Fix readme table and links

saqadri · saqadri · commit 99bb33148e3f · 2025-10-28T13:56:26.000-04:00
diff --git a/README.md b/README.md
@@ -150,21 +150,21 @@ mcp-agent's complete documentation is available at **[docs.mcp-agent.com](https:
   - [Workflows & decorators](#workflows--decorators)
   - [Configuration & secrets](#configuration--secrets)
   - [MCP integration](#mcp-integration)
-- [Workflow patterns](#workflows)
-- [Durable execution](#durable-execution)
-- [Agent servers](#agent-servers)
+- [Workflow patterns](#workflow-patterns)
 - [CLI reference](#cli-reference)
 - [Authentication](#authentication)
 - [Advanced](#advanced)
   - [Observability & controls](#observability--controls)
-  - [Composing workflows](#composability)
-  - [Signals & human input](#signaling-and-human-input)
-  - [App configuration](#app-config)
+  - [Composing workflows](#composing-workflows)
+  - [Durable execution](#durable-execution)
+  - [Agent servers](#agent-servers)
+  - [Signals & human input](#signals--human-input)
+  - [App configuration](#app-configuration)
   - [Icons](#icons)
   - [MCP server management](#mcp-server-management)
 - [Cloud deployment](#cloud-deployment)
 - [Examples](#examples)
-- [FAQ](#faqs)
+- [FAQs](#faqs)
 - [Community & contributions](#contributing)
 
 ## Get Started
@@ -464,15 +464,15 @@ Docs: [MCP integration overview](https://docs.mcp-agent.com/mcp/overview) • Ex
 
 Key agent patterns are implemented as an `AugmentedLLM`. Use factory helpers to wire them up or inspect the runnable projects listed in [gallery.md](gallery.md#workflow-patterns).
 
-| Pattern               | Factory helper                                                                 | Summary                                                  | Docs & examples                                                                                                                                                                |
-| --------------------- | ------------------------------------------------------------------------------ | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| Parallel (Map-Reduce) | `create_parallel_llm(...)`                                                     | Fan out to specialists and combine their reports.        | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/map-reduce) • [`workflow_parallel`](./examples/workflows/workflow_parallel/)                                |
-| Router                | `create_router_llm(...)`, `create_router_embedding(...)`                       | Route requests to the best agent, server, or function.   | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/router) • [`workflow_router`](./examples/workflows/workflow_router/)                                        |
-| Intent classifier     | `create_intent_classifier_llm(...)`, `create_intent_classifier_embedding(...)` | Bucket requests into labelled intents before automation. | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/intent-classifier) • [`workflow_intent_classifier`](./examples/workflows/workflow_intent_classifier/)       |
-| Orchestrator-workers  | `create_orchestrator(...)`                                                     | Generate plans, assign work, and coordinate completion.  | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/planner) • [`workflow_orchestrator_worker`](./examples/workflows/workflow_orchestrator_worker/)             |
-| Deep research         | `create_deep_orchestrator(...)`                                                | Long-horizon research with policy guardrails.            | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/deep-research) • [`workflow_deep_orchestrator`](./examples/workflows/workflow_deep_orchestrator/)           |
-| Evaluator-optimizer   | `create_evaluator_optimizer_llm(...)`                                          | Iterate until a reviewer approves the output.            | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/evaluator-optimizer) • [`workflow_evaluator_optimizer`](./examples/workflows/workflow_evaluator_optimizer/) |
-| Swarm                 | `create_swarm(...)`                                                            | Multi-agent handoffs compatible with OpenAI Swarm.       | [Docs](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/swarm) • [`workflow_swarm`](./examples/workflows/workflow_swarm/)                                           |
+| Pattern               | Helper                                                                          | Summary                                                                                                                                                                                                                                                                                                                                                                                                                                                            | Docs                                                                                                   |
+| --------------------- | ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------ |
+| Parallel (Map-Reduce) | `create_parallel_llm(...)`                                                      | Fan-out specialists and fan-in aggregated reports.<br><a href="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F406bb032ca007fd1624f261af717d70e6ca86286-2401x1000.png&w=3840&q=75"><img src="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F406bb032ca007fd1624f261af717d70e6ca86286-2401x1000.png&w=3840&q=75" width="260"/></a>     | [Parallel](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/map-reduce)                     |
+| Router                | `create_router_llm(...)` / `create_router_embedding(...)`                       | Route requests to the best agent, server, or function.<br><a href="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F5c0c0e9fe4def0b584c04d37849941da55e5e71c-2401x1000.png&w=3840&q=75"><img src="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F5c0c0e9fe4def0b584c04d37849941da55e5e71c-2401x1000.png&w=3840&q=75" width="260"/></a> | [Router](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/router)                           |
+| Intent classifier     | `create_intent_classifier_llm(...)` / `create_intent_classifier_embedding(...)` | Bucket user input into intents before automation.                                                                                                                                                                                                                                                                                                                                                                                                                  | [Intent classifier](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/intent-classifier)     |
+| Orchestrator-workers  | `create_orchestrator(...)`                                                      | Generate plans and coordinate worker agents.<br><a href="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F8985fc683fae4780fb34eab1365ab78c7e51bc8e-2401x1000.png&w=3840&q=75"><img src="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F8985fc683fae4780fb34eab1365ab78c7e51bc8e-2401x1000.png&w=3840&q=75" width="260"/></a>           | [Planner](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/planner)                         |
+| Deep research         | `create_deep_orchestrator(...)`                                                 | Long-horizon research with knowledge extraction and policy checks.                                                                                                                                                                                                                                                                                                                                                                                                 | [Deep research](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/deep-research)             |
+| Evaluator-optimizer   | `create_evaluator_optimizer_llm(...)`                                           | Iterate until an evaluator approves the result.<br><a href="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F14f51e6406ccb29e695da48b17017e899a6119c7-2401x1000.png&w=3840&q=75"><img src="https://www.anthropic.com/_next/image?url=https%3A%2F%2Fwww-cdn.anthropic.com%2Fimages%2F4zrzovbb%2Fwebsite%2F14f51e6406ccb29e695da48b17017e899a6119c7-2401x1000.png&w=3840&q=75" width="260"/></a>        | [Evaluator-optimizer](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/evaluator-optimizer) |
+| Swarm                 | `create_swarm(...)`                                                             | Multi-agent handoffs compatible with OpenAI Swarm.<br><a href="https://github.com/openai/swarm/blob/main/assets/swarm_diagram.png?raw=true"><img src="https://github.com/openai/swarm/blob/main/assets/swarm_diagram.png?raw=true" width="220"/></a>                                                                                                                                                                                                               | [Swarm](https://docs.mcp-agent.com/mcp-agent-sdk/effective-patterns/swarm)                             |
 
 ## Durable execution
 
@@ -715,7 +715,7 @@ You can use mcp-agent applications in a standalone fashion (i.e. they aren't par
 ### How do I deploy to Cloud?
 
 Run `uvx mcp-agent deploy <app-name>` after logging in with `uvx mcp-agent login`. The CLI packages your project, provisions secrets, and exposes an MCP endpoint backed by a durable Temporal runtime. See the [Cloud quickstart](https://docs.mcp-agent.com/get-started/
-  cloud) for step-by-step screenshots and CLI output.
+cloud) for step-by-step screenshots and CLI output.
 
 ### Where is the API reference?
 
diff --git a/gallery.md b/gallery.md
@@ -48,11 +48,25 @@ This gallery collects runnable projects from `/examples` that correspond to sect
 
 ## Spotlight demos
 
-- **Claude Desktop multi-agent evaluation** — [Video](https://github.com/user-attachments/assets/7807cffd-dba7-4f0c-9c70-9482fd7e0699) showing Claude Desktop connected to the `mcp_agent_server` orchestration workflow. Code: [`examples/basic/mcp_server_aggregator`](./examples/basic/mcp_server_aggregator/). Thanks to [Jerron Lim (@StreetLamb)](https://github.com/StreetLamb).
-- **Gmail Streamlit agent** — [Video](https://github.com/user-attachments/assets/54899cac-de24-4102-bd7e-4b2022c956e3) that drives Gmail actions (read/send/delete) via an MCP server from a Streamlit UI. Code: [gmail-mcp-server](https://github.com/jasonsum/gmail-mcp-server/blob/add-mcp-agent-streamlit/streamlit_app.py). Thanks to [Jason Summer (@jasonsum)](https://github.com/jasonsum).
-- **Streamlit RAG chatbot** — [Video](https://github.com/user-attachments/assets/f4dcd227-cae9-4a59-aa9e-0eceeb4acaf4) answering questions against a Qdrant corpus with MCP servers. Code: [`examples/usecases/streamlit_mcp_rag_agent`](./examples/usecases/streamlit_mcp_rag_agent/). Thanks to [Jerron Lim (@StreetLamb)](https://github.com/StreetLamb).
-- **Marimo file finder** — [Screenshot](https://github.com/user-attachments/assets/139a95a5-e3ac-4ea7-9c8f-bad6577e8597) of the Quickstart finder agent running inside [Marimo](https://github.com/marimo-team/marimo). Code: [`examples/usecases/marimo_mcp_basic_agent`](./examples/usecases/marimo_mcp_basic_agent/). Thanks to [Akshay Agrawal (@akshayka)](https://github.com/akshayka).
-- **Swarm airline workflow** — [Video](https://github.com/user-attachments/assets/b314d75d-7945-4de6-965b-7f21eb14a8bd) featuring the Swarm workflow for customer service handoffs. Code: [`examples/workflows/workflow_swarm`](./examples/workflows/workflow_swarm/).
+- **Claude Desktop multi-agent evaluation** — Claude Desktop connected to the `mcp_agent_server` orchestration workflow. Code: [`examples/basic/mcp_server_aggregator`](./examples/basic/mcp_server_aggregator/). Thanks to [Jerron Lim (@StreetLamb)](https://github.com/StreetLamb).
+
+  https://github.com/user-attachments/assets/7807cffd-dba7-4f0c-9c70-9482fd7e0699
+
+- **Gmail Streamlit agent** — Drives Gmail actions (read/send/delete) via an MCP server from a Streamlit UI. Code: [gmail-mcp-server](https://github.com/jasonsum/gmail-mcp-server/blob/add-mcp-agent-streamlit/streamlit_app.py). Thanks to [Jason Summer (@jasonsum)](https://github.com/jasonsum).
+
+  https://github.com/user-attachments/assets/54899cac-de24-4102-bd7e-4b2022c956e3
+
+- **Streamlit RAG chatbot** — Answers questions against a Qdrant corpus with MCP servers. Code: [`examples/usecases/streamlit_mcp_rag_agent`](./examples/usecases/streamlit_mcp_rag_agent/). Thanks to [Jerron Lim (@StreetLamb)](https://github.com/StreetLamb).
+
+  https://github.com/user-attachments/assets/f4dcd227-cae9-4a59-aa9e-0eceeb4acaf4
+
+- **Marimo file finder** — Screenshot of the Quickstart finder agent running inside [Marimo](https://github.com/marimo-team/marimo). Code: [`examples/usecases/marimo_mcp_basic_agent`](./examples/usecases/marimo_mcp_basic_agent/). Thanks to [Akshay Agrawal (@akshayka)](https://github.com/akshayka).
+
+  https://github.com/user-attachments/assets/139a95a5-e3ac-4ea7-9c8f-bad6577e8597
+
+- **Swarm airline workflow** — Customer service workflow built with the Swarm pattern. Code: [`examples/workflows/workflow_swarm`](./examples/workflows/workflow_swarm/).
+
+  https://github.com/user-attachments/assets/b314d75d-7945-4de6-965b-7f21eb14a8bd
 
 ---
 
