Urgent.News

What's breaking now, across hundreds of outlets.

Tech

Mingle (MIT): Bring Your Local Coding Agents into Slack, Discord, Telegram & More — With Zero Servers

Bringing your own coding agent (Claude Code, Codex, Cursor, OpenCode, Kimi Code, etc.) into custom tooling is pretty common now. What still bothered me about most agent-to-IM bridges was the cloud relay : if a third-party server sits between your chat apps and your agent, your private work conversations pass through someone else's infrastructure—bringing both the risk of a server breach and the…

Mingle is a new desktop application that allows users to integrate their local coding agents, such as Claude Code or Kimi Code, directly into popular chat platforms like Slack, Discord, Telegram, iMessage, WeChat, Feishu/Lark, WeCom, DingTalk, QQ, and GitHub Issues/PRs. The app is built with security and privacy in mind, as it operates without any servers or third-party relays.

All connections are made directly to the chat platform's official bot interface, and credentials are stored securely in the OS keychain. The app also ensures that the agent's memory and persona are stored as local files, allowing for a seamless experience across different platforms. Mingle enables users to have a single, unified memory for each agent across all chat apps, making it easy to refer to information from one platform in another.

It also supports running background tasks while staying responsive in chat, and automatically adapts its behavior in busy channels to minimize spamming. Currently, Mingle supports 14 different coding agents and is still in early development, with plans for further improvements and additional features in the future.

Rewritten by urgent.news; may contain errors — check the original.

Read the original at dev.to →

Report a problem with this story

More in Tech

My --config-test accepted a listen address that could never bind

transponder is a Go proxy I've been building. It has a --config-test flag: load the config, validate it, exit 0 or 1. It runs in CI and in the deploy script before anything starts.

  • Configuration test passed despite invalid listen address ":nope"
  • Server crashed 200ms after passing --config-test
  • Author added rule to reject unspecified addresses with same port

Interaction Nets Explained: The Programming Model Behind the Frostbite CPU

On November 18, 2026, the chip-design startup Architect Labs published a post introducing Frostbite . They describe it as a general-purpose CPU with a new instruction set.

  • Interaction nets enable Frostbite's energy-efficient programming model
  • Programs represented as graphs with nodes and wires in interaction nets
  • Frostbite's quad achieved 4.59x better performance per watt using interaction nets

The Fix That Brought the Bug Back

I use a second iPhone at home through a stream ( the setup ): the phone's screen comes off USB as H.264, an old laptop's GPU re-encodes it, and a fork of Sunshine streams it to my main phone.

  • Bug resurfaces after initial fix, causing connection delay and termination
  • Transcoder fixes include timeout for bus threads and replays for new viewers
  • System functionality restored with updated transcoder and fallback mechanism

More from Saturday 21 November →