diff --git a/knowledge base/ai/claude/claude code.md b/knowledge base/ai/claude/claude code.md
index 9910b75..fff051a 100644
--- a/knowledge base/ai/claude/claude code.md	
+++ b/knowledge base/ai/claude/claude code.md	
@@ -57,6 +57,9 @@ claude -c
 
 # Resume a previous conversation
 claude -r
+
+# Add MCPs
+claude mcp add --transport 'sse' 'linear-server' 'https://mcp.linear.app/sse'
 ```
 
 </details>
@@ -109,7 +112,7 @@ Claude Code version: `v2.1.41`.<br/>
 | llama.cpp (ollama) |   16384 |     20 GB | No           |                2m 16s | No                         |
 | llama.cpp (ollama) |   32768 |     22 GB | No           |                 7.12s | No                         |
 | llama.cpp (ollama) |   65536 |     25 GB | No? (unsure) |                10.25s | Meh (minor stutters)       |
-| llama.cpp (ollama) |  131072 |     33 GB | No           |                3m 42s | **No** (major stutters)    |
+| llama.cpp (ollama) |  131072 |     33 GB | **Yes**      |                3m 42s | **No** (major stutters)    |
 
   </details>
 
diff --git a/knowledge base/ai/gemini/cli.md b/knowledge base/ai/gemini/cli.md
index ac9046d..7a4a040 100644
--- a/knowledge base/ai/gemini/cli.md	
+++ b/knowledge base/ai/gemini/cli.md	
@@ -16,7 +16,9 @@ Can read and edit files, execute shell commands, and search the web.
 
 ```sh
 # Install.
+brew install 'gemini-cli'
 npm install -g '@google/gemini-cli'
+port install 'gemini-cli'
 
 # Run without installation.
 docker run --rm -it 'us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.1.1'
@@ -32,6 +34,9 @@ export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"
   <summary>Usage</summary>
 
 ```sh
+# Show version.
+gemini --version
+
 # Start.
 gemini
 
diff --git a/knowledge base/ai/ollama.md b/knowledge base/ai/ollama.md
index 7bee45a..0338a01 100644
--- a/knowledge base/ai/ollama.md	
+++ b/knowledge base/ai/ollama.md	
@@ -32,11 +32,25 @@ Excellent for building applications that require seamless migration from OpenAI.
 
 ```sh
 brew install --cask 'ollama-app'  # or just brew install 'ollama'
+curl -fsSL 'https://ollama.com/install.sh' | sh
 docker pull 'ollama/ollama'
 
 # Run in containers.
 docker run -d -v 'ollama:/root/.ollama' -p '11434:11434' --name 'ollama' 'ollama/ollama'
 docker run -d --gpus='all' … 'ollama/ollama'
+
+# Expose (bind) the server to specific IP addresses and/or with custom ports.
+# Default is 127.0.0.1 on port 11434.
+# Only valid for the *'serve'* command.
+OLLAMA_HOST='some.fqdn:11435' ollama serve
+
+# Use a custom context length.
+# Only valid for the *'serve'* command.
+OLLAMA_CONTEXT_LENGTH=64000 ollama serve
+
+# Use a remotely served model.
+# Valid for all commands *but* 'serve'.
+OLLAMA_HOST='some.fqdn:11435' ollama …
 ```
 
 </details>
@@ -86,18 +100,21 @@ The model can describe, classify, and answer questions about what it sees.
   <summary>Usage</summary>
 
 ```sh
+# Start the server.
+ollama serve
+
+# Verify the server is running.
+curl 'http://localhost:11434/'
+
 # Access the API via cURL.
 curl 'http://localhost:11434/api/generate' -d '{
   "model": "gemma3",
   "prompt": "Why is the sky blue?"
 }'
 
-# Expose (bind) the server to specific IP addresses and/or with custom ports.
-# Default is 127.0.0.1 on port 11434.
-OLLAMA_HOST='some.fqdn:11435'
-
 # Start the interactive menu.
 ollama
+ollama launch
 
 # Download models.
 ollama pull 'qwen2.5-coder:7b'
@@ -107,9 +124,8 @@ ollama pull 'glm-4.7:cloud'
 ollama list
 ollama ls
 
-# Start Ollama.
-ollama serve
-OLLAMA_CONTEXT_LENGTH=64000 ollama serve
+# Show models information.
+ollama show 'codellama:13b'
 
 # Run models interactively.
 ollama run 'gemma3'
@@ -120,10 +136,7 @@ ollama run 'glm-4.7-flash:q4_K_M' 'Hi! Are you there?' --verbose
 ollama run 'deepseek-r1' --think=false "Summarize this article"
 ollama run 'gemma3' --hidethinking "Is 9.9 bigger or 9.11?"
 ollama run 'gpt-oss' --think=low "Draft a headline"
-ollama run 'gemma3' './image.png' "what's in this image?"
-
-# Quickly set up a coding tool with Ollama models.
-ollama launch
+ollama run 'gemma3' './image.png' "what's in this image?" --temperature '0.8' --top-p '0.9'
 
 # Launch integrations.
 ollama launch 'opencode'
@@ -168,26 +181,27 @@ ollama signout
 
 </details>
 
+<!-- Uncomment if used
 <details>
   <summary>Real world use cases</summary>
 
 ```sh
-# Run Claude Code on a model served locally by Ollama.
-ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" \
-  claude --model 'lfm2.5-thinking:1.2b'
 ```
 
 </details>
+-->
 
 ## Further readings
 
 - [Website]
 - [Codebase]
 - [Blog]
+- [Models library]
 
 ### Sources
 
 - [Documentation]
+- [The Complete Guide to Ollama: Run Large Language Models Locally]
 
 <!--
   Reference
@@ -203,6 +217,8 @@ ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_
 [Blog]: https://ollama.com/blog
 [Codebase]: https://github.com/ollama/ollama
 [Documentation]: https://docs.ollama.com/
+[Models library]: https://ollama.com/library
 [Website]: https://ollama.com/
 
 <!-- Others -->
+[The Complete Guide to Ollama: Run Large Language Models Locally]: https://dev.to/ajitkumar/the-complete-guide-to-ollama-run-large-language-models-locally-2mge
diff --git a/knowledge base/ai/opencode.md b/knowledge base/ai/opencode.md
index 95a2f2c..ff81617 100644
--- a/knowledge base/ai/opencode.md	
+++ b/knowledge base/ai/opencode.md	
@@ -23,23 +23,77 @@ docker run -it --rm 'ghcr.io/anomalyco/opencode'
 mise use -g 'opencode'
 nix run 'nixpkgs#opencode'
 npm i -g 'opencode-ai@latest'
+pacman -S 'opencode'
 paru -S 'opencode-bin'
 
 # Desktop app
 brew install --cask 'opencode-desktop'
 ```
 
+Configure OpenCode using `opencode.json` (or `.jsonc`) configuration files.<br/>
+Configuration files are merged, not replaced. Settings from more specific ones override those of the same name in less
+specific ones.
+
+| Scope   | Location                                        | Summary                   |
+| ------- | ----------------------------------------------- | ------------------------- |
+| Remote  | `.well-known/opencode`                          | organizational defaults   |
+| Global  | `~/.config/opencode/opencode.json`              | user preferences          |
+| Custom  | `OPENCODE_CONFIG` environment variable          | custom overrides          |
+| Project | `opencode.json` in the project's directory      | project-specific settings |
+| Agent   | `.opencode` directories                         | agents, commands, plugins |
+| Inline  | `OPENCODE_CONFIG_CONTENT` environment variables | runtime overrides         |
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "ollama": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "Ollama (local)",
+      "options": {
+        "baseURL": "http://localhost:11434/v1"
+      },
+      "models": {
+        "llama2": {
+          "name": "Llama 2"
+        }
+      }
+    }
+  }
+}
+```
+
 </details>
 
-<!-- Uncomment if used
 <details>
   <summary>Usage</summary>
 
 ```sh
+# Start in interactive mode.
+opencode
+opencode 'path/to/directory'
+
+# List available models.
+opencode models
+opencode models 'anthropic'
+
+# Update the cashed models list.
+opencode models --refresh
+
+# Run tasks in headless mode.
+opencode run "Explain how closures work in JavaScript"
+
+# Start a headless server.
+opencode serve
+
+# Attach to headless servers.
+opencode run --attach 'http://localhost:4096' "Explain async/await in JavaScript"
+
+# List existing agents.
+opencode agent list
 ```
 
 </details>
--->
 
 <!-- Uncomment if used
 <details>