Document local AI coding setup

.gitignore

@@ -132,3 +132,4 @@ dist
 .yarn/build-state.yml
 .yarn/install-state.gz
 .pnp.*
+.aider*

README.md

@@ -207,3 +207,107 @@ npx @openai/codex resume <session-id> --no-alt-screen -s workspace-write
 ```
 
 For repository-specific agent behavior, see `AGENTS.md`.
+
+## Local AI coding setup
+
+The following optional setup provides local coding assistance on Kubuntu or Ubuntu with Ollama, Aider, and the Continue extension for VS Code.
+
+### Ollama
+
+Install Ollama:
+
+```bash
+curl -fsSL https://ollama.com/install.sh | sh
+sudo systemctl status ollama
+```
+
+Download the recommended local models:
+
+```bash
+ollama pull qwen2.5-coder:1.5b-base
+ollama pull qwen2.5-coder:7b
+ollama pull qwen2.5-coder:14b
+ollama pull nomic-embed-text
+```
+
+Verify that the Ollama API is available:
+
+```bash
+curl http://127.0.0.1:11434/api/tags
+```
+
+Recommended model usage:
+
+| Use case | Model |
+| --- | --- |
+| Autocomplete | `qwen2.5-coder:1.5b-base` |
+| Daily coding | `qwen2.5-coder:7b` |
+| Larger refactoring and review | `qwen2.5-coder:14b` |
+| Embeddings | `nomic-embed-text` |
+
+### Aider
+
+Install Aider with `uv`:
+
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source ~/.bashrc
+uv tool install aider-chat
+```
+
+Configure the local Ollama endpoint and optional aliases:
+
+```bash
+echo 'export OLLAMA_API_BASE=http://127.0.0.1:11434' >> ~/.bashrc
+echo 'alias aider7="aider --model ollama_chat/qwen2.5-coder:7b"' >> ~/.bashrc
+echo 'alias aider14="aider --model ollama_chat/qwen2.5-coder:14b"' >> ~/.bashrc
+source ~/.bashrc
+```
+
+Start Aider from the repository root:
+
+```bash
+cd <project>
+aider7
+```
+
+Ollama must be running locally on port `11434`. Aider works best inside a Git repository and may ask to add its local files to `.gitignore`.
+
+### Continue for VS Code
+
+Install the Continue extension from the VS Code extension view or with:
+
+```bash
+code --install-extension Continue.continue
+```
+
+Open the command palette with `Ctrl+Shift+P`, run `Continue: Open Config`, and use:
+
+```yaml
+name: Local Ollama Coding
+version: 0.0.1
+schema: v1
+
+models:
+  - name: Qwen Coder 7B
+    provider: ollama
+    model: qwen2.5-coder:7b
+    roles:
+      - chat
+      - edit
+      - apply
+
+  - name: Qwen Coder 1.5B
+    provider: ollama
+    model: qwen2.5-coder:1.5b-base
+    roles:
+      - autocomplete
+
+  - name: Nomic Embeddings
+    provider: ollama
+    model: nomic-embed-text
+    roles:
+      - embed
+```
+
+Enable Continue tab autocomplete in the VS Code settings. Use Aider with Ollama for project-wide terminal changes, Continue for editor navigation and autocomplete, and Codex for larger repository tasks.