agi-diy

Python client for api.agi.diy. Lease a VLA policy, run it over the LeRobot remote-inference protocol (zenoh). One call = one token per action in the chunk.

pip install agi-diy "lerobot[remote] @ git+https://github.com/huggingface/lerobot"
agi login
agi run act/so101 --probe

import agi

with agi.Policy("act/so101") as session:
    actions = session.predict(
        {"observation.state": state, "observation.images.top": top, "observation.images.wrist": wrist},
        task="pick up the cube",
    )  # np.ndarray [n_action_steps, dof]

The key comes from AGI_API_KEY or ~/.agi/credentials (AGI_API_KEY=agi_sk_live_…).

Surface

agi.Policy("act/so101")          # POST /v1/sessions → lease; raises agi.NoSlots / agi.InsufficientCredits / agi.AuthError
session.endpoint                 # "tcp/bore.pub:35706"  (verbatim from the runner; session.encoding = "jpeg")
session.deployment               # "d_…"
session.url                      # "zenoh://bore.pub:35706/d_…"  → strands_robots.Policy(session.url)
session.connect()                # admitted lerobot.remote_inference.RemoteClient
session.predict(obs, task="…")   # one chunk, np.ndarray
session.policy()                 # strands-robots policy: arm.run(session.policy(), seconds=30)
session.rollout_args()           # flags for lerobot-rollout
session.close()                  # DELETE /v1/sessions/:id (also a context manager)
agi.models(); agi.me(); agi.usage(); agi.sessions(); agi.health()

CLI: agi login · agi models · agi session act/so101 · agi run act/so101 --probe · agi rollout act/so101 -- --robot.type=so101_follower … · agi usage.

connect(), predict() and rollout need LeRobot's remote inference, which is on lerobot main only today (pip install "lerobot[remote] @ git+https://github.com/huggingface/lerobot"). The REST part has no dependencies.

Errors subclass agi.Error with .error, .status, .retry_after_s.