Metadata-Version: 2.4
Name: manifold-ai
Version: 2.3.0
Summary: Manifold: nodes publish one value each; agents read it as text, people see it as a picture; your machines share it.
License-Expression: Apache-2.0
Project-URL: Homepage, https://github.com/Manifold-agents/manifold
Project-URL: Repository, https://github.com/Manifold-agents/manifold
Project-URL: Issues, https://github.com/Manifold-agents/manifold/issues
Classifier: Operating System :: MacOS
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Environment :: Console
Classifier: Environment :: Web Environment
Classifier: Topic :: Software Development :: Libraries
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: End Users/Desktop
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: jsonschema>=4.18
Requires-Dist: starlette>=0.37
Requires-Dist: uvicorn>=0.29
Requires-Dist: keyring>=24
Requires-Dist: iroh>=1.1
Requires-Dist: certifi>=2024.2
Requires-Dist: websockets>=13
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"
Requires-Dist: httpx2; extra == "dev"
Requires-Dist: httpx; extra == "dev"
Dynamic: license-file

# Manifold

Manifold runs live nodes on your Mac and shows them to people and agents at once. Each node publishes one value.
People see it as a card on a canvas. Agents read it as text and press its actions from the command line. A manifold
is a set of nodes arranged for a purpose: a trading desk, a research queue, a household.

It runs on your machine with your accounts. Other machines join by invitation and see what you grant them. No one's
code runs on anyone else's machine.

This release is for **macOS**. Apple silicon gets the Rust door; Intel Macs run the Python door. Python 3.11 or newer.

## Install

```bash
uv tool install manifold-ai
```

This installs the `manifold` command on its own, fetching Python 3.13 if your Mac has nothing new enough. `uv` is
`brew install uv`. With Python 3.11 or newer already installed, `pip install manifold-ai` or `pipx install
manifold-ai` do the same. A Mac's built-in `python3` is 3.9, which is too old.

## First manifold

```bash
manifold                         # the canvas, in your browser; the first time, it installs the core to run at login
manifold new desk --purpose "where the market stands" --section Market
```

`manifold` on its own always lands on the canvas, starting the core if it is not running. Seeing anything else means
something failed, and the line says what. `manifold -h` is the help.

Place nodes from the library, a thousand node types in a hundred domains. `manifold library` lists the domains,
`manifold library stocks` one domain's types, `manifold library weather` whatever matches a word; the canvas shows
them as a gallery.

```bash
manifold -m desk place stocks/quote Market symbol=^GSPC name="S&P 500"
manifold -m desk approve quote   # a type that reaches outside through a tool runs once you approve it
manifold -m desk ls              # what an agent reads: every card's headline values
manifold -m desk cat quote       # one card in full
```

A node that needs a key asks for it by name. `manifold key add` stores it in the macOS keychain, and it goes only
to the tool you approved it for.

## Agents

Any agent with a shell works a manifold through the same commands a person uses. One run of Claude Code or Codex
with Manifold as its tool:

```bash
manifold -m desk agent "say where the S&P stands and whether volatility is high" --can act
```

Agents that live in a manifold, with a standing task and a schedule: `manifold -m desk agents new …`. An agent runs
only on its own machine, on your own sign-in. No machine starts an agent on another.

An agent's learning outlives its run through the `memory` node (`manifold place agents/memory Knowledge`): one fact
per line, with where it came from and the day, written with `do remember`, revised or forgotten by id, read by the
next agent on any machine the section is shared with. It is a node like any other, so grants and feeds apply to it.

A fast, typed judgment — a probability, a pick, a grade — comes from a System One model through the `systemone` tool
and the `judge` node (`manifold place agents/judge Knowledge`). Set the tool up once on a machine: `manifold key add
TYPESAFE_API_KEY` for TypeSafe's jev, or `manifold tool set systemone provider=local url=…` for a model on this machine,
or `provider=custom` for any host that speaks the System One shape. Then any agent asks `do judge ask state=… question=…`,
and every judgment is logged on the card with what it cost.

## Working from Codex or Claude Code

Give the harness Manifold as a tool, not the raw command line:

```bash
codex mcp add manifold -- manifold mcp -m desk --can act,place,arrange     # one manifold
claude mcp add manifold -- manifold mcp -m all --can act,place,arrange     # any manifold here: the tool takes `manifold` with each command
```

Each session is one run with that grant: it shows on the Agents card as `codex · session`, every command it sends is in
the activity feed, and the tool refuses whatever the grant does not cover. Approving, keys, members and the canvas stay
yours, in your own terminal or in the browser. A shell inside a harness that runs `manifold` directly can read, and is
told to use the tool for the rest. When you ask the agent to show you the canvas, its `canvas` command opens it in your
browser on this machine; the agent gets no address.

## Talking to a manifold

A person can talk to a manifold from the canvas and have the voice work it. Three voices answer: xAI's or OpenAI's
realtime model with a key on the machine, or Codex itself on its own sign-in:

```bash
manifold key add XAI_API_KEY
manifold -m desk voice on can=act,place,agents            # provider=openai model=… voice=… choose who answers
manifold -m desk voice on provider=codex can=act,place    # Codex's voice: no key; Codex (CLI or the ChatGPT app) signed in here
```

Press **Talk** on the canvas. The voice is an agent like any other: a run with the grant you gave, every command in
the feed, the one `manifold` tool, and `agent` to start Claude or Codex on a longer task when `agents` is in the grant.
Approving, keys and members stay yours: the voice asks, you press. The browser does the microphone and speaker; the
key never leaves the core.

With `provider=codex` the core starts a `codex app-server` on this machine for the conversation. Codex negotiates the
call on your Codex sign-in and is the voice's hands: a thread with no shell and one tool, `manifold`, on the voice run's
socket, so it does exactly what the grant allows and every command is in the feed. The audio goes between your browser
and the model directly (WebRTC); the core passes the handshake, the transcripts and the tool calls. Codex runs here, so
this voice reaches only this machine's manifolds. Voices: juniper, maple, spruce, ember, vale, breeze, arbor, sol, cove.

## Reading the web

Agents have no browser and no network of their own: a link in a card is readable through a **Reader** card. An agent
(or you) places one — `place web/reader <section> url=https://…` — you approve the type once (it reaches the web), and
`cat` gives the page as plain markdown: title, text, links. `do <node> fetch url=…` reads another page into the same
card. The `web` tool behind it reads public pages only, never anything on your machine or network, and every page read
is in the feed. `library <words>` lets a run find a type in the node library instead of guessing its name.

## Other machines

A manifold runs on one machine. Any other machine, yours or a friend's, joins with a one-time invitation:

```bash
manifold -m desk share --role build       # on the machine the manifold lives on: prints an invitation
manifold join mf2.…                       # on the other machine
```

Roles: `read` (ls, cat), `act` (also press actions), `build` (also place, set, move and remove nodes). Approving,
inviting and keys never leave the machine the manifold runs on. A **private** section is invisible to everyone
you share with until you open it to one of them by name:

```bash
manifold -m desk private Account
manifold -m desk members allow "MacBook Air" Account
```

Your devices keep a copy of what they may see, so they can read the manifold while the machine it runs on is off.

## Where things are

| | |
|---|---|
| your manifolds, keys' names, feeds | `~/.manifold` (or `MANIFOLD_HOME`) |
| a manifold | a folder: `layout.json`, `nodes/<type>/` (`node.json`, `node.py`, `view.html`), `docs/` |
| the node library | shipped in the package; `MANIFOLD_LIBRARY` points elsewhere |
| the door | the process that carries connections between machines (Rust; `door/` in the source) |
| the canvas | `http://127.0.0.1:8730` |

The package contains code, the node library with synthetic sample data, and the door binary; nothing from the
machine it was built on. Everything you make lives in your home folder. A key goes to the macOS keychain, never to
a file. Nothing leaves your machine except what you grant to a machine you invited, through the door.

## Building a node

A node is three files. `node.json` says what it answers, its settings and the shape of its value. `node.py` has
`gather(m, s)`, which returns the value, and `act_<name>(m, s, …)` for each action. `view.html` draws the card.
`manifold bench <folder> --save --shot` runs one without a core. `library/GUIDE.md` is how library nodes are built.

## Development

```bash
git clone … && cd manifold && uv venv --python 3.13 && uv pip install -e ".[dev]"
(cd door && cargo build --release)          # the door; without it the Python door runs
.venv/bin/python -m pytest -q
```

`DECISIONS.md` holds every design decision with its reason and what would prove it wrong. `AUDIT.md` records what a
hostile machine was tried against and what remains unproven. Apache-2.0.
