adaptyv

Files (2)

• SKILL.md
• api-endpoints.md · references/

SKILL.md (first lines)

## ZeroWall execution contract

These host rules override upstream examples when they differ:

- Call the exact native tool name with its argument object; use the host tool list to confirm the current schema. Loading a Skill supplies instructions, not execution. Use `python` for the managed local interpreter, and discover `pwsh` on Windows or `bash` on Unix when shell work is needed.
- Use `python` or `r` for short interactive work. Use `run_in_context` plus `monitor_run` for training, GPU, Nextflow, batch, remote, or otherwise long-running work; do not extend the ordinary `shell` timeout.
- Resolve credentials only through **Settings > Credentials** and the approved execution-context environment. Never create, scan, or load project `.env` files and never print or persist secret values.
- Treat network calls, cloud jobs, experiment submissions, writes, deletion, and physical equipment actions as approval-gated. Default to read-only inspection, validation, or dry-run planning until the user explicitly requests execution.
- Use `zerowall-python-packages` for managed Python dependency changes: inspect, preview, obtain confirmation, apply, and verify. Do not run pip/uv/conda against the managed snapshot. Report missing external runtimes separately.
- Use `pathlib`, project-relative paths, and platform temporary directories. Gate Unix-only commands behind an explicit WSL/SSH execution context.
- Current companion capabilities take precedence over upstream names: `publication-figures`, `figure-style`, `paper-to-report`, `literature-review`, `citation-reviewer`, `probe-compute-environment`, `ppt-maker`, `generate_image`, and bundled MCP tools discovered with Host tool registry.

# Adaptyv Bio Foundry API

Adaptyv Bio is a cloud lab that turns protein sequences into experimental data. Users submit amino acid sequences via API or UI; Adaptyv's automated lab runs assays (binding, thermostability, expression, fluorescence) and delivers results in ~21 days.

**Official docs:** [docs.adaptyvbio.com/api-reference](https://docs.adaptyvbio.com/api-reference) · [llms.txt index](https://docs.adaptyvbio.com/llms.txt) · [OpenAPI spec](https://foundry-api-public.adaptyvbio.com/api/v1/openapi.json)

## Quick Start

**Base URL:** `https://foundry-api-public.adaptyvbio.com/api/v1`

**Authentication:** Bearer token in the `Authorization` header. Tokens are obtained from [foundry.adaptyvbio.com](https://foundry.adaptyvbio.com/) sidebar.

When writing code, read the API key only from the `ADAPTYV_API_KEY`
environment variable injected by ZeroWall Settings > Credentials. Never scan
the project for credential files or hardcode tokens.

The [official API docs](https://docs.adaptyvbio.com/api-reference/api-introduction) use `FOUNDRY_API_TOKEN` in curl examples; that is the same bearer token — prefer `ADAPTYV_API_KEY` in Python and new shell scripts for consistency with the SDK.

```bash
export ADAPTYV_API_KEY="abs0_..."
curl https://foundry-api-public.adaptyvbio.com/api/v1/targets?limit=3 \
  -H "Authorization: Bearer $ADAPTYV_API_KEY"
```

Every request except `GET /openapi.json` requires authentication. Store tokens
in ZeroWall Settings > Credentials and never commit them to source control.

## Python SDK

**Version note:** `adaptyv-sdk` **0.1.0** (beta) is not yet on PyPI — install from GitHub:

```bash
uv pip install "git+https://github.com/adaptyvbio/adaptyv-sdk.git"
```

In a project with `pyproject.toml`:

```bash
uv add "adaptyv-sdk @ git+https://github.com/adaptyvbio/adaptyv-sdk.git"
```

**Environment variables** (injected by the approved ZeroWall execution context):

```bash
ADAPTYV_API_KEY=your_api_key
ADAPTYV_API_URL=https://foundry-api-public.adaptyvbio.com/api/v1
ADAPTYV_ORGANIZATION_ID=your_org_id  # optional
```

The `@lab.experiment` decorator and `FoundryClient` both read `ADAPTYV_API_KEY` and `ADAPTYV_API_URL` from the environment when not passed explicitly.

### Decorator Pattern

```python
from adaptyv import lab

@lab.experiment(target="PD-L1", experiment_type="screening", method="bli")
def design_binders():
    return {"design_a": "MVKVGVNG...", "design_b": "MKVLVAG..."}

result = design_binders()
print(f"Experiment: {result.experiment_url}")
```

### Client Pattern

```python
import os
from adaptyv import FoundryClient

client = FoundryClient(
    api_key=os.environ["ADAPTYV_API_KEY"],
    base_url=os.environ.get(
        "ADAPTYV_API_URL",
        "https://foundry-api-public.adaptyvbio.com/api/v1",
    ),
)

# Browse targets
targets = client.targets.list(search="EGFR", selfservice_only=True)

# Estimate cost
estimate = client.experiments.cost_estimate({
    "experiment_spec": {
        "experiment_type": "screening",
        "method": "bli",
        "target_id": "target-uuid",
        "sequences": {"seq1": "EVQLVESGGGLVQ..."},
        "n_replicates": 3
    }
})

# Create and submit
exp = client.experiments.create({...})
client.experiments.submit(exp.experiment_id)

# Later: retrieve results
results = client.experiments.get_results(exp.experiment_id)
```

## Experiment Types

| Type | Method | Measures | Requires Target |
|---|---|---|---|
| `affinity` | `bli` or `spr` | KD, kon, koff kinetics | Yes |
| `screening` | `bli` or `spr` | Yes/no binding | Yes |
| `thermostability` | — | Melting temperature (Tm) | No |

From ccfwwm/zerowall-dsh-plugins, MIT.

More from ccfwwm/zerowall-dsh-plugins