vibehacker
News
GitHub (deepseek-ai/dsh-superagent-prototype) ·

DeepSeek open-sources dsh-superagent, a prototype agent that takes GitHub requests and answers with PRs

Published Oct 31 under MIT as a bundle for DeepSeek Harness, it watches one GitHub repo (and optionally Feishu), opens a work item when an allowed person asks, works in its own session and directory, and replies in the original thread, for example with a pull request, while a web panel shows what needs a human. DeepSeek labels it research code, not an official product, and setup is meant to be done by asking your coding agent to follow its SETUP.md.

Read at github.com

More news

View all

Google Workspace MCP servers will reject OAuth clients not marked as AI agents from Nov 11

If your agent calls the Gmail, Drive, Docs, Calendar or Chat MCP servers, tick "Use this client for an AI powered agent" on its OAuth client in Google Auth Platform Clients before Nov 11, when unmarked clients start getting rejected. After Nov 12 the setting locks, so a missed client means creating a new agentic one and updating your MCP config; REST only apps aren't affected (setup guide)…

Google Workspace Developer Release Notes

Smithery's MCP proxy is now shut down, so run.tools and server.smithery.ai URLs have stopped working

As of Oct 31, Smithery's proxy, accounts, API keys, Connect, Toolbox, CLI and SDKs are gone, and smithery.ai stays only as a public directory now powered by Arcade.dev, with paid plans refunded back to Aug 5. Search your .mcp.json or .cursor/mcp.json for run.tools , server.smithery.ai and @smithery/cli and swap each for the vendor's official URL, like https://mcp.linear.app/mcp (migration list)…

Smithery

Breakwise 0.3.0 ships an offline CLI for its open registry of tested Python breaking changes

Released Oct 31, pip install breakwise bundles a copy of the registry so breakwise explain BW 2026 0001 shows a notice offline: the package, the release that breaks your code, and a before and after fix that's run against real PyPI releases before it's accepted. A command that finds the code an upgrade breaks is next, and the notices are CC BY 4.0 if you want to feed them to your agent (GitHub)…

PyPI (breakwise)

Octomind 0.67.0 lets its open-source CLI agent schedule MCP tool calls that run without a model turn

Released Oct 31, the agent's schedule tool now takes a tool call instead of a message, firing it directly at a set time, on idle or on a repeat ( every: "10m" ), with permissions and guardrails re checked at fire time and busy repeats skipping a tick instead of piling up. The release also tracks per session agent run history with main model costs and moves octohub and ChatGPT calls onto one persistent WebSocket, which is a breaking config change for per model transport (changelog)…

Octomind Blog

fastbrowse, an MIT browser agent, picks clicks from the page's real elements instead of screenshots

Launched Oct 30 on Show HN and Product Hunt, it lists each page's buttons, links and fields and has a small choice model (Jev) pick the next step, falling back to a cheap LLM when unsure, cites a page quote for every claim, and holds submit, pay, delete and send until your code allows them; try it with uvx fastbrowse "..." local or via its MCP server and agent skill. The makers report $0.030 per run versus $0.318 for Browser Use's hosted agent on their own 46 task suite, so treat that as self reported (Show HN recap)…

GitHub (agent-labs-dev/fastbrowse)

Spotted something we missed? Start a thread.