diff --git a/nanobot/agent/tools/web.py b/nanobot/agent/tools/web.py
index 9de1d3c..0541ea7 100644
--- a/nanobot/agent/tools/web.py
+++ b/nanobot/agent/tools/web.py
@@ -44,7 +44,7 @@ def _validate_url(url: str) -> tuple[bool, str]:
 
 
 class WebSearchTool(Tool):
-    """Search the web using Brave Search API."""
+    """Search the web using DuckDuckGo (free, no API key required)."""
     
     name = "web_search"
     description = "Search the web. Returns titles, URLs, and snippets."
@@ -58,13 +58,20 @@ class WebSearchTool(Tool):
     }
     
     def __init__(self, api_key: str | None = None, max_results: int = 5):
+        # Keep api_key parameter for backward compatibility, but use DuckDuckGo if not provided
         self.api_key = api_key or os.environ.get("BRAVE_API_KEY", "")
         self.max_results = max_results
+        self.use_brave = bool(self.api_key)
     
     async def execute(self, query: str, count: int | None = None, **kwargs: Any) -> str:
-        if not self.api_key:
-            return "Error: BRAVE_API_KEY not configured"
-        
+        # Try Brave API if key is available, otherwise use DuckDuckGo
+        if self.use_brave:
+            return await self._brave_search(query, count)
+        else:
+            return await self._duckduckgo_search(query, count)
+    
+    async def _brave_search(self, query: str, count: int | None = None) -> str:
+        """Search using Brave API (requires API key)."""
         try:
             n = min(max(count or self.max_results, 1), 10)
             async with httpx.AsyncClient() as client:
@@ -88,6 +95,79 @@ class WebSearchTool(Tool):
             return "\n".join(lines)
         except Exception as e:
             return f"Error: {e}"
+    
+    async def _duckduckgo_search(self, query: str, count: int | None = None) -> str:
+        """Search using DuckDuckGo (free, no API key)."""
+        try:
+            n = min(max(count or self.max_results, 1), 10)
+            
+            # Try using duckduckgo_search library if available
+            try:
+                from duckduckgo_search import DDGS
+                with DDGS() as ddgs:
+                    results = []
+                    for r in ddgs.text(query, max_results=n):
+                        results.append({
+                            "title": r.get("title", ""),
+                            "url": r.get("href", ""),
+                            "description": r.get("body", "")
+                        })
+                    
+                    if not results:
+                        return f"No results found for: {query}"
+                    
+                    lines = [f"Results for: {query}\n"]
+                    for i, item in enumerate(results, 1):
+                        lines.append(f"{i}. {item['title']}\n   {item['url']}")
+                        if item['description']:
+                            lines.append(f"   {item['description']}")
+                    return "\n".join(lines)
+            except ImportError:
+                # Fallback: use DuckDuckGo instant answer API (simpler, but limited)
+                async with httpx.AsyncClient(
+                    follow_redirects=True,
+                    timeout=15.0
+                ) as client:
+                    # Use DuckDuckGo instant answer API (no key needed)
+                    url = "https://api.duckduckgo.com/"
+                    r = await client.get(
+                        url,
+                        params={"q": query, "format": "json", "no_html": "1", "skip_disambig": "1"},
+                        headers={"User-Agent": USER_AGENT},
+                    )
+                    r.raise_for_status()
+                    data = r.json()
+                    
+                    results = []
+                    # Get RelatedTopics (search results)
+                    if "RelatedTopics" in data:
+                        for topic in data["RelatedTopics"][:n]:
+                            if "Text" in topic and "FirstURL" in topic:
+                                results.append({
+                                    "title": topic.get("Text", "").split(" - ")[0] if " - " in topic.get("Text", "") else topic.get("Text", "")[:50],
+                                    "url": topic.get("FirstURL", ""),
+                                    "description": topic.get("Text", "")
+                                })
+                    
+                    # Also check AbstractText for direct answer
+                    if "AbstractText" in data and data["AbstractText"]:
+                        results.insert(0, {
+                            "title": data.get("Heading", query),
+                            "url": data.get("AbstractURL", ""),
+                            "description": data.get("AbstractText", "")
+                        })
+                    
+                    if not results:
+                        return f"No results found for: {query}. Try installing 'duckduckgo-search' package for better results: pip install duckduckgo-search"
+                    
+                    lines = [f"Results for: {query}\n"]
+                    for i, item in enumerate(results[:n], 1):
+                        lines.append(f"{i}. {item['title']}\n   {item['url']}")
+                        if item['description']:
+                            lines.append(f"   {item['description']}")
+                    return "\n".join(lines)
+        except Exception as e:
+            return f"Error searching: {e}. Try installing 'duckduckgo-search' package: pip install duckduckgo-search"
 
 
 class WebFetchTool(Tool):
diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index ee98536..b901953 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -494,9 +494,16 @@ def agent(
     if message:
         # Single message mode
         async def run_once():
-            with _thinking_ctx():
-                response = await agent_loop.process_direct(message, session_id)
-            _print_agent_response(response, render_markdown=markdown)
+            try:
+                with _thinking_ctx():
+                    response = await agent_loop.process_direct(message, session_id)
+                # response is a string (content) from process_direct
+                _print_agent_response(response or "", render_markdown=markdown)
+            except Exception as e:
+                import traceback
+                console.print(f"[red]Error: {e}[/red]")
+                console.print(f"[dim]{traceback.format_exc()}[/dim]")
+                raise
         
         asyncio.run(run_once())
     else: