dead-letter

<!-- mcp-name: io.github.BigCactusLabs/dead-letter -->

<p align="center">
  <img src="https://raw.githubusercontent.com/BigCactusLabs/dead-letter/main/docs/brand/production/readme-logo.png" width="128" alt="dead-letter">
</p>

# dead-letter

[![PyPI package](https://img.shields.io/pypi/v/dead-letter?label=PyPI%20package&cacheSeconds=300)](https://pypi.org/project/dead-letter/)
[![Python versions](https://img.shields.io/pypi/pyversions/dead-letter?label=Python&cacheSeconds=300)](https://pypi.org/project/dead-letter/)
[![License: PolyForm Noncommercial](https://img.shields.io/badge/License-PolyForm%20Noncommercial-purple.svg)](https://github.com/BigCactusLabs/dead-letter/blob/main/LICENSE)

**Turn `.eml` email exports into clean, local, LLM-ready Markdown.**

dead-letter converts `.eml` email exports into clean Markdown with YAML front matter — threads split, signatures stripped, attachments extracted, calendars parsed. One file or ten thousand.

Use it to build a readable email archive, move messages into Markdown-based knowledge systems, or prepare email for RAG and LLM pipelines without feeding raw MIME and base64 into your context window. No account, upload, or API key required.

## ⚡ Try it

If you already have [`uv`](https://docs.astral.sh/uv/), run dead-letter without installing it globally:

```bash
uvx --python 3.12 dead-letter convert message.eml
```

Or install with Homebrew or pip below. Agents and MCP clients can use the client-specific setup in [`llms-install.md`](https://github.com/BigCactusLabs/dead-letter/blob/main/llms-install.md).

## 🎯 Common use cases

- **Email → Markdown archives** — turn exported `.eml` collections into readable, portable Markdown with structured metadata
- **RAG and LLM ingestion** — normalize message text, thread structure, links, and attachment metadata before chunking or indexing
- **Agent workflows** — expose conversion and diagnostics directly to Claude, Codex, and other MCP clients
- **Knowledge bases** — move email into Markdown-first systems such as Obsidian, static archives, or local search pipelines
- **Digital preservation** — retain human-readable content and useful message structure without depending on one mail client

## ✨ Features

- **Full-fidelity conversion** — HTML sanitization, Gmail/Outlook thread segmentation, inline image handling, and calendar event summaries
- **CLI** — point it at a file or a directory and go
- **Local web UI** — dark command-center interface with drag-and-drop import, watch mode, conversion grade badges, processing history, and per-job diagnostics
- **Inbox/Cabinet workflow** — drop `.eml` files into an Inbox, let dead-letter organize the Markdown bundles into a Cabinet
- **Install validation** — `dead-letter doctor` checks your runtime environment
- **Conversion report** — opt-in JSON report with per-file diagnostics, including attachment referenced/retained counts for automation and audit
- **MCP server** — integrate with Claude Desktop, Claude Code, Codex, and other MCP clients
- **Claude plugin** — marketplace install in Claude Code or Cowork with five slash commands (`/dead-letter:convert`, `/dead-letter:summarize`, `/dead-letter:triage`, `/dead-letter:cabinet`, `/dead-letter:mbox`)
- **Portable Agent Skill** — teaches skill-aware agents when and how to convert `.eml` files
- **Python API** — `from dead_letter import convert` and you're off

## 🧠 Built for LLM Pipelines

Raw `.eml` files are noisy input for downstream LLM and retrieval pipelines — MIME headers, multipart boundaries, duplicated HTML/plain bodies, and encoded attachments all get mixed into the text path.

dead-letter normalizes that into Markdown with YAML front matter, so message text and metadata are ready for chunking or indexing without MIME parsing or base64 cleanup. Default `convert()` and `convert_dir()` runs write a single `.md` per message and keep attachment names in front matter.

To separate the filesystem artifacts too, bundle and Cabinet workflows write `message.md` plus retained decoded files under `attachments/`. The Markdown is ready for text ingestion, while PDFs, spreadsheets, calendar files, and other retained binary attachments stay cleanly split out for whatever downstream parser you already use.

For direct LLM integration, the MCP server lets clients call dead-letter's conversion tools without shelling out. Conversion is local; your chosen MCP host may still send returned email text to a remote model.

### 📊 Token-cost benchmarks

dead-letter's value isn't fewer tokens than every alternative — it's **fidelity per token**: keeping useful email structure without carrying raw MIME into context. Measured across an 11-message synthetic corpus of HTML threads, attachments, and newsletters (tokenizer `o200k_base`, structured thread mode):

- **~88% fewer tokens than the raw `.eml`** in the reported aggregate comparison — the attachment category's median is ~126k tokens raw vs ~180 converted.
- **Structure survives** — thread structure, per-message sender attribution, links, and attachment metadata remain readable. The tested naive baselines are often cheaper because they discard information (0/2 attachment names retained vs dead-letter's 2/2).

Those counts measure the Markdown representation, not the contents of retained binary attachments or downstream answer quality. The shipping default is latest-message mode; the benchmark uses structured mode for a same-thread comparison.

The benchmark is honest about where it loses: naive extraction is fewer tokens when you don't mind throwing away metadata, links, and thread structure. Full method, the complete table (including those rows), tokenizer disclosure, and a one-command reproduce are in [`benchmarks/`](https://github.com/BigCactusLabs/dead-letter/tree/main/benchmarks/).

## 📦 Install

Pick one route. The [distribution map](https://github.com/BigCactusLabs/dead-letter/blob/main/docs/reference/distribution.md) explains how the channels fit together; installing all of them is not necessary.

| You want | Start here |
| --- | --- |
| Core CLI or Python API | Homebrew / pip below, or the `uvx` quick try |
| Local web UI | `dead-letter[ui]` below |
| Claude Desktop extension or another MCP client | [MCP Server](#-mcp-server) |
| Claude Code / Cowork commands | [Plugin](https://github.com/BigCactusLabs/dead-letter/blob/main/plugin/README.md) |
| Container-isolated MCP | [Containers](https://github.com/BigCactusLabs/dead-letter/blob/main/docs/reference/containers.md) |
| Portable agent instructions | [Agent Skill](#agent-skill-any-host) |

With Homebrew on Apple silicon macOS:

```bash
brew tap BigCactusLabs/tap
brew install dead-letter
```

The Homebrew formula installs the core CLI only: `dead-letter convert` and
`dead-letter doctor`. It intentionally does not bundle the optional web UI or
MCP server dependency stacks.

With pip:

```bash
pip install dead-letter            # core + CLI
pip install 'dead-letter[cli]'      # + watchfiles (used by backend/UI watch mode)
pip install 'dead-letter[ui]'       # + web UI, API server, and watch mode
pip install 'dead-letter[mcp]'      # + MCP server
```

Use [pipx](https://pipx.pypa.io/) for an isolated UI or MCP install:

```bash
pipx install 'dead-letter[ui]'      # installs dead-letter and dead-letter-ui
# Or, for MCP instead:
pipx install 'dead-letter[mcp]'     # installs dead-letter and dead-letter-mcp
```

Or run individual entrypoints without a global package install using `uvx`:

```bash
uvx --python 3.12 dead-letter convert message.eml
uvx --python 3.12 --from 'dead-letter[mcp]' dead-letter-mcp
```

uv caches tools/dependencies and may download Python on first use. These
unpinned trial commands do not promise a fresh latest version on every run;
see [version pinning](https://github.com/BigCactusLabs/dead-letter/blob/main/docs/reference/distribution.md#pin-the-thing-you-actually-install)
for a reviewed deployment.

From source:

```bash
git clone https://github.com/BigCactusLabs/dead-letter.git
cd dead-letter
uv sync --extra dev --locked     # all extras
# Or choose only the surface you're developing:
uv sync --extra ui --locked      # UI only
uv sync --extra mcp --locked     # MCP only
```

### Agent Skill (any host)

Install the portable Agent Skill into whichever agent you use:

```bash
gh skill install BigCactusLabs/dead-letter dead-letter --agent claude-code
gh skill install BigCactusLabs/dead-letter dead-letter --agent codex
gh skill install BigCactusLabs/dead-letter dead-letter --agent github-copilot
```

Needs `gh` 2.90 or newer. The skill is independent of the Claude plugin. Pin a
reviewed skill tag/commit for reproducibility; the default latest release can
also be a plugin release. For exact pin syntax, other hosts, manual installation,
and discovery metadata, see [Agent Discovery](https://github.com/BigCactusLabs/dead-letter/blob/main/docs/reference/agent-discovery.md).

## 🚀 Quick Start

**CLI** — convert a single file:

```bash
dead-letter convert message.eml
```

Convert a whole directory:

```bash
dead-letter convert inbox/ --output out/
```

Generate a JSON conversion report alongside the output:

```bash
dead-letter convert inbox/ --output out/ --report
```

With `--output`, the report is written to that output directory as
`.dead-letter-report.json`. Without `--output`, file conversions write the
report next to the source message and directory conversions write it to the
input directory root.

Check your runtime environment:

```bash
dead-letter doctor
```

Directory conversion scans recursively for `.eml` files, matches the suffix
case-insensitively, skips symlinked files whose resolved targets escape the
requested input tree, and deduplicates in-tree symlink aliases that resolve to
the same message file.

**Web UI** — start the local server:

```bash
dead-letter-ui --host 127.0.0.1 --port 8765
```

Open `http://127.0.0.1:8765` — on first launch, a setup prompt suggests default Inbox and Cabinet folders. Configure those