Remindly launches unified notes with MCP support

// 5h agoPRODUCT LAUNCH

Remindly launches unified notes with MCP support

Solo developer Dylan Roy has launched Remindly, a cross-platform notes app where any note can carry time- or location-based reminders. The application features offline-first local Markdown storage, on-device AI search, and a built-in MCP server for Claude and ChatGPT integration.

// ANALYSIS

Remindly demonstrates how personal knowledge tools should adapt to the agentic era by shipping first-class MCP endpoints instead of walled silos. Exposing notes and reminders as structured, tool-callable resources bridges the gap between daily note-taking and autonomous AI assistants.

–Native MCP endpoint (/mcp) enables Claude and ChatGPT to search, create, and append notes using standard OAuth tool calling
–Dual AI execution keeps on-device queries private via Apple Intelligence or local models while selectively routing external requests
–Offline-first architecture exports clean Markdown folders with attachments, simplifying migration from legacy tools like Evernote
–Free tier supports unlimited notes across two devices, while a $49/year Pro plan adds cross-platform sync and 100 GB attachment storage

// TAGS

remindlymcplocal-firsttool-useagentdevtool

DISCOVERED

5h ago

2026-11-15

PUBLISHED

9h ago

2026-11-15

RELEVANCE

5/ 10

AUTHOR

Dylan Roy

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE1h ago

GGML hits 1.0, slashes prompt latency

The foundational C/C++ tensor library behind llama.cpp has officially reached version 1.0.0, establishing a stabilized public API alongside significant prefill and inference optimizations. Benchmarks demonstrate immediate performance gains on unchanged hardware, cutting runtime on a 50K-token prompt from 4:22 down to 3:59.

RESEARCH2h ago

NVIDIA cuts reasoning distillation compute 38%

NVIDIA researchers demonstrate that forward-KL reasoning LLM distillation requires supervising students on only the teacher's top probability tokens rather than the full vocabulary. Distilling exclusively from truncated teacher support matches full-distribution benchmark accuracy while cutting training step time by 38% and peak memory by 24%.

NEWS3h ago

Developer argues AI code belongs open source

Open-source developer Jakub Jankiewicz argues that software generated by AI should be released under open-source licenses or dedicated to the public domain via CC0. He contends that training models on open repositories without attribution amounts to license laundering, while purely machine-generated code lacks human authorship under copyright law.