chore(docs): reposition copy to the agents workspace

Update SDK, docs config, and intro/identity copy from the old LLMOps-platform
framing to the new positioning: the open-source workspace for your agents.
Prompt management, evaluation, and observability are reframed as supporting
capabilities, not removed. Carries the 0.105.8 version bump from main.

Claude-Session: https://claude.ai/code/session_013Qe1Vf2yvj33BVd5W1q7HB

Author: mmabrouk

docs/docs/getting-started/01-introduction.mdx

@@ -1,15 +1,15 @@
 ---
 slug: /
 title: What is Agenta?
-description: "Agenta is an open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM Observability all in one place."
+description: "Agenta is the open-source workspace for your agents. Build agents through chat, improve them with feedback, and share them with your whole team."
 id: introduction
 sidebar_position: 0
 ---
 
 
-Agenta is an **open-source LLMOps platform** that helps **AI engineers** and **subject matter experts** build reliable AI applications.
+Agenta is the **open-source workspace for your agents**. You build agents through chat, improve them with feedback, and share them with your whole team. It helps **AI engineers** and **subject matter experts** work on the same agents together.
 
-Agenta covers the entire LLM development lifecycle: **prompt management**, **evaluation**, and **observability**.
+Underneath, Agenta gives you everything you need to make those agents reliable: **prompt management**, **evaluation**, and **observability**.
 
 Learn how a typical workflow in Agenta looks like in this 5 minute walkthrough:
 

docs/docs/misc/01-opensource.mdx

@@ -1,7 +1,7 @@
 ---
 title: Open Source vs. Commercial
 sidebar_label: "OSS vs. Commercial"
-description: Agenta offers both MIT-licensed open source LLMOps tools and commercial features. Compare self-hosting options, feature availability, and licensing details.
+description: Agenta, the open-source workspace for your agents, offers both MIT-licensed open source features and commercial features. Compare self-hosting options, feature availability, and licensing details.
 ---
 
 ## Our Approach
@@ -12,7 +12,7 @@ We believe this approach offers the best balance. You get freedom to use all fun
 
 ### Why Open Source?
 
-Open source matters for an LLMOps platform like Agenta because it gives you:
+Open source matters for a workspace like Agenta because it gives you:
 
 1. **Flexibility**: Modify and customize the software to fit your needs.
 2. **Independence**: Avoid vendor lock-in, ensuring long-term project continuity.

docs/docs/tutorials/cookbooks/02-observability_langchain.mdx

@@ -13,7 +13,7 @@ import GoogleColabButton from "@site/src/components/GoogleColabButton";
 
 ## Introduction
 
-This guide shows you how to set up tracing for a RAG application in Langchain using Agenta, the open-source LLMOps platform.
+This guide shows you how to set up tracing for a RAG application in Langchain using Agenta, the open-source workspace for your agents.
 
 Tracing allows us to debug effectively complex LLM applications. It allows us to view exact prompts sent and contexts retrieved.
 

docs/docusaurus.config.dev.ts

@@ -7,7 +7,7 @@ import type * as OpenApiPlugin from "docusaurus-plugin-openapi-docs";
 
 const config: Config = {
   title: "Docs - Agenta",
-  tagline: "The LLMOps platform.",
+  tagline: "The open-source workspace for your agents.",
   favicon: "images/favicon.ico",
   // Local development configuration
   url: "http://localhost:5000",

docs/docusaurus.config.ts

@@ -8,7 +8,7 @@ import "dotenv/config";
 
 const config: Config = {
   title: "Docs - Agenta",
-  tagline: "The LLMOps platform.",
+  tagline: "The open-source workspace for your agents.",
   favicon: "images/favicon.ico",
   // Public site lives on the main domain under /docs
   url: "https://agenta.ai",
@@ -690,7 +690,7 @@ const config: Config = {
       "docusaurus-plugin-llms-txt",
       {
         title: "Agenta Documentation",
-        description: "The LLMOps platform for building and deploying LLM applications.",
+        description: "The open-source workspace for your agents — build them through chat, improve them with feedback, and share them with your team.",
         fullLLMsTxt: true,
       },
     ],

sdks/python/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "agenta"
 version = "0.105.8"
-description = "The SDK for agenta is an open-source LLMOps platform."
+description = "Agenta — the open-source workspace for your agents. Build agents through chat, improve them with feedback, and share them with your team."
 readme = "README.md"
 requires-python = ">=3.11,<3.14"
 license = "MIT"