Metadata-Version: 2.4
Name: aclade
Version: 0.1.0
Summary: Official Python SDK for Aclade — autonomous AI experts that do real work. `import aclade`, delegate a task, read the report.
Author-email: Aclade <support@aclade.com>
License: Proprietary (UNLICENSED) — distributed exclusively for users of the Aclade platform
Project-URL: Homepage, https://aclade.com
Project-URL: npm (local connector), https://www.npmjs.com/package/aclade
Keywords: aclade,ai,agent,autonomous,experts,sdk,api
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# aclade

**The official Python SDK for [Aclade](https://aclade.com)** — autonomous AI experts that do real work.

`import aclade` and you can list your AI team, delegate tasks to individual experts, and read their reports — from any Python code, notebook, or pipeline.

## Install

```bash
pip install aclade
```

Python 3.8+, zero third-party dependencies (standard library only).

## Get a token

1. Sign in at [aclade.com](https://aclade.com)
2. **Settings → Local Agent → Get connection token** (the same token the local connector uses)
3. `export ACLADE_TOKEN=<TOKEN>`

Tokens are signed 12-hour sessions bound to your workspace. If you already connected a machine with the [npm connector](https://www.npmjs.com/package/aclade), the SDK picks the token up from `~/.aclade-agent.json` automatically — `import aclade` just works.

## Quickstart

```python
import aclade

team = aclade.Aclade()                    # token from $ACLADE_TOKEN or ~/.aclade-agent.json
team = aclade.Aclade(token="<TOKEN>")     # …or explicitly

# Who's on the roster?
for e in team.experts():
    print(e["name"], "—", e["title"])

# Delegate a task and wait for the report
result = team.delegate("Priya", "Summarize our top 3 customer complaints and draft replies")
print(result["status"])                   # completed | needs-input | needs-approval
print(result["run"]["report"])
```

## The three outcomes

| `result["status"]` | Meaning | What to do |
|---|---|---|
| `completed` | The expert finished the work | Read `result["run"]["report"]` |
| `needs-input` | The expert asked clarifying questions | Re-call with `answers={"<question>": "<answer>"}` |
| `needs-approval` | A high-risk step awaits a human | Approve in the portal (email link goes to your admin) |

## CLI

```bash
aclade experts                # roster
aclade run "Priya" "task"     # delegate + print the report
aclade tasks                  # pending tasks by expert
aclade agent                  # local-agent fleet (connector installs)
aclade whoami                 # identity carried by the token
```

## Where does the AI run?

On aclade.com — not on your machine. This SDK is the official client: it holds your token, sends work, and returns results. The reasoning harness, tools, and per-second metering are Aclade platform services — the same way `import stripe` never contains Stripe's rails.

Optionally, your machine can also run the [zero-trust local connector](https://www.npmjs.com/package/aclade) (`npm i -g aclade`), which lets your experts act on your own filesystem, shell, and browser — outbound HTTPS polling only, no inbound ports.

## Security notes

- The token is a credential: anyone holding it can delegate work as your workspace (billed to your account). Keep it in an env var or secrets manager.
- This package ships no AI logic, model weights, or telemetry.
- License: proprietary (`UNLICENSED`), for users of the Aclade platform.
