We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord.
Use this to message Claude Code directly from your phone.
Second: Quick Prompts. ↯
Tabs for Get Started / Skills / Automations. Each prompt has an ID, icon keyword, and free-form text. Edit inline, duplicate, delete. Autosave skips empty entries silently.
fix-bugs pr dashboard — these are mine.
Yours will be different. That’s the point
Every card shows revision count, timestamp, and status — Needs Attention, Aging, Unlinked.
The goal isn’t just visibility. It’s that you can actually debug and intervene when something goes wrong.
That’s been the missing piece in most agent systems.
v1.0.1 was about two things: more capability, less friction.
We added Codex + Claude agent choice, long-term memory, automations, multimodal App messages (image/voice/file), OpenAI-compatible API Connect, and .agents/skills discovery.
Tentarc v1.0.1 is live.
What’s new: Codex as a new agent option (alongside Claude), long-term memory, automations, Apps can now send images/voice/files, OpenAI-compatible Custom API Connect, and Skills now detect .agents/skills.