Skip to content

Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai

Make crawl4ai a core dep, center HYPER, simplify install

Jordan3909b1f53446
diff --git a/README.md b/README.md
index d780ef2..400c1de 100644
--- a/README.md
+++ b/README.md
@@ -18,7 +18,7 @@ Your AI agent searches the web, finds great sources, synthesizes an answer — t
**Hyperresearch makes research persist.** Every source your agent finds is fetched with a real headless browser, saved as searchable markdown, and indexed into a knowledge base that compounds across sessions.
```bash
-pip install hyperresearch[crawl4ai]
+pip install hyperresearch
hyperresearch install
```
diff --git a/assets/banner.png b/assets/banner.png
index 539fcb7..789582f 100644
Binary files a/assets/banner.png and b/assets/banner.png differ
diff --git a/pyproject.toml b/pyproject.toml
index c8166bf..2563928 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -28,12 +28,12 @@ dependencies = [
"pydantic>=2.0",
"jinja2>=3.1",
"platformdirs>=4.0",
+ "Crawl4AI>=0.4",
]
[project.optional-dependencies]
-crawl4ai = ["Crawl4AI>=0.4"]
mcp = ["mcp>=1.6"]
-all = ["hyperresearch[crawl4ai,mcp]"]
+all = ["hyperresearch[mcp]"]
dev = [
"pytest>=7.4",
"pytest-cov>=4.1",