SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Doc: Update API reference landing page
Kilian Lieret3349137c3277
diff --git a/docs/reference/index.md b/docs/reference/index.mdindex 8ad4a9b6..1c3d85ba 100644--- a/docs/reference/index.md+++ b/docs/reference/index.md@@ -1,25 +1,9 @@-# Code structure and reference+# API Reference++This section shows all configuration options, as well as API details for the main classes.!!! warning "This section is in development"- Some submodules are missing. We also do not strive for completeness, but provide this as an easy entry point- for people who want to start reading the code.- Also note that SWE-agent is still developed very actively, so the python implementation details- are still changing. See [the changelog](../installation/changelog.md) for more information.+ We're currently expanding this section. There's already a lot available here (see the sidebar), but we're still adding more.!!! tip "SWE-agent architecture"- Please first read the [architecture page](../background/architecture.md) for an overview of SWE-agent.--The core:--* The `sweagent/agent/` []() submodule implements the agent.- * [Read about the `Agent` class](agent.md)- * [Explore the code](https://github.com/princeton-nlp/SWE-agent/tree/main/sweagent/agent/)-* The `sweagent/environment/` submodule handles the communication with the docker container where we execute code.- * [Read about the `SWEEnv` class](agent.md)- * [Explore the code](https://github.com/princeton-nlp/SWE-agent/tree/main/sweagent/environment/)--More subfolders--* See the [`scripts/`](https://github.com/princeton-nlp/SWE-agent/tree/main/scripts/) folder for other useful scripts and details.-* See the [`config/`](https://github.com/princeton-nlp/SWE-agent/tree/main/config/) folder for details about how you can define your own configuration!-* See the [`trajectories/`](https://github.com/princeton-nlp/SWE-agent/tree/main/trajectories) folder for details about the output of `run.py`.+ Before you dive into the code, please first read the [architecture page](../background/architecture.md) for an overview of SWE-agent.