Miaw AI Secretary goes open source

// 46d agoOPENSOURCE RELEASE

Miaw AI Secretary goes open source

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

Miaw AI Secretary is a Windows-first Electron recreation of the Miaw floating chat app, built to stay on screen with a tray icon and global shortcut. The repo ships Tauri-compatible shims, chat and history command surfaces, and a LiteLLM-friendly model setup for local or remote endpoints.

// ANALYSIS

This looks more like a pragmatic desktop reimplementation than a polished consumer launch, but that is exactly what makes it interesting: it lowers the barrier to forking and experimenting with an always-available AI sidecar.

–The Electron shell plus `Ctrl+Shift+Space` shortcut makes the assistant feel like a lightweight overlay instead of a full app switch
–Compatibility shims for Tauri APIs suggest the author is preserving an existing UI surface rather than rewriting the product from scratch
–The default LiteLLM-compatible OpenAI endpoint makes it easy to point at local models or self-hosted backends
–Search is still stubbed and some macOS-specific flows fall back to safe defaults, so this is more foundation than finished secretarial workflow
–As an open-source desktop assistant, it fits the broader trend toward customizable AI companions, but it is not yet a standout devtool

// TAGS

chatbotopen-sourceautomationagentmiaw-ai-secretary

DISCOVERED

46d ago

2026-04-30

PUBLISHED

47d ago

2026-04-30

RELEVANCE

5/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE43m ago

Moonshot AI open-sources Kimi Code CLI

Moonshot AI has released Kimi Code CLI under the MIT license, a terminal-based AI coding assistant optimized for running long-horizon agentic workflows in local environments. The tool assists developers with tasks like debugging and refactoring, automatically handling read-only actions while requesting explicit confirmation for file modifications or shell commands.

MODEL1h ago

DeepSeek has launched its V4 model series, featuring a 1.6-trillion parameter open-weights Mixture-of-Experts model that challenges proprietary frontier systems.

DeepSeek has released the DeepSeek-V4 model series, featuring the flagship 1.6-trillion parameter DeepSeek-V4-Pro MoE model alongside the 284-billion parameter DeepSeek-V4-Flash. Designed to rival top closed-source frontier models, DeepSeek-V4 supports a 1-million-token context window powered by efficient compressed attention mechanisms. The model series is notable for its inference efficiency—activating only 49 billion parameters per token—and its training optimization on Huawei Ascend 950PR hardware, demonstrating high-end capability independent of Nvidia infrastructure.

OPEN SOURCE1h ago

Gortex cuts coding agent token usage 50x

Gortex is a local-first, Go-based code graph engine that indexes repositories to resolve references and call chains in sub-milliseconds. By providing structured context directly to AI agents via CLI, MCP server, and a web UI, it avoids context window bloat and reduces token usage by up to 50x.