Render any input as a portico – a three-layer ASCII visualization.
Project description
Try it online • Try it locally • Example • Inputs • Customization
About
portico renders input as a three-layered visual abstraction.
- An LLM reads your input, classifies it, and decomposes it into three layers
_ii^: roof, pillars, base. - The renderer turns those layers into a fixed ASCII shape that resembles a portico.
- It builds a tiny monument for the thing you're trying to understand.
| Glyph | Layer | Meaning |
|---|---|---|
^ |
Roof | The unifying idea |
ii |
Pillars | The load-bearing components |
_ |
Base | The foundation everything rests on |
Try it locally
Install
uv tool install portico-cli
portico README.md
portico https://example.com/article
portico ./src --no-legend
echo "your text here" | portico -
Try it online
Run portico in your browser, no install required:
–> Hugging Face Space <–
The space uses 🦙 Llama 3.3 70B via Groq. Paste input and render.
Example
portico "https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture)"
── encyclopedia article: Transformer ──────────────────────────────────────────
***
=== ◇ ===
╔═══════════════════════════════════════════════════════════════════╗
║ Attention Is All You Need ║
╚═══════════════════════════════════════════════════════════════════╝
////º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º\\\\
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
▀██▀ ▀██▀ ▀██▀ ▀██▀ ▀██▀
██ ██ ██ ██ ██
██ ██ ██ ██ ██
Predecessors Architecture Training Efficiency Applications
██ ██ ██ ██ ██
██ ██ ██ ██ ██
▄██▄ ▄██▄ ▄██▄ ▄██▄ ▄██▄
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
╔═════════════════════════════════════════════════════════════════════════════╗
║ Scaled dot-product attention ║
╚═════════════════════════════════════════════════════════════════════════════╝
legend:
^ Attention Is All You Need: The 2017 thesis that pure attention, with neither
recurrence nor convolution, suffices for sequence-to-sequence modeling —
yielding parallel training and the foundational architecture of modern AI.
ii Predecessors: RNN and LSTM seq2seq models suffered from vanishing gradients and
sequential bottlenecks; Bahdanau and Luong attention bolted onto these
recurrent backbones in 2014-15 set up the 2017 Vaswani et al. paper to drop
recurrence entirely.
ii Architecture: Tokenization, learned embeddings, and sinusoidal or learned
positional encoding feed stacks of multi-head self- and cross-attention plus
position-wise feedforward sublayers, composed into encoder-only, decoder-only,
or full encoder-decoder variants with residual connections and layer
normalization throughout.
ii Training: Self-supervised pretraining on masked, autoregressive, or prefix-LM
objectives followed by supervised fine-tuning, with Adam-family optimizers and
warmup schedules, and pre- vs post-norm placement materially shaping
convergence at depth.
ii Efficiency: KV caching, FlashAttention's I/O-aware kernels, multi-query and
grouped-query attention, speculative decoding, and sub-quadratic variants such
as Linformer, Performer, and state-space hybrids cut the memory and compute
costs of training and inference.
ii Applications: Transformers underpin systems across NLP (BERT, GPT, T5), vision
(ViT), speech (Whisper), code, multimodal generation (DALL-E, GPT-4o),
structural biology (AlphaFold), robotics, and reinforcement learning.
_ Scaled dot-product attention: The atomic operation that computes a softmax-
weighted average of value vectors, with weights given by scaled query-key dot
products — the single load-bearing mechanism from which multi-head, self-,
masked, and cross-attention all derive.
──────────────────────────────────────────────────────────── built with _ii^ ──
Run with claude-sonnet-4-6.
Inputs
- Raw text or stdin
- Local files and directories
- URLs (page content is extracted)
- Git repositories
When an input doesn't fit a three-layer shape – poems, flat lists, gibberish – portico refuses honestly rather than fake one.
Customization
| Flag | What it does |
|---|---|
--no-legend |
Hide the per-layer summary (legend renders by default) |
--reapex=N |
Pin the apex to seed N (random by default; pool of 600+ variants) |
--json |
Emit the analyzer's JSON instead of rendering |
--diagnose |
Print a pipeline report (input type, model, fit quality) and exit |
Run portico --help for the full list.
Apex
The apex is the ornament crowning the portico — picked at render time from a pool of 600+ variants.
🎲 --reapex=SEED pins a specific composition to reproduce.
portico https://0trm.blog/data-science-at-camp-nou/ --reapex=0
── essay: Data Science at Camp Nou ─────────────────
▲ * ▲
~~~ ▲ ~~~
╔════════════════════════════════════════╗
║ Data-Driven Ticketing ║
╚════════════════════════════════════════╝
////º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~\\\\
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
▀██▀ ▀██▀ ▀██▀
██ ██ ██
██ ██ ██
Analytics Experimentation Predictive
██ ██ Modeling
██ ██ ██
██ ██ ██
▄██▄ ▄██▄ ▄██▄
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
╔══════════════════════════════════════════════════╗
║ Fan Behavior ║
╚══════════════════════════════════════════════════╝
portico https://0trm.blog/data-science-at-camp-nou/ --reapex=1
── essay: Data Science at Camp Nou ─────────────────
◆ ◆
═══ ◆ ═══
╔════════════════════════════════════════╗
║ Data-Driven Ticketing ║
╚════════════════════════════════════════╝
////º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~\\\\
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
▀██▀ ▀██▀ ▀██▀
██ ██ ██
██ ██ ██
Analytics Experimentation Predictive
██ ██ Modeling
██ ██ ██
██ ██ ██
▄██▄ ▄██▄ ▄██▄
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
╔══════════════════════════════════════════════════╗
║ Fan Behavior ║
╚══════════════════════════════════════════════════╝
portico https://0trm.blog/data-science-at-camp-nou/ --reapex=7
── essay: Data Science at Camp Nou ─────────────────
· · ·
░░░ ▲ ░░░
╔════════════════════════════════════════╗
║ Data-Driven Ticketing ║
╚════════════════════════════════════════╝
////º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~~º~\\\\
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
▀██▀ ▀██▀ ▀██▀
██ ██ ██
██ ██ ██
Analytics Experimentation Predictive
██ ██ Modeling
██ ██ ██
██ ██ ██
▄██▄ ▄██▄ ▄██▄
░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
╔══════════════════════════════════════════════════╗
║ Fan Behavior ║
╚══════════════════════════════════════════════════╝
License
MIT
Built by with AI.
© 2026 trm
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
portico_cli-0.1.4.tar.gz
(24.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file portico_cli-0.1.4.tar.gz.
File metadata
- Download URL: portico_cli-0.1.4.tar.gz
- Upload date:
- Size: 24.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0333bfe1b0bbf5a28114599c93ee48aa0711f0c65b438be2eadce01a7814ec50
|
|
| MD5 |
6419fc6ffcdc811b9cd99899a7301ef5
|
|
| BLAKE2b-256 |
bd1c8ed6821b157ae64829359aa68105a0810990e8b1b5b4315d06136fcb170d
|
File details
Details for the file portico_cli-0.1.4-py3-none-any.whl.
File metadata
- Download URL: portico_cli-0.1.4-py3-none-any.whl
- Upload date:
- Size: 32.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b2b13b8302523c29414aef996404f85804a19e5753e414b36f7e6b6eaf7fe93f
|
|
| MD5 |
deabe8ef1870a951583b8533733e8d78
|
|
| BLAKE2b-256 |
7c48fda50875d710f6fe84f529861cf5a12965aa884250e6264b8960e4fb03b2
|
