livepeer · rickstaa · Aug 12, 2026 · Aug 12, 2026
diff --git a/README.md b/README.md
@@ -5,7 +5,7 @@ Example **apps that run on** the Livepeer **live runner** — [go-livepeer](http
 The point is to **swap the compute without changing your app — permissionlessly, no lock-in**. Your app stays a plain service with little or no Livepeer-specific code, so you're never tied to us. And the network is permissionless: anyone can run or extend it, no one gatekeeps what you deploy, and no single party can take your app down. Write the app once; **move the compute freely**.
 
 > [!NOTE]
-> Live runners ship in mainline go-livepeer since [v0.9.0](https://github.com/livepeer/go-livepeer/releases/tag/v0.9.0). The Python SDK is installed from its `main` branch until it is published to PyPI.
+> Live runners ship in mainline go-livepeer since [v0.9.0](https://github.com/livepeer/go-livepeer/releases/tag/v0.9.0), and the Python SDK is on PyPI as [`livepeer-gateway`](https://pypi.org/project/livepeer-gateway/).
 
 ## How it works
 
@@ -110,12 +110,12 @@ Each example is self-contained and its README has the run commands. Everything b
 
 ### Prerequisites
 
-- **Docker** for the end-to-end demos, so there is nothing to build. They currently run a mainline `livepeer/go-livepeer` master build rather than a release image: metered pricing needs the session-scoped payment URL added after v0.9.0 ([#4008](https://github.com/livepeer/go-livepeer/pull/4008)). They move back to a release tag once one carries it.
+- **Docker** for the end-to-end demos, so there is nothing to build. They run the `livepeer/go-livepeer:v0.9.1` release image.
 - **Python 3.12+** and [`uv`](https://docs.astral.sh/uv/) for the client.
-- The **`livepeer-gateway` SDK** from its `main` branch (not yet on PyPI):
+- The **[`livepeer-gateway` SDK](https://pypi.org/project/livepeer-gateway/)** (`uv run` installs it for you from each app's `pyproject.toml`):
 
   ```sh
-  pip install "git+https://github.com/livepeer/livepeer-python-gateway@main"
+  pip install "livepeer-gateway>=1.0.0"
   ```
 
 ### Shared components

diff --git a/api-proxy/README.md b/api-proxy/README.md
@@ -11,7 +11,7 @@ The live runner can also **pass calls through to an API that runs somewhere else
 | Pricing      | fixed (one price per call)                   |
 | Port         | 8989                                         |
 
-Prerequisites (Docker, `uv`, and the not-yet-released `livepeer-gateway` SDK — pinned in `pyproject.toml`) and the shared on-chain/payment setup live in the [repo README](../README.md). The demo upstream additionally needs a **Hugging Face API token** (`HF_TOKEN`, from [huggingface.co → settings → tokens](https://huggingface.co/settings/tokens)) with inference-provider credits.
+Prerequisites (Docker, `uv`, and the [`livepeer-gateway` SDK](https://pypi.org/project/livepeer-gateway/)) and the shared on-chain/payment setup live in the [repo README](../README.md). The demo upstream additionally needs a **Hugging Face API token** (`HF_TOKEN`, from [huggingface.co → settings → tokens](https://huggingface.co/settings/tokens)) with inference-provider credits.
 
 ## How it's wired
 

diff --git a/api-proxy/pyproject.toml b/api-proxy/pyproject.toml
@@ -5,9 +5,5 @@ description = "API proxy example app for the Livepeer network."
 requires-python = ">=3.12"
 dependencies = [
     "aiohttp",
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }
diff --git a/compose.onchain.yml b/compose.onchain.yml
@@ -14,7 +14,7 @@
 services:
   signer:
     # Master build, matching the orchestrator; see compose.orchestrator.yml.
-    image: livepeer/go-livepeer:sha-cc49228
+    image: livepeer/go-livepeer:v0.9.1
     container_name: example_apps_signer
     command:
       - -remoteSigner

diff --git a/compose.orchestrator.yml b/compose.orchestrator.yml
@@ -18,7 +18,7 @@
 
 services:
   orchestrator:
-    image: livepeer/go-livepeer:sha-cc49228
+    image: livepeer/go-livepeer:v0.9.1
     container_name: example_apps_orchestrator
     # Two distinct addresses:
     #   serviceAddr    advertised to external clients in discovery responses,

diff --git a/echo/Dockerfile b/echo/Dockerfile
@@ -4,14 +4,10 @@ FROM python:3.12-slim
 # Flush stdout/stderr immediately so output isn't block-buffered in `docker logs`.
 ENV PYTHONUNBUFFERED=1
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends git \
-    && rm -rf /var/lib/apt/lists/*
-
 # livepeer-gateway SDK isn't on PyPI yet; install from Git. av (PyAV) ships its
 # own ffmpeg; opencv-python-headless needs no system GUI libs.
 RUN pip install --no-cache-dir \
-    "livepeer-gateway @ git+https://github.com/livepeer/livepeer-python-gateway@main" \
+    "livepeer-gateway>=1.0.0" \
     av opencv-python-headless aiohttp
 
 WORKDIR /app

diff --git a/echo/README.md b/echo/README.md
@@ -11,7 +11,7 @@ A realtime video app on the Livepeer network: it receives a live video stream ov
 | Pricing      | hour (metered per second)            |
 | Port         | 8989                                 |
 
-Prerequisites (Docker, `uv`, the not-yet-released SDK) and the shared setup are in the [repo README](../README.md).
+Prerequisites (Docker, `uv`, the [SDK](https://pypi.org/project/livepeer-gateway/)) and the shared setup are in the [repo README](../README.md).
 
 ## How it's wired
 
@@ -115,12 +115,12 @@ A metered session pays **more than once**. The upfront payment that answers the
 
 ## Run without Docker
 
-Start an orchestrator built from go-livepeer `v0.9.0` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
+Start an orchestrator built from go-livepeer `v0.9.1` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
 
 ```sh
 ./livepeer -orchestrator -useLiveRunners -serviceAddr localhost:8935 -orchSecret abcdef -v 6
 uv run runner.py --orchestrator https://localhost:8935 --orchSecret abcdef
 uv run client.py --mode blur sample.mp4
 ```
 
-The paid path needs a newer orchestrator than the offchain one: metered sessions rely on the session-scoped payment URL added after `v0.9.0` ([#4008](https://github.com/livepeer/go-livepeer/pull/4008)), which is why the compose files pin a master build.
+Metered sessions rely on the session-scoped payment URL added in `v0.9.1` ([#4008](https://github.com/livepeer/go-livepeer/pull/4008)), which is the release the compose files pin.
diff --git a/echo/pyproject.toml b/echo/pyproject.toml
@@ -8,9 +8,5 @@ dependencies = [
     "opencv-python-headless",  # runner: gray/invert/blur transforms
     "numpy",            # runner: robot ring modulation
     "aiohttp",
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }
diff --git a/hello-world/Dockerfile b/hello-world/Dockerfile
@@ -4,13 +4,8 @@ FROM python:3.12-slim
 # Flush stdout/stderr immediately so output isn't block-buffered in `docker logs`.
 ENV PYTHONUNBUFFERED=1
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends git \
-    && rm -rf /var/lib/apt/lists/*
-
-# livepeer-gateway SDK isn't on PyPI yet; install from Git.
 RUN pip install --no-cache-dir \
-    "livepeer-gateway @ git+https://github.com/livepeer/livepeer-python-gateway@main"
+    "livepeer-gateway>=1.0.0"
 
 WORKDIR /app
 COPY runner.py client.py ./

diff --git a/hello-world/README.md b/hello-world/README.md
@@ -11,7 +11,7 @@ The smallest possible app on the Livepeer network: a synchronous request/respons
 | Pricing      | fixed (one price per call)           |
 | Port         | 8989                                 |
 
-Prerequisites (Docker, `uv`, and the not-yet-released `livepeer-gateway` SDK — pinned in `pyproject.toml`) and the shared on-chain/payment setup live in the [repo README](../README.md).
+Prerequisites (Docker, `uv`, and the [`livepeer-gateway` SDK](https://pypi.org/project/livepeer-gateway/)) and the shared on-chain/payment setup live in the [repo README](../README.md).
 
 ## How it's wired
 
@@ -47,7 +47,7 @@ The app registers with a price (`--price` from `.env`, in USD billed once per ca
 
 ## Run without Docker
 
-Start an orchestrator built from go-livepeer `v0.9.0` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
+Start an orchestrator built from go-livepeer `v0.9.1` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
 
 ```sh
 ./livepeer -orchestrator -useLiveRunners -serviceAddr localhost:8935 -orchSecret abcdef -v 6

diff --git a/hello-world/pyproject.toml b/hello-world/pyproject.toml
@@ -4,9 +4,5 @@ version = "0.1.0"
 description = "Hello-world example app for the Livepeer network."
 requires-python = ">=3.12"
 dependencies = [
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }
diff --git a/realtime-transcription/Dockerfile b/realtime-transcription/Dockerfile
@@ -4,17 +4,13 @@ FROM python:3.12-slim
 # Flush stdout/stderr immediately so output isn't block-buffered in `docker logs`.
 ENV PYTHONUNBUFFERED=1
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends git \
-    && rm -rf /var/lib/apt/lists/*
-
 # livepeer-gateway SDK isn't on PyPI yet; install from Git. CTranslate2 (under
 # faster-whisper) loads cuBLAS/cuDNN from the nvidia wheels, so no CUDA base image
 # is needed -- the host driver comes in via the compose `deploy` reservation.
 RUN pip install --no-cache-dir \
     faster-whisper numpy \
     nvidia-cublas-cu12 nvidia-cudnn-cu12 \
-    "livepeer-gateway @ git+https://github.com/livepeer/livepeer-python-gateway@main"
+    "livepeer-gateway>=1.0.0"
 
 ENV LD_LIBRARY_PATH=/usr/local/lib/python3.12/site-packages/nvidia/cublas/lib:/usr/local/lib/python3.12/site-packages/nvidia/cudnn/lib
 

diff --git a/realtime-transcription/README.md b/realtime-transcription/README.md
@@ -11,7 +11,7 @@ Realtime speech-to-text on the Livepeer network over a **WebSocket** — the cli
 | Transport    | WebSocket (`/transcribe`)                 |
 | Port         | 8989                                      |
 
-**Requires an NVIDIA GPU.** The model is fixed at `large-v3-turbo`: it swaps large-v3's 32-layer decoder for 4, so it runs far below realtime on a 3090 while staying near large-v3 quality. The device is pinned with it (`cuda`/`float16`) rather than exposed as a flag: on CPU the model loads but falls behind a live stream, which is the one thing this example is about. Prerequisites (Docker, `uv`, the not-yet-released SDK) and the shared on-chain/payment setup are in the [repo README](../README.md).
+**Requires an NVIDIA GPU.** The model is fixed at `large-v3-turbo`: it swaps large-v3's 32-layer decoder for 4, so it runs far below realtime on a 3090 while staying near large-v3 quality. The device is pinned with it (`cuda`/`float16`) rather than exposed as a flag: on CPU the model loads but falls behind a live stream, which is the one thing this example is about. Prerequisites (Docker, `uv`, the [SDK](https://pypi.org/project/livepeer-gateway/)) and the shared on-chain/payment setup are in the [repo README](../README.md).
 
 ## How it's wired
 
@@ -85,7 +85,7 @@ docker compose -f compose.yml -f compose.onchain.yml down
 
 ## Run without Docker
 
-Start an orchestrator built from go-livepeer `v0.9.0` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly (the app needs `faster-whisper` installed):
+Start an orchestrator built from go-livepeer `v0.9.1` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly (the app needs `faster-whisper` installed):
 
 ```sh
 ./livepeer -orchestrator -useLiveRunners -serviceAddr localhost:8935 -orchSecret abcdef -v 6

diff --git a/realtime-transcription/pyproject.toml b/realtime-transcription/pyproject.toml
@@ -7,9 +7,5 @@ dependencies = [
     "faster-whisper",   # runner: streaming Whisper ASR
     "numpy",            # runner: PCM buffers + energy VAD
     "aiohttp",
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }
diff --git a/tiles/Dockerfile b/tiles/Dockerfile
@@ -4,14 +4,9 @@ FROM python:3.12-slim
 # Flush stdout/stderr immediately so output isn't block-buffered in `docker logs`.
 ENV PYTHONUNBUFFERED=1
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends git \
-    && rm -rf /var/lib/apt/lists/*
-
-# livepeer-gateway SDK isn't on PyPI yet; install from Git.
 # opencv-python-headless needs no system GUI libs.
 RUN pip install --no-cache-dir \
-    "livepeer-gateway @ git+https://github.com/livepeer/livepeer-python-gateway@main" \
+    "livepeer-gateway>=1.0.0" \
     opencv-python-headless numpy aiohttp
 
 WORKDIR /app

diff --git a/tiles/README.md b/tiles/README.md
@@ -11,7 +11,7 @@ An image processor on the Livepeer network that shows what **capacity** does. It
 | Pricing      | fixed (one price per tile call)      |
 | Port         | 8989                                 |
 
-Prerequisites (Docker, `uv`, and the not-yet-released `livepeer-gateway` SDK — pinned in `pyproject.toml`) and the shared on-chain/payment setup live in the [repo README](../README.md).
+Prerequisites (Docker, `uv`, and the [`livepeer-gateway` SDK](https://pypi.org/project/livepeer-gateway/)) and the shared on-chain/payment setup live in the [repo README](../README.md).
 
 ## How it's wired
 
@@ -63,7 +63,7 @@ Each tile is one paid single-shot call — the orchestrator reserves a session f
 
 ## Run without Docker
 
-Start an orchestrator built from go-livepeer `v0.9.0` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
+Start an orchestrator built from go-livepeer `v0.9.1` or newer (see [Build from source](https://docs.livepeer.org/v1/orchestrators/guides/install-go-livepeer#build-from-source)), then the app and client directly:
 
 ```sh
 ./livepeer -orchestrator -useLiveRunners -serviceAddr localhost:8935 -orchSecret abcdef -v 6

diff --git a/tiles/pyproject.toml b/tiles/pyproject.toml
@@ -7,9 +7,5 @@ dependencies = [
     "opencv-python-headless",  # runner: stylize tiles; client: split/stitch
     "numpy",
     "aiohttp",
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }
diff --git a/vllm/README.md b/vllm/README.md
@@ -11,7 +11,7 @@ Runs an OpenAI-compatible LLM on the Livepeer network and consumes it with the *
 | Pricing      | hour (metered per second of the call)      |
 | Port         | 8000 (vLLM), 8080 (gateway)                |
 
-**Requires an NVIDIA GPU** for vLLM. The model (`Qwen/Qwen2.5-0.5B-Instruct`) is tiny so it fits a modest card; serving a different one means changing `compose.yml` and `runners.json` together. Prerequisites (Docker, `uv`, the not-yet-released SDK) and the shared on-chain/payment setup are in the [repo README](../README.md).
+**Requires an NVIDIA GPU** for vLLM. The model (`Qwen/Qwen2.5-0.5B-Instruct`) is tiny so it fits a modest card; serving a different one means changing `compose.yml` and `runners.json` together. Prerequisites (Docker, `uv`, the [SDK](https://pypi.org/project/livepeer-gateway/)) and the shared on-chain/payment setup are in the [repo README](../README.md).
 
 ## How it's wired
 

diff --git a/vllm/pyproject.toml b/vllm/pyproject.toml
@@ -5,10 +5,6 @@ description = "vLLM (OpenAI-compatible LLM) example app for the Livepeer network
 requires-python = ">=3.12"
 dependencies = [
     "aiohttp",          # for gateway.py (the OpenAI -> Livepeer gateway)
-    "livepeer-gateway",
+    "livepeer-gateway>=1.0.0",
     "openai",           # for client.py (stock OpenAI library)
 ]
-
-# livepeer-gateway is not on PyPI yet; pull it from the branch.
-[tool.uv.sources]
-livepeer-gateway = { git = "https://github.com/livepeer/livepeer-python-gateway", branch = "main" }