openenv 0.2.0__tar.gz → 0.2.2__tar.gz

{openenv-0.2.0 → openenv-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openenv
-Version: 0.2.0
+Version: 0.2.2
 Summary: A unified framework for reinforcement learning environments
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -17,6 +17,9 @@ Requires-Dist: openai>=2.7.2
 Requires-Dist: tomli>=2.3.0
 Requires-Dist: tomli-w>=1.2.0
 Requires-Dist: websockets>=15.0.1
+Requires-Dist: fastmcp>=3.0.0
+Requires-Dist: gradio>=4.0.0
+Requires-Dist: httpx>=0.28.1
 Provides-Extra: core
 Requires-Dist: fastapi>=0.104.0; extra == "core"
 Requires-Dist: pydantic>=2.0.0; extra == "core"
@@ -31,9 +34,28 @@ Requires-Dist: huggingface_hub>=0.20.0; extra == "cli"
 Requires-Dist: openai>=2.7.2; extra == "cli"
 Requires-Dist: tomli>=2.3.0; extra == "cli"
 Requires-Dist: tomli-w>=1.2.0; extra == "cli"
+Provides-Extra: docs
+Requires-Dist: sphinx==7.2.6; extra == "docs"
+Requires-Dist: pytorch-sphinx-theme2; extra == "docs"
+Requires-Dist: sphinxcontrib.katex==0.9.10; extra == "docs"
+Requires-Dist: docutils<0.21,>=0.18.1; extra == "docs"
+Requires-Dist: sphinx-design==0.6.1; extra == "docs"
+Requires-Dist: sphinxcontrib-mermaid==1.0.0; extra == "docs"
+Requires-Dist: myst-parser; extra == "docs"
+Requires-Dist: sphinxext-opengraph; extra == "docs"
+Requires-Dist: sphinx-sitemap==2.7.1; extra == "docs"
+Requires-Dist: sphinx-gallery>=0.14.0; extra == "docs"
+Requires-Dist: matplotlib; extra == "docs"
+Requires-Dist: nest-asyncio; extra == "docs"
+Requires-Dist: smolagents; extra == "docs"
 Provides-Extra: all
 Requires-Dist: openenv[core]; extra == "all"
 Requires-Dist: openenv[cli]; extra == "all"
+Provides-Extra: daytona
+Requires-Dist: daytona>=0.136.0; extra == "daytona"
+Requires-Dist: pyyaml>=6.0; extra == "daytona"
+Provides-Extra: inspect
+Requires-Dist: inspect-ai>=0.3.0; extra == "inspect"
 Dynamic: license-file
 
 # <img width="35" height="35" alt="image" src="https://github.com/user-attachments/assets/2700a971-e5d6-4036-b03f-2f89c9791609" /> OpenEnv: Agentic Execution Environments
@@ -49,10 +71,61 @@ An e2e framework for creating, deploying and using isolated execution environmen
 
 **🚀 Featured Example:** Train LLMs to play BlackJack using [torchforge](https://github.com/meta-pytorch/torchforge) (PyTorch's agentic RL framework): [`examples/grpo_blackjack/`](examples/grpo_blackjack/)
 
+**🔥 Zero to Hero Tutorial:** End to end tutorial from our [GPU Mode](tutorial/README.md) lecture and other hackathons.
+
+## Quick Start
+
+Install the OpenEnv core package:
+
+```bash
+pip install openenv
+```
+
+Install an environment client (e.g., Echo):
+
+```bash
+pip install git+https://huggingface.co/spaces/openenv/echo_env
+```
+
+Then use the environment:
+
+```python
+import asyncio
+from echo_env import EchoAction, EchoEnv
+
+async def main():
+    # Connect to a running Space (async context manager)
+    async with EchoEnv(base_url="https://openenv-echo-env.hf.space") as client:
+        # Reset the environment
+        result = await client.reset()
+        print(result.observation.echoed_message)  # "Echo environment ready!"
+
+        # Send messages
+        result = await client.step(EchoAction(message="Hello, World!"))
+        print(result.observation.echoed_message)  # "Hello, World!"
+        print(result.reward)  # 1.3 (based on message length)
+
+asyncio.run(main())
+```
+
+**Synchronous usage** is also supported via the `.sync()` wrapper:
+
+```python
+from echo_env import EchoAction, EchoEnv
+
+# Use .sync() for synchronous context manager
+with EchoEnv(base_url="https://openenv-echo-env.hf.space").sync() as client:
+    result = client.reset()
+    result = client.step(EchoAction(message="Hello, World!"))
+    print(result.observation.echoed_message)
+```
+
+For a detailed quick start, check out the [docs page](https://meta-pytorch.org/OpenEnv/quickstart/).
+
 ## OpenEnv on partner platforms:
 
 - [Lightning AI Studio](https://lightning.ai/environments?section=featured)
-- [TRL example](https://huggingface.co/docs/trl/main/en/openenv)
+- [TRL example](https://huggingface.co/docs/trl/openenv)
 - [Unsloth Google Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/OpenEnv_gpt_oss_(20B)_Reinforcement_Learning_2048_Game.ipynb)
 - [ART example](https://art.openpipe.ai/integrations/openenv-integration)
 - [Oumi example](https://github.com/oumi-ai/oumi/blob/main/notebooks/Oumi%20-%20OpenEnv%20GRPO%20with%20trl.ipynb)
@@ -77,6 +150,10 @@ The OpenEnv CLI (`openenv`) provides commands to initialize new environments and
 Below is a list of active and historical RFCs for OpenEnv. RFCs are proposals for major changes or features. Please review and contribute!
 
 - [RFC 001: Baseline API and Interface Specifications](https://github.com/meta-pytorch/OpenEnv/pull/26)
+- [RFC 002: Discoverability of environment tools by agents](https://github.com/meta-pytorch/OpenEnv/pull/32)
+- [RFC 003: Add MCP (Model Context Protocol) support](https://github.com/meta-pytorch/OpenEnv/pull/224)
+- [RFC 004: Add delayed rewards support for trajectory-based scoring](https://github.com/meta-pytorch/OpenEnv/pull/337)
+- [RFC 005: Agentic Harness Integration](https://github.com/meta-pytorch/OpenEnv/pull/387)
 
 ## Architecture
 
@@ -87,10 +164,10 @@ Below is a list of active and historical RFCs for OpenEnv. RFCs are proposals fo
 │                    Client Application                   │
 │  ┌────────────────┐              ┌──────────────────┐   │
 │  │  EchoEnv       │              │  CodingEnv       │   │
-│  │ (HTTPEnvClient)│              │  (HTTPEnvClient) │   │
+│  │  (EnvClient)   │              │   (EnvClient)    │   │
 │  └────────┬───────┘              └────────┬─────────┘   │
 └───────────┼───────────────────────────────┼─────────────┘
-            │ HTTP                          │ HTTP
+            │ WebSocket                     │ WebSocket
             │ (reset, step, state)          │
 ┌───────────▼───────────────────────────────▼─────────────┐
 │              Docker Containers (Isolated)               │
@@ -137,9 +214,11 @@ Base class for implementing environment logic:
 - **`step(action)`**: Execute an `Action`, returns resulting `Observation`
 - **`state()`**: Access episode metadata (`State` with episode_id, step_count, etc.)
 
-#### 3. HTTPEnvClient (Client-Side)
-Base class for HTTP communication:
-- Handles HTTP requests to environment server
+#### 3. EnvClient (Client-Side)
+Base class for environment communication:
+- **Async by default**: Use `async with` and `await` for all operations
+- **Sync wrapper**: Call `.sync()` to get a `SyncEnvClient` for synchronous usage
+- Handles WebSocket connections to environment server
 - Contains a utility to spin up a docker container locally for the corresponding environment
 - Type-safe action/observation parsing
 
@@ -172,7 +251,7 @@ my_env/
 ├── .dockerignore        # Docker build exclusions
 ├── __init__.py           # Export YourAction, YourObservation, YourEnv
 ├── models.py             # Define Action, Observation, State dataclasses
-├── client.py             # Implement YourEnv(HTTPEnvClient)
+├── client.py             # Implement YourEnv(EnvClient)
 ├── README.md             # Document your environment
 ├── openenv.yaml          # Environment manifest
 ├── pyproject.toml        # Dependencies and package configuration
@@ -219,10 +298,23 @@ See [`envs/README.md`](envs/README.md) for a complete guide on building environm
 ### For Environment Users
 
 To use an environment:
-1. Import from `envs.your_env`: `from envs.echo_env import EchoAction, EchoEnv`
-2. Create client: `client = EchoEnv.from_docker_image("echo-env:latest")`
-3. Interact: `client.reset()`, `client.step(action)`, `client.state()`
-4. Cleanup: `client.close()`
+1. Install the client: `pip install git+https://huggingface.co/spaces/openenv/echo-env`
+2. Import: `from echo_env import EchoAction, EchoEnv`
+3. Use async (recommended) or sync API:
+
+**Async (recommended):**
+```python
+async with EchoEnv(base_url="...") as client:
+    result = await client.reset()
+    result = await client.step(action)
+```
+
+**Sync (via `.sync()` wrapper):**
+```python
+with EchoEnv(base_url="...").sync() as client:
+    result = client.reset()
+    result = client.step(action)
+```
 
 See example scripts in `examples/` directory.
 
@@ -253,37 +345,56 @@ For detailed options: `openenv init --help` and `openenv push --help`.
 3. **Container Isolation**: Each environment runs in its own container
 4. **Simple APIs**: Minimal, intuitive interfaces
 
-## Quick Start
+## Development
 
-### Using the Echo Environment(Example)
+### Installation
 
-```python
-from envs.echo_env import EchoAction, EchoEnv
+```bash
+# Clone the repository
+git clone https://github.com/meta-pytorch/OpenEnv.git
+cd OpenEnv
+
+# Install core package in editable mode
+pip install -e .
+# Or using uv (faster)
+uv pip install -e .
+```
+
+### Running Tests
 
-# Automatically start container and connect
-client = EchoEnv.from_docker_image("echo-env:latest")
+OpenEnv uses a modular dependency structure: the core package is minimal, and each environment has its own dependencies. This means some tests require environment-specific packages.
 
-# Reset the environment
-result = client.reset()
-print(result.observation.echoed_message)  # "Echo environment ready!"
+```bash
+# Install pytest (required for running tests)
+uv pip install pytest
 
-# Send messages
-result = client.step(EchoAction(message="Hello, World!"))
-print(result.observation.echoed_message)  # "Hello, World!"
-print(result.reward)  # 1.3 (based on message length)
+# Run all tests (skips tests requiring uninstalled dependencies)
+PYTHONPATH=src:envs uv run pytest tests/ -v --tb=short
 
-# Cleanup
-client.close()  # Stops and removes container
+# Run a specific test file
+PYTHONPATH=src:envs uv run pytest tests/envs/test_echo_environment.py -v
 ```
 
+**To run environment-specific tests**, install that environment's dependencies:
+
+```bash
+# Example: Install coding_env with dev dependencies (includes smolagents + pytest)
+uv pip install -e "envs/coding_env[dev]"
+
+# Then run coding_env tests
+PYTHONPATH=src:envs uv run pytest tests/envs/test_python_codeact_rewards.py -v
+```
+
+Tests will be automatically skipped if their required dependencies aren't installed.
+
 ## Requirements
 
-- Python 3.11+
+- Python 3.10+
 - Docker Desktop or Docker Engine
 - FastAPI >= 0.104.0
 - Uvicorn >= 0.24.0
 - Requests >= 2.25.0
-- smolagents (for coding environment)
+- Environment-specific dependencies (e.g., smolagents for coding_env)
 
 ## Supported RL Tools
 The goal of this project is to support a broad set of open and closed tools to help standardize the agentic RL community. If you have a project that supports OpenEnv environments, please put up a PR to add your tool name along with a link to your documentation.
@@ -292,7 +403,7 @@ The goal of this project is to support a broad set of open and closed tools to h
 See GRPO BlackJack training example: [`examples/grpo_blackjack/`](examples/grpo_blackjack/)
 
 ### TRL
-See the [TRL example](https://huggingface.co/docs/trl/main/en/openenv) on how to integrate OpenEnv environments with GRPO training.
+See the [TRL example](https://huggingface.co/docs/trl/openenv) on how to integrate OpenEnv environments with GRPO training.
 
 ### Unsloth
 See the 2048 game example based on gpt-oss: [Colab notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/OpenEnv_gpt_oss_(20B)_Reinforcement_Learning_2048_Game.ipynb)
@@ -308,27 +419,20 @@ See the [Oumi example](https://github.com/oumi-ai/oumi/blob/main/notebooks/Oumi%
 
 ## Example Environments
 
-### Echo Environment
-A simple environment that echoes back messages with metadata. Perfect for:
-- Testing the HTTP server infrastructure
-- Learning the framework basics
-- Verifying container deployment
-
-See: [`envs/echo_env/README.md`](envs/echo_env/README.md)
-
-### Coding Environment
-Executes arbitrary Python code in a sandboxed environment. Features:
-- Safe code execution using smolagents
-- Capture stdout, stderr, and exit codes
-- Persistent execution context within episodes
-- Error handling with detailed messages
+| Environment | Description |
+|---|---|
+| [Echo Environment](envs/echo_env/README.md) | Echoes back messages with metadata. Ideal for testing HTTP server infrastructure, learning framework basics, and verifying container deployment. |
+| [Coding Environment](envs/coding_env/README.md) | Sandboxed Python code execution via smolagents. Captures stdout/stderr/exit codes, supports persistent episode context, and provides detailed error handling. |
+| [Chess Environment](envs/chess_env/README.md) | Chess RL environment with configurable opponents and full rules support. |
+| [Atari Environment](envs/atari_env/README.md) | Classic Arcade Learning Environment tasks for RL benchmarking. |
+| [FinRL Environment](envs/finrl_env/README.md) | Financial market simulations for algorithmic trading experiments. |
 
-See: [`envs/coding_env/README.md`](envs/coding_env/README.md)
+> Browse the full catalog of community environments at [meta-pytorch.org/OpenEnv/environments](https://meta-pytorch.org/OpenEnv/environments/).
 
 ## Community Support & Acknowledgments
 This is an open and community-centric project. If you would like to add your name here, please put up a pull request and tag @jspisak for review. Ty!!
 
-Supporters include: Meta-PyTorch, Hugging Face, [Patronus AI](https://patronus.ai), [Surge AI](https://surgehq.ai), [LastMile AI](https://www.lastmileai.dev), Unsloth AI, Reflection AI, vLLM, SkyRL (UC-Berkeley), LightningAI, Axolotl AI, Stanford Scaling Intelligence Lab, Mithril, [OpenMined](https://openmined.org/), [Fleet AI](https://fleetai.com), [Halluminate](https://halluminate.ai/), [Turing](https://www.turing.com/) ..
+Supporters include: Meta-PyTorch, Hugging Face, [Scaler AI Labs](https://scalerailabs.com), [Patronus AI](https://patronus.ai), [Surge AI](https://surgehq.ai), [LastMile AI](https://www.lastmileai.dev), Unsloth AI, Reflection AI, vLLM, SkyRL (UC-Berkeley), LightningAI, Axolotl AI, Stanford Scaling Intelligence Lab, Mithril, [OpenMined](https://openmined.org/), [Fleet AI](https://fleetai.com), [Halluminate](https://halluminate.ai/), [Turing](https://www.turing.com/), [Scale AI](https://scale.com/) ..
 
 And we'd also like to acknowledge the team at Farama Foundation as the OpenEnv API was heavily inspired by the work you all have done on Gymnasium. Cheers!
 

openenv-0.2.0/src/openenv.egg-info/PKG-INFO → openenv-0.2.2/README.md

@@ -1,41 +1,3 @@
-Metadata-Version: 2.4
-Name: openenv
-Version: 0.2.0
-Summary: A unified framework for reinforcement learning environments
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: fastapi>=0.104.0
-Requires-Dist: pydantic>=2.0.0
-Requires-Dist: uvicorn>=0.24.0
-Requires-Dist: requests>=2.25.0
-Requires-Dist: typer>=0.9.0
-Requires-Dist: rich>=13.0.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: huggingface_hub>=0.20.0
-Requires-Dist: openai>=2.7.2
-Requires-Dist: tomli>=2.3.0
-Requires-Dist: tomli-w>=1.2.0
-Requires-Dist: websockets>=15.0.1
-Provides-Extra: core
-Requires-Dist: fastapi>=0.104.0; extra == "core"
-Requires-Dist: pydantic>=2.0.0; extra == "core"
-Requires-Dist: uvicorn>=0.24.0; extra == "core"
-Requires-Dist: requests>=2.25.0; extra == "core"
-Requires-Dist: websockets>=15.0.1; extra == "core"
-Provides-Extra: cli
-Requires-Dist: typer>=0.9.0; extra == "cli"
-Requires-Dist: rich>=13.0.0; extra == "cli"
-Requires-Dist: pyyaml>=6.0; extra == "cli"
-Requires-Dist: huggingface_hub>=0.20.0; extra == "cli"
-Requires-Dist: openai>=2.7.2; extra == "cli"
-Requires-Dist: tomli>=2.3.0; extra == "cli"
-Requires-Dist: tomli-w>=1.2.0; extra == "cli"
-Provides-Extra: all
-Requires-Dist: openenv[core]; extra == "all"
-Requires-Dist: openenv[cli]; extra == "all"
-Dynamic: license-file
-
 # <img width="35" height="35" alt="image" src="https://github.com/user-attachments/assets/2700a971-e5d6-4036-b03f-2f89c9791609" /> OpenEnv: Agentic Execution Environments
 
 An e2e framework for creating, deploying and using isolated execution environments for agentic RL training, built using Gymnasium style simple APIs.
@@ -49,10 +11,61 @@ An e2e framework for creating, deploying and using isolated execution environmen
 
 **🚀 Featured Example:** Train LLMs to play BlackJack using [torchforge](https://github.com/meta-pytorch/torchforge) (PyTorch's agentic RL framework): [`examples/grpo_blackjack/`](examples/grpo_blackjack/)
 
+**🔥 Zero to Hero Tutorial:** End to end tutorial from our [GPU Mode](tutorial/README.md) lecture and other hackathons.
+
+## Quick Start
+
+Install the OpenEnv core package:
+
+```bash
+pip install openenv
+```
+
+Install an environment client (e.g., Echo):
+
+```bash
+pip install git+https://huggingface.co/spaces/openenv/echo_env
+```
+
+Then use the environment:
+
+```python
+import asyncio
+from echo_env import EchoAction, EchoEnv
+
+async def main():
+    # Connect to a running Space (async context manager)
+    async with EchoEnv(base_url="https://openenv-echo-env.hf.space") as client:
+        # Reset the environment
+        result = await client.reset()
+        print(result.observation.echoed_message)  # "Echo environment ready!"
+
+        # Send messages
+        result = await client.step(EchoAction(message="Hello, World!"))
+        print(result.observation.echoed_message)  # "Hello, World!"
+        print(result.reward)  # 1.3 (based on message length)
+
+asyncio.run(main())
+```
+
+**Synchronous usage** is also supported via the `.sync()` wrapper:
+
+```python
+from echo_env import EchoAction, EchoEnv
+
+# Use .sync() for synchronous context manager
+with EchoEnv(base_url="https://openenv-echo-env.hf.space").sync() as client:
+    result = client.reset()
+    result = client.step(EchoAction(message="Hello, World!"))
+    print(result.observation.echoed_message)
+```
+
+For a detailed quick start, check out the [docs page](https://meta-pytorch.org/OpenEnv/quickstart/).
+
 ## OpenEnv on partner platforms:
 
 - [Lightning AI Studio](https://lightning.ai/environments?section=featured)
-- [TRL example](https://huggingface.co/docs/trl/main/en/openenv)
+- [TRL example](https://huggingface.co/docs/trl/openenv)
 - [Unsloth Google Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/OpenEnv_gpt_oss_(20B)_Reinforcement_Learning_2048_Game.ipynb)
 - [ART example](https://art.openpipe.ai/integrations/openenv-integration)
 - [Oumi example](https://github.com/oumi-ai/oumi/blob/main/notebooks/Oumi%20-%20OpenEnv%20GRPO%20with%20trl.ipynb)
@@ -77,6 +90,10 @@ The OpenEnv CLI (`openenv`) provides commands to initialize new environments and
 Below is a list of active and historical RFCs for OpenEnv. RFCs are proposals for major changes or features. Please review and contribute!
 
 - [RFC 001: Baseline API and Interface Specifications](https://github.com/meta-pytorch/OpenEnv/pull/26)
+- [RFC 002: Discoverability of environment tools by agents](https://github.com/meta-pytorch/OpenEnv/pull/32)
+- [RFC 003: Add MCP (Model Context Protocol) support](https://github.com/meta-pytorch/OpenEnv/pull/224)
+- [RFC 004: Add delayed rewards support for trajectory-based scoring](https://github.com/meta-pytorch/OpenEnv/pull/337)
+- [RFC 005: Agentic Harness Integration](https://github.com/meta-pytorch/OpenEnv/pull/387)
 
 ## Architecture
 
@@ -87,10 +104,10 @@ Below is a list of active and historical RFCs for OpenEnv. RFCs are proposals fo
 │                    Client Application                   │
 │  ┌────────────────┐              ┌──────────────────┐   │
 │  │  EchoEnv       │              │  CodingEnv       │   │
-│  │ (HTTPEnvClient)│              │  (HTTPEnvClient) │   │
+│  │  (EnvClient)   │              │   (EnvClient)    │   │
 │  └────────┬───────┘              └────────┬─────────┘   │
 └───────────┼───────────────────────────────┼─────────────┘
-            │ HTTP                          │ HTTP
+            │ WebSocket                     │ WebSocket
             │ (reset, step, state)          │
 ┌───────────▼───────────────────────────────▼─────────────┐
 │              Docker Containers (Isolated)               │
@@ -137,9 +154,11 @@ Base class for implementing environment logic:
 - **`step(action)`**: Execute an `Action`, returns resulting `Observation`
 - **`state()`**: Access episode metadata (`State` with episode_id, step_count, etc.)
 
-#### 3. HTTPEnvClient (Client-Side)
-Base class for HTTP communication:
-- Handles HTTP requests to environment server
+#### 3. EnvClient (Client-Side)
+Base class for environment communication:
+- **Async by default**: Use `async with` and `await` for all operations
+- **Sync wrapper**: Call `.sync()` to get a `SyncEnvClient` for synchronous usage
+- Handles WebSocket connections to environment server
 - Contains a utility to spin up a docker container locally for the corresponding environment
 - Type-safe action/observation parsing
 
@@ -172,7 +191,7 @@ my_env/
 ├── .dockerignore        # Docker build exclusions
 ├── __init__.py           # Export YourAction, YourObservation, YourEnv
 ├── models.py             # Define Action, Observation, State dataclasses
-├── client.py             # Implement YourEnv(HTTPEnvClient)
+├── client.py             # Implement YourEnv(EnvClient)
 ├── README.md             # Document your environment
 ├── openenv.yaml          # Environment manifest
 ├── pyproject.toml        # Dependencies and package configuration
@@ -219,10 +238,23 @@ See [`envs/README.md`](envs/README.md) for a complete guide on building environm
 ### For Environment Users
 
 To use an environment:
-1. Import from `envs.your_env`: `from envs.echo_env import EchoAction, EchoEnv`
-2. Create client: `client = EchoEnv.from_docker_image("echo-env:latest")`
-3. Interact: `client.reset()`, `client.step(action)`, `client.state()`
-4. Cleanup: `client.close()`
+1. Install the client: `pip install git+https://huggingface.co/spaces/openenv/echo-env`
+2. Import: `from echo_env import EchoAction, EchoEnv`
+3. Use async (recommended) or sync API:
+
+**Async (recommended):**
+```python
+async with EchoEnv(base_url="...") as client:
+    result = await client.reset()
+    result = await client.step(action)
+```
+
+**Sync (via `.sync()` wrapper):**
+```python
+with EchoEnv(base_url="...").sync() as client:
+    result = client.reset()
+    result = client.step(action)
+```
 
 See example scripts in `examples/` directory.
 
@@ -253,37 +285,56 @@ For detailed options: `openenv init --help` and `openenv push --help`.
 3. **Container Isolation**: Each environment runs in its own container
 4. **Simple APIs**: Minimal, intuitive interfaces
 
-## Quick Start
+## Development
 
-### Using the Echo Environment(Example)
+### Installation
 
-```python
-from envs.echo_env import EchoAction, EchoEnv
+```bash
+# Clone the repository
+git clone https://github.com/meta-pytorch/OpenEnv.git
+cd OpenEnv
 
-# Automatically start container and connect
-client = EchoEnv.from_docker_image("echo-env:latest")
+# Install core package in editable mode
+pip install -e .
+# Or using uv (faster)
+uv pip install -e .
+```
 
-# Reset the environment
-result = client.reset()
-print(result.observation.echoed_message)  # "Echo environment ready!"
+### Running Tests
 
-# Send messages
-result = client.step(EchoAction(message="Hello, World!"))
-print(result.observation.echoed_message)  # "Hello, World!"
-print(result.reward)  # 1.3 (based on message length)
+OpenEnv uses a modular dependency structure: the core package is minimal, and each environment has its own dependencies. This means some tests require environment-specific packages.
 
-# Cleanup
-client.close()  # Stops and removes container
+```bash
+# Install pytest (required for running tests)
+uv pip install pytest
+
+# Run all tests (skips tests requiring uninstalled dependencies)
+PYTHONPATH=src:envs uv run pytest tests/ -v --tb=short
+
+# Run a specific test file
+PYTHONPATH=src:envs uv run pytest tests/envs/test_echo_environment.py -v
 ```
 
+**To run environment-specific tests**, install that environment's dependencies:
+
+```bash
+# Example: Install coding_env with dev dependencies (includes smolagents + pytest)
+uv pip install -e "envs/coding_env[dev]"
+
+# Then run coding_env tests
+PYTHONPATH=src:envs uv run pytest tests/envs/test_python_codeact_rewards.py -v
+```
+
+Tests will be automatically skipped if their required dependencies aren't installed.
+
 ## Requirements
 
-- Python 3.11+
+- Python 3.10+
 - Docker Desktop or Docker Engine
 - FastAPI >= 0.104.0
 - Uvicorn >= 0.24.0
 - Requests >= 2.25.0
-- smolagents (for coding environment)
+- Environment-specific dependencies (e.g., smolagents for coding_env)
 
 ## Supported RL Tools
 The goal of this project is to support a broad set of open and closed tools to help standardize the agentic RL community. If you have a project that supports OpenEnv environments, please put up a PR to add your tool name along with a link to your documentation.
@@ -292,7 +343,7 @@ The goal of this project is to support a broad set of open and closed tools to h
 See GRPO BlackJack training example: [`examples/grpo_blackjack/`](examples/grpo_blackjack/)
 
 ### TRL
-See the [TRL example](https://huggingface.co/docs/trl/main/en/openenv) on how to integrate OpenEnv environments with GRPO training.
+See the [TRL example](https://huggingface.co/docs/trl/openenv) on how to integrate OpenEnv environments with GRPO training.
 
 ### Unsloth
 See the 2048 game example based on gpt-oss: [Colab notebook](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/OpenEnv_gpt_oss_(20B)_Reinforcement_Learning_2048_Game.ipynb)
@@ -308,27 +359,20 @@ See the [Oumi example](https://github.com/oumi-ai/oumi/blob/main/notebooks/Oumi%
 
 ## Example Environments
 
-### Echo Environment
-A simple environment that echoes back messages with metadata. Perfect for:
-- Testing the HTTP server infrastructure
-- Learning the framework basics
-- Verifying container deployment
-
-See: [`envs/echo_env/README.md`](envs/echo_env/README.md)
-
-### Coding Environment
-Executes arbitrary Python code in a sandboxed environment. Features:
-- Safe code execution using smolagents
-- Capture stdout, stderr, and exit codes
-- Persistent execution context within episodes
-- Error handling with detailed messages
+| Environment | Description |
+|---|---|
+| [Echo Environment](envs/echo_env/README.md) | Echoes back messages with metadata. Ideal for testing HTTP server infrastructure, learning framework basics, and verifying container deployment. |
+| [Coding Environment](envs/coding_env/README.md) | Sandboxed Python code execution via smolagents. Captures stdout/stderr/exit codes, supports persistent episode context, and provides detailed error handling. |
+| [Chess Environment](envs/chess_env/README.md) | Chess RL environment with configurable opponents and full rules support. |
+| [Atari Environment](envs/atari_env/README.md) | Classic Arcade Learning Environment tasks for RL benchmarking. |
+| [FinRL Environment](envs/finrl_env/README.md) | Financial market simulations for algorithmic trading experiments. |
 
-See: [`envs/coding_env/README.md`](envs/coding_env/README.md)
+> Browse the full catalog of community environments at [meta-pytorch.org/OpenEnv/environments](https://meta-pytorch.org/OpenEnv/environments/).
 
 ## Community Support & Acknowledgments
 This is an open and community-centric project. If you would like to add your name here, please put up a pull request and tag @jspisak for review. Ty!!
 
-Supporters include: Meta-PyTorch, Hugging Face, [Patronus AI](https://patronus.ai), [Surge AI](https://surgehq.ai), [LastMile AI](https://www.lastmileai.dev), Unsloth AI, Reflection AI, vLLM, SkyRL (UC-Berkeley), LightningAI, Axolotl AI, Stanford Scaling Intelligence Lab, Mithril, [OpenMined](https://openmined.org/), [Fleet AI](https://fleetai.com), [Halluminate](https://halluminate.ai/), [Turing](https://www.turing.com/) ..
+Supporters include: Meta-PyTorch, Hugging Face, [Scaler AI Labs](https://scalerailabs.com), [Patronus AI](https://patronus.ai), [Surge AI](https://surgehq.ai), [LastMile AI](https://www.lastmileai.dev), Unsloth AI, Reflection AI, vLLM, SkyRL (UC-Berkeley), LightningAI, Axolotl AI, Stanford Scaling Intelligence Lab, Mithril, [OpenMined](https://openmined.org/), [Fleet AI](https://fleetai.com), [Halluminate](https://halluminate.ai/), [Turing](https://www.turing.com/), [Scale AI](https://scale.com/) ..
 
 And we'd also like to acknowledge the team at Farama Foundation as the OpenEnv API was heavily inspired by the work you all have done on Gymnasium. Cheers!