diff --git a/README.md b/README.md
index d38d02c..9fb8bff 100644
--- a/README.md
+++ b/README.md
@@ -58,7 +58,7 @@ It gives you one place to manage repositories, issue-driven worktrees, embedded
 
 ### Agent Chat
 - Interactive chat sessions with ACP agents (Claude, Codex, Pi, Gemini, and more via acpx)
-- OpenAI-compatible provider support: Ollama, LM Studio, OpenRouter, OpenAI, and any `/v1/chat/completions` endpoint
+- OpenAI-compatible provider support: Ollama, LM Studio, OpenRouter, Requesty, OpenAI, and any `/v1/chat/completions` endpoint
 - Streaming responses via SSE for OpenAI-compatible providers and JSONL for ACP agents
 - Automatic model discovery: probes `/v1/models` at startup for configured providers
 - Model selector with per-provider sections and distinct icons (ACP vs API)
diff --git a/crates/arbor-daemon-client/src/types.rs b/crates/arbor-daemon-client/src/types.rs
index 311a0ac..2f0b598 100644
--- a/crates/arbor-daemon-client/src/types.rs
+++ b/crates/arbor-daemon-client/src/types.rs
@@ -254,7 +254,7 @@ pub struct AgentChatSessionDto {
 pub enum AgentChatTransport {
     /// ACP agent via acpx CLI subprocess.
     Acp,
-    /// OpenAI-compatible HTTP API (Ollama, LM Studio, OpenRouter, etc.).
+    /// OpenAI-compatible HTTP API (Ollama, LM Studio, OpenRouter, Requesty, etc.).
     OpenAiChat {
         base_url: String,
         api_key: Option<String>,
diff --git a/crates/arbor-gui/src/app_config.rs b/crates/arbor-gui/src/app_config.rs
index 3cbade0..9c5f3a2 100644
--- a/crates/arbor-gui/src/app_config.rs
+++ b/crates/arbor-gui/src/app_config.rs
@@ -41,7 +41,7 @@ const DEFAULT_CONFIG_CONTENT: &str = r#"# Arbor configuration
 # key = "copilot"
 # command = "copilot --allow-all"
 
-# OpenAI-compatible providers (Ollama, LM Studio, OpenRouter, etc.)
+# OpenAI-compatible providers (Ollama, LM Studio, OpenRouter, Requesty, etc.)
 # Arbor probes /v1/models at startup when fetch_models = true.
 #
 # [[providers]]
@@ -67,6 +67,13 @@ const DEFAULT_CONFIG_CONTENT: &str = r#"# Arbor configuration
 # fetch_models = true
 #
 # [[providers]]
+# name = "Requesty"
+# kind = "openai-compatible"
+# base_url = "https://router.requesty.ai/v1"
+# api_key_env = "REQUESTY_API_KEY"
+# fetch_models = true
+#
+# [[providers]]
 # name = "OpenAI"
 # kind = "openai-compatible"
 # base_url = "https://api.openai.com/v1"
diff --git a/crates/arbor-httpd/src/agent_chat.rs b/crates/arbor-httpd/src/agent_chat.rs
index 7767064..907acfb 100644
--- a/crates/arbor-httpd/src/agent_chat.rs
+++ b/crates/arbor-httpd/src/agent_chat.rs
@@ -4,7 +4,7 @@
 //! - **ACP** (Agent Client Protocol): spawns agent CLI processes via `acpx`,
 //!   parses their JSONL stdout into structured events.
 //! - **OpenAI-compatible**: sends HTTP requests to `/v1/chat/completions`
-//!   endpoints (Ollama, LM Studio, OpenRouter, OpenAI, etc.) and streams SSE
+//!   endpoints (Ollama, LM Studio, OpenRouter, Requesty, OpenAI, etc.) and streams SSE
 //!   responses.
 //!
 //! Events from both transports are broadcast over a `tokio::sync::broadcast`
@@ -49,7 +49,7 @@ pub(crate) enum AgentChatStatus {
 pub(crate) enum AgentChatTransport {
     /// ACP agent via acpx CLI subprocess.
     Acp,
-    /// OpenAI-compatible HTTP API (Ollama, LM Studio, OpenRouter, etc.).
+    /// OpenAI-compatible HTTP API (Ollama, LM Studio, OpenRouter, Requesty, etc.).
     OpenAiChat {
         base_url: String,
         api_key: Option<String>,