Skip to content

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: Add more forwarding to mini-swe-agent

Kilian Adriano Lieretc1a9b34df5b1
diff --git a/README.md b/README.md
index a8447f57..2b38c307 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,12 @@
<a href="https://arxiv.org/abs/2405.15793"><img src="https://img.shields.io/badge/arxiv-2405.15793-red?style=for-the-badge&logo=arxiv&logoColor=white&labelColor=black" alt="arxiv 2405.15793"></a>
</p>
+> [!warning]
+> Most of our current development effort is on [mini-swe-agent](https://github.com/SWE-agent/mini-swe-agent/),
+> which has supersedes SWE-agent. It matches the performance performance of SWE-agent, while being
+> much simpler.
+> See the [FAQ](https://mini-swe-agent.com/latest/faq/) for more details about the differences.
+
SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4) to autonomously use tools to
[fix issues in real GitHub repositories](https://swe-agent.com/latest/usage/hello_world),
@@ -23,12 +29,6 @@ SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4)
SWE-agent is built and maintained by researchers from Princeton University and Stanford University.
-> [!note]
-> Most of our current development effort is on [mini-swe-agent](https://github.com/SWE-agent/mini-swe-agent/),
-> which will eventually supersede SWE-agent. It already matches the performance performance of SWE-agent, while being
-> much simpler.
-> See the [FAQ](https://mini-swe-agent.com/latest/faq/) about whether you should switch already.
-
## 📣 News
* July 24: [Mini-SWE-Agent](https://github.com/SWE-agent/mini-SWE-agent) achieves 65% on SWE-bench verified in 100 lines of python!
diff --git a/docs/index.md b/docs/index.md
index 131ae0a5..1041d668 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -13,6 +13,12 @@ title: "Getting Started"
<img class="dark-mode-only" src="assets/readme_assets/swe-agent-banner-dark.svg" alt="SWE-agent banner" style="height: 10em;">
</div>
+!!! warning "We recommend mini-swe-agent instead of SWE-agent"
+ Most of our current development effort is on [mini-swe-agent](https://github.com/SWE-agent/mini-swe-agent/),
+ which has superseded SWE-agent. It matches the performance of SWE-agent, while being
+ much simpler.
+ See the [FAQ](https://mini-swe-agent.com/latest/faq/) for more details about the differences.
+
SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4) to autonomously use tools to
[fix issues in real GitHub repositories](https://swe-agent.com/latest/usage/hello_world),
[find cybersecurity vulnerabilities](https://enigma-agent.com/), or
diff --git a/docs/overrides/main.html b/docs/overrides/main.html
index 513b491a..9f799fb9 100644
--- a/docs/overrides/main.html
+++ b/docs/overrides/main.html
@@ -1,6 +1,6 @@
{% extends "base.html" %}
{% block announce %}
-📣 Check out <a href="https://mini-swe-agent.com">Mini-SWE-Agent</a>, an AI agent implemented in 100 lines that achieves 65% on SWE-bench verified!
+📣 We now recommend <a href="https://mini-swe-agent.com">mini-swe-agent</a> instead of SWE-agent: Same performance, much more simple &amp; flexible
{% endblock %}
{% block content %}