Posthorn – A self-contained email pen-pal daemon for slow, self-hosted LLMs

Posthorn, a self-contained email pen-pal daemon for slow, self-hosted LLMs, has been released. It allows users to send emails to an LLM via SMTP, which queues the request, calls an OpenAI-compatible gateway, and delivers the reply to a maildir accessible via IMAP. The tool supports threaded conversations, live new-mail notifications via inotify, and requires Linux, Rust, PostgreSQL, and an OpenAI-compatible gateway like Ollama.

posthorn posthorn A self-contained email pen-pal daemon for slow, self-hosted LLMs. You send an email to model@provider.domain over SMTP. posthorn queues an LLM completion, calls an OpenAI-compatible gateway, and delivers the reply to your maildir — readable via IMAP from any standard mail client mutt, Thunderbird, etc. . Conversations thread correctly across round-trips. How it works how-it-works ┌────────┐ SMTP ┌─────────┐ enqueue ┌─────────┐ HTTP ┌──────────┐ │ client │ ──────► │ smtp.rs │ ────────► │ llm jobs│ ───────► │ gateway │ └────────┘ └─────────┘ └─────────┘ │ ollama │ ▲ └────┬─────┘ │ IMAP │ chat │ ┌─────▼─────┐ ┌────┴─────┐ read ┌─────────┐ write ┌─────────┐ poll │ worker.rs │ │ client │ ◄────── │ imap.rs │ ◄─────── │ maildir │ ◄───── │ + lettre │ └──────────┘ └─────────┘ └─────────┘ └───────────┘ SMTP src/smtp.rs — minimal receiver; no AUTH, no TLS. Accepts mail to model-id@provider-id.<domain with + standing in for : in the model-id, so model+tag reaches model:tag , parses headers/body, resolves the thread via In-Reply-To / References , and stores the message in maildir++. Worker src/worker.rs - runs as a short-lived child process , one per job. The serve dispatcher claims pending llm jobs and spawns posthorn worker --job-id N ; the child builds the chat history from the thread, resolves the provider's gateway by name, calls it, and composes the reply email correct Message-ID / In-Reply-To / References so clients thread it . IMAP src/imap/ — IMAP4rev1 server using imap-codec for spec-correct parsing and encoding. Supports SASL AUTHENTICATE PLAIN , SELECT / EXAMINE , FETCH with BODY.PEEK HEADER.FIELDS ... subsetting , STORE \Seen / \Deleted , EXPUNGE , CLOSE , SEARCH , IDLE , and LIST . Storage — maildir++ on disk for raw .eml files. IDLE push live new-mail notifications idle-push-live-new-mail-notifications Instead of polling, IDLE uses inotify to watch the user's maildir and pushes N EXISTS the instant a message lands — so mutt shows new replies without a manual refresh. No polling, kernel-driven. Requirements requirements - Linux inotify is Linux-only - Rust edition 2021, MSRV 1.84 - PostgreSQL 15+ - An OpenAI-compatible gateway e.g. Ollama https://ollama.com Build build cargo build -r Configure configure posthorn reads a TOML config figment; also overridable via POSTHORN env vars . Example test/config.toml.example : daemon domain = "posthorn.localhost" data dir = "test/data" imap host = "127.0.0.1" port = 11143 smtp host = "127.0.0.1" port = 11025 max message bytes = 10485760 llm default system prompt = "You are a helpful test assistant. Keep replies short." default provider = "ollama" One block per OpenAI-compatible gateway. The name is the subdomain used for routing: mail to model-id@<name .<domain is sent to that gateway. llm.providers name = "ollama" gateway url = "http://127.0.0.1:11434" llm.providers name = "llama-cpp" gateway url = "http://127.0.0.1:8080" api key env = "LLAMACPP API KEY" optional; read from env at request time users email = "user@example.com" password = "hunter2" Users declared under users are seeded into the DB on startup. The mail address for a model is model-id@provider-id.<domain - e.g. glm-4.7-flash@ollama.posthorn.localhost or llama@llama-cpp.posthorn.localhost . Each provider name must match a llm.providers entry; the gateway URL is resolved from config at runtime, so different providers can point at different machines. Models are discovered automatically from each provider's gateway on startup. A model tag e.g. an Ollama quant or a multi-segment provider name is written with + in place of : — the + is translated to : for the gateway call, and translated back on the reply address so the thread round-trips. For example glm-4.7-flash+q8 0@ollama.posthorn.localhost reaches model glm-4.7-flash:q8 0 , and hf+zai-org/GLM-5.2@ollama.posthorn.localhost reaches hf:zai-org/GLM-5.2 . Replies come back from the + form, which your mail client threads normally. Run run The server subcommand serve is the default and runs SMTP + IMAP plus a dispatcher that spawns a worker child process per claimed LLM job. RUST LOG=info target/release/posthorn --config test/config.toml.example Then point an mail client at the SMTP/IMAP ports and send mail to your model. Client setup mutt client-setup-mutt set ssl starttls = no set ssl force tls = no set imap user = "user@example.com" set imap pass = "hunter2" set folder = "imap://127.0.0.1:11143" set spoolfile = "+INBOX" set smtp url = "smtp://127.0.0.1:11025" set from = "user@example.com" set imap idle = yes live new-mail push Project layout project-layout php src/ main.rs wiring: config - DB - SMTP - IMAP - dispatcher serve or single-job runner worker --job-id N cli.rs serve / worker subcommands config.rs figment TOML + env config; LlmConfig + per-provider entries smtp.rs SMTP receiver + recipient parsing model@provider.domain worker.rs runs one LLM job: builds history, resolves gateway, replies gateway.rs reqwest-based HTTP SSE-streaming client OpenAI-compatible maildir.rs maildir++ storage for raw .eml files mailparse.rs header/body extraction for inbound mail storage.rs sqlx queries + migrations imap/ mod.rs ImapServer accept + ImapConn per-connection dispatch proto.rs pure IMAP value/sequence helpers fetch.rs FETCH response construction envelope, body, sections messages.rs maildir + Postgres backend glue; inotify IDLE watcher migrations/ Postgres schema sqlx test/ example config + end-to-end roundtrip test + mock gateway Status status Early, single-purpose, no TLS. Designed for a trusted home network talking to a self-hosted LLM. Passwords are plaintext v1 — use per-user tokens, not real credentials.