theme every week.
Follow #hf26challenge for theme reveals →
This year's Hacktoberfest is not about open source pull requests. There's no PR count to hit and no repos to hunt for. Instead, you build a brand-new project with open-source AI at its core, and write about it on DEV. Here's everything you need to know about Hacktoberfest 2026.
Hacktoberfest is here, and this year we're running five DEV Challenges back to back, all month long. Every challenge uses the same prompt. Every challenge gets its own theme, and each theme stays secret until the day it launches.
Joining late? No problem. Every challenge is a fresh start, so someone who finds us in week four competes on the same footing as someone who's been here since day one.
Every challenge has its own winners, and we'll share each challenge's prizes when it launches. Here's what's up for grabs in the Weekend Challenge:
Overall winner: $250, a DEV++ membership, and an exclusive DEV badge.
Featured partner categories: $200 for each winner.
Partner categories: $100 for each winner.
Every winner also gets an exclusive DEV badge, and everyone with a valid submission gets a completion badge.
Free partner credits
Several partners are giving participants credits and promo codes, including Tinker, Render, Backboard, and a free .tech domain. Claim yours at hacktoberfest.com/my/promos.
Build something with open-source AI at its core.
That can mean running an open-weight model, building on an open-source agent harness or framework, running inference locally, or all three. Whatever you pick, the open pieces should be what makes your project work.
In your post, tell us why open innovation matters for what you built. Does it run on a laptop with no internet? Keep someone's data off a server they don't control? Let you fine-tune, swap models, or change how your agent behaves? Cost nothing to run? Tell us where your open-based approach worked better than a closed one.
Show your work. We'd love to see how you built it. Save your agent session with DevRelay and embed it in your post, or link to it. It's optional, but it helps the judges understand your process.
$200 for each winner
Use Render as your project's AI runtime, to host an agent's front end, or to run Hermes or OpenClaw.
Use TabPFN, Prior Labs' tabular foundation model, to forecast, predict, classify, or spot anomalies from historical data like a CSV. Prior Labs strongly recommends the latest version, TabPFN-3.5: it's open-weight and free to use once you sign the non-commercial license at platform.priorlabs.ai, and you can then run it locally. The API adds features like Thinking Mode. Prior Labs favors projects that use TabPFN inside a wider prediction agent (with or without the MCP server).
Use Thinking Machines' Tinker to fine-tune a model for a specific task, and show a clear improvement in performance, latency, or cost over a baseline.
Build with an Arduino UNO Q: run a model on the board, build a physical agent that senses and acts, or optimize a model for it with Qualcomm AI Hub. Open to anyone building with an UNO Q, whether you got one at an in-person Fest or have your own.
Build or deploy your project on DigitalOcean: host your app or agent, run an open-weight model on a GPU Droplet (1-Click Models make this quick), or build an agent on the Gradient AI Platform.
Use Gemma, Google's open-weight model, in building your project: run it locally, fine-tune it, or serve it through Google Cloud or another provider.
$100 for each winner
Use Auth0 for AI Agents: sign users in to an agent, call tools on a user's behalf with Token Vault, ask a person to approve a risky action before the agent takes it, or limit what a RAG pipeline can retrieve with fine-grained authorization.
Build with R-CLI, Backboard's open-source terminal coding agent, compare open-weight models through a single Backboard API key, or give an open-source project's assistant memory and RAG.
Give an open-source agent a voice, transcribe audio for a local model, or generate narration for your demo.
Give your agent a real browser: drive a live site end to end using Stagehand's SDK, pull the context an open-weight model reasons over, or turn a one-off agent run into a repeatable workflow.
Share the agent sessions behind your project in the write-up, or search past agent work to explain why code exists.
Build with Copilot's coding agent, the Copilot CLI, or the new Copilot app, automate your project with GitHub Actions, or review contributors' PRs with Copilot.
Orchestrate an agent over open models, add memory and tools to a chat agent, or build a workflow that triages GitHub issues.
Use Atlas as your data layer: Atlas Vector Search for retrieval, long-term memory for an agent, or the database behind an app built on an open-weight model.
Put Ultramarine, Paper Instruments' model, to work on something real: research, analysis, drafting, or an agent that reasons over a pile of documents. Call it with the OpenAI or Anthropic SDKs, and say what your run actually cost. Claim $5 of free credit at hacktoberfest.com/my/promos.
Show your agent's work: how it's set up, how it performs (latency, tokens, cost), what you found, and how you debugged it. Include traces or screenshots in your write-up.
Give an agent live web search, ground a RAG app in fresh results, or track news for an open-source project.
Put your project live on a .tech domain you claimed through Hacktoberfest, and link to it in your write-up. Claim a free first-year .tech domain at hacktoberfest.com/my/promos (it renews at $29.99 a year).
Make your agent durable. Wrap it in a Temporal workflow so it survives failures, retries flaky tool calls, and picks up where it left off.
Store embeddings with pgvector, run hybrid keyword and vector search for an agent, or let an agent manage a database through Tiger MCP.
Partner categories may change from challenge to challenge as new partners join.
Pick the challenge that's live, then publish a post on
本页为82搜索生成的网页快照,内容来自站内索引;演示数据的原文链接仅作示例。