Context
Stays in the room
Holds the files and decisions of the session you are already in.
An agent that stays open beside your work. Local-first, always running.
Install via terminal
curl -fsSL letronna.ai/install.sh | shCapabilities
Context
Holds the files and decisions of the session you are already in.
Memory
Plain text you can open, edit and delete. A file, not a black box.
Local
Real files, real commands. Nothing leaves unless you send it.
Schedule
Briefings and backups on a cadence you describe in a sentence.
Delegate
Subagents with their own terminals, reporting into one thread.
Extend
MCP servers, shell tools and HTTP endpoints, wired in directly.
Platforms
13+, Apple silicon & Intel
Download .dmg38 MB11, x64 & ARM64
Download .exe41 MBAny distro, glibc 2.31+
Download .AppImage44 MBNo. The app runs locally with your own model keys. An account only exists for hosted models and cloud deploy on Pro.
On your disk. Context and memory are plain-text files under ~/.letronna. Nothing leaves the machine unless you connect a hosted model.
Any OpenAI-compatible endpoint, Anthropic, local models through Ollama or llama.cpp, and the hosted pool on Pro.
Yes. Memory is written to disk as you work and loaded on the next launch. Edit or delete it like any other file.
Scheduled runs pause unless you have deployed to cloud. Nothing runs on your machine while the app is closed.
The agent runtime is Apache-2.0 on GitHub. The hosted model pool and cloud deploy are the paid parts.
Pricing
Free
$0forever
Bring your own keys.
Pro · Most chosen
$20per month
Hosted models included.
Team
$18per seat, monthly
Shared memory, shared agents.
Prices in USD. Local use is free forever; you only pay for hosted models and cloud.