Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
SkillForge is an AI platform mapping tech career gaps for students. Using RAG and agentic planning, it analyzes skills and builds structured roadmaps to turn learners into production-ready engineers.
A transaction layer for AI agents: preview and guard changes before execution, require human approval when needed, and revert committed actions exactly—all through WebMCP.
Student Verification, Built for AI Agents.
Less tax paperwork. More human control.
Payoff helps creators design what an audience should feel, then uses real audience reactions to discover whether the story actually got them there.
Prompt Lab — an agent-ready prompt library where humans and AI can create, organize, and reuse prompts together through WebMCP.
From prompt to post. Your agent writes it. Send invoices, cancellation requests, heartfelt letters and birthday cards through WebMCP on pieterpost.com.
Agents can't read a canvas. Nirnay gives them the exact overshoot, settling time and stability margins behind its plots, so human and agent tune the same controller together, live.
Ask a video a question. WebMCP Video finds the right moment, explains what happens, and prepares the official player at that time.
An agent can take your course, and edit it. 33 WebMCP tools scoped by route and permission.
A shared 256x256 pixel canvas where you choose the zone and your browser agent paints it. Three WebMCP tools split the work: humans pick the spot, agents place the pixels.
An analytics workspace where the AI agent does the whole analysis without ever seeing your data. It stays in DuckDB in your tab; WebMCP tools return only aggregates. Raw rows need your approval.
Agents move the work. Policy makes the call. An agent triages 40 expenses in one WebMCP call; the server (not the agent) decides and authorizes every money action.
An agent redacts a document it is not allowed to read. WebMCP tools return only structure — masked previews, counts, pages. Every real value and every irreversible step waits for a human click.
AI-Powered Visual Database Designer
Two-hop WebMCP discovery and execution for better decisions
Human guided incident recovery where AI agents investigate disruptions, compare recovery options, and execute approved plans through WebMCP.
Live LaTeX workspace, co-authored with your agent.
Speak your ideas. STICK builds the presentation.
An agent that finds money your transactions should have returned.
One verified chessboard. Two native interfaces. Humans and AI agents share every turn through WebMCP.
Lopaka is a tool for designing GUI for small displays. It generates code and all the graphics you need, plus it has a ton of assets.
Your agent chronicles the campaign as you play, then recalls it by meaning weeks later. The whole codex lives in your tab, powered by ExtendDB. Your codex never leaves the page.
Eleven native WebMCP tools turn a 12-step reflection into a safe human-agent workflow: the agent clarifies and navigates, the browser scores, and the person confirms every choice.
1993 – 2016 of 2474
