Correct LLM provider count to 11 across README, docs, corpus, and tests

Author: jddunn

README.md

@@ -6,7 +6,7 @@
 
 <br />
 
-# **AgentOS** · TypeScript AI Agent Runtime
+# **AgentOS** · TypeScript AI Agent Framework
 
 **Agents that remember, forge their own tools, and survive long-running sessions.** Persistent cognitive memory, optional HEXACO personality, multi-agent orchestration, and one dispatch interface across 11 LLM providers. Apache-2.0.
 
@@ -27,7 +27,7 @@
 
 ---
 
-AgentOS is an open-source TypeScript runtime for AI agents that **remember, adapt, and write their own tools**.
+AgentOS is an open-source TypeScript framework for AI agents that **remember, adapt, and write their own tools**.
 
 - **85.6% on [LongMemEval-S](https://github.com/framersai/agentos-bench/blob/master/results/LEADERBOARD.md)** at $0.0090 per correct answer (gpt-4o reader): +1.4 points over Mastra OM gpt-4o (84.23%), 0.4 behind Emergence.ai's 86% closed-source SOTA.
 - **70.2% on LongMemEval-M** (1.5M-token haystacks, 500 sessions per question): the only open-source library on the public record above 65% on M with publicly reproducible methodology.

docs/getting-started/GETTING_STARTED.md

@@ -181,7 +181,7 @@ flowchart LR
 ```
 
 - **Agent** — the runtime loop. Receives input, calls the LLM, executes tool calls, retrieves memory, returns a response. `agent()` and `agency()` are the two factories that build one.
-- **LLM** — the language model. AgentOS routes through 21 provider adapters; the agent does not care which one you pick.
+- **LLM** — the language model. AgentOS routes through 11 provider adapters; the agent does not care which one you pick.
 - **Memory** — what survives across turns and sessions. Working memory (short-term scratchpad) plus cognitive memory (episodic, semantic, procedural traces with Ebbinghaus decay, retrieval-induced forgetting, and reconsolidation).
 - **Tools** — functions the agent can invoke when the LLM decides it needs one. Pre-registered tools work the same way runtime-generated tools do once approved by the LLM judge.
 

package.json

@@ -1,7 +1,7 @@
 {
   "name": "@framers/agentos",
   "version": "0.9.23",
-  "description": "AgentOS: open-source TypeScript runtime for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.",
+  "description": "AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.",
   "homepage": "https://agentos.sh",
   "repository": {
     "type": "git",

scripts/build-knowledge-corpus.mjs

@@ -210,7 +210,7 @@ function getFaqEntries(skillCount = 0) {
       id: 'faq:supported-models',
       heading: 'What LLM models are supported?',
       content:
-        'AgentOS supports 21 LLM providers: OpenAI (gpt-4o, gpt-4o-mini), Anthropic (claude-sonnet, claude-haiku, claude-opus), Google (gemini-2.5-pro, gemini-2.5-flash), Ollama (any local model), OpenRouter (800+ models), plus Groq, Together, Fireworks, Mistral, Cohere, Perplexity, DeepSeek, xAI, and more.',
+        'AgentOS supports 11 LLM providers: OpenAI (gpt-4o, gpt-4o-mini), Anthropic (claude-sonnet, claude-haiku, claude-opus), Google Gemini (gemini-2.5-pro, gemini-2.5-flash), Groq, Together AI, Mistral, xAI, OpenRouter (fans out to 200+ models), and Ollama (any local model), plus CLI bridges for Claude Code and Gemini CLI.',
       category: 'faq',
     },
     {
@@ -489,7 +489,7 @@ function getApiReferenceEntries() {
       id: 'api:generateText',
       heading: 'generateText() API',
       content:
-        "import { generateText } from '@framers/agentos'. generateText({ model: 'openai:gpt-4o', prompt: 'Hello', system?: '...', tools?: [...], maxSteps?: 5, temperature?: 0.7 }) -> Promise<{ text, provider, model, usage, toolCalls }>. The core text generation function supporting all 21 LLM providers.",
+        "import { generateText } from '@framers/agentos'. generateText({ model: 'openai:gpt-4o', prompt: 'Hello', system?: '...', tools?: [...], maxSteps?: 5, temperature?: 0.7 }) -> Promise<{ text, provider, model, usage, toolCalls }>. The core text generation function supporting all 11 LLM providers.",
       category: 'api',
     },
     {

src/orchestration/pipeline/query/__tests__/platform-knowledge.test.ts

@@ -34,7 +34,7 @@ const PLATFORM_CORPUS_FIXTURE = JSON.stringify([
     id: 'api:generateText',
     heading: 'generateText() API',
     content:
-      "import { generateText } from '@framers/agentos'. Core text generation function supporting all 21 LLM providers.",
+      "import { generateText } from '@framers/agentos'. Core text generation function supporting all 11 LLM providers.",
     category: 'api',
   },
   {

tests/e2e/platform-knowledge.e2e.spec.ts

@@ -178,7 +178,7 @@ describe('Platform Knowledge — e2e', () => {
 
     // Generator mock
     mockGenerateText.mockResolvedValueOnce({
-      text: 'AgentOS supports 21 LLM providers including OpenAI, Anthropic, Google, and Ollama.',
+      text: 'AgentOS supports 11 LLM providers including OpenAI, Anthropic, Google, and Ollama.',
       provider: 'openai',
       model: 'gpt-4o-mini',
       usage: { promptTokens: 150, completionTokens: 40, totalTokens: 190 },