IntelGraph AI Symphony - Agent-Centric Aider Config

Configure Aider with a multi-agent architecture using local LLM routing through LiteLLM proxy, optimized for resource-constrained systems.

What This Does

Sets up Aider to work with locally-hosted AI models through a LiteLLM proxy at `http://127.0.0.1:4000/v1`, enabling role-based agent switching (architect, security reviewer, CI tasks, research) with intelligent performance tuning for systems with limited VRAM.

Instructions

1. **Create the configuration file** at `.aider.conf.yml` in your project root with the following content:

```yaml

IntelGraph AI Symphony - Agent-Centric Aider Config

Default to your Qwen route (fast, low-VRAM coder)

model: openai/local/llama

Aider reads these dashed keys (not an "openai:" block)

openai-api-base: http://127.0.0.1:4000/v1

openai-api-key: sk-anything

Quality & performance settings

pretty: true

stream: true

auto-commits: false

git: true

edit-format: diff

show-diffs: true

max-chat-history-tokens: 8192

Performance tuning for M2 16GB

cache-prompts: true

restore-chat-history: false

File handling

encoding: utf-8

ignore-globs: |

*.log

*.tmp

**/node_modules/**

**/dist/**

**/build/**

**/.vite/**

**/.next/**

**/coverage/**

rag/index/*.duckdb*

**/*.pyc

**/__pycache__/**

```

2. **Ensure LiteLLM proxy is running** on `http://127.0.0.1:4000` with your model routes configured (llama, llama-cpu, llama-small, etc.)

3. **Launch Aider** with default configuration:

```bash

aider

```

4. **Switch agents by overriding the model** for specific tasks:

- **Architect/Coder (default)**: `aider` or `aider --model openai/local/llama`

- **Security Review**: `aider --model openai/local/llama-cpu`

- **Quick CI/PR Tasks**: `aider --model openai/local/llama-small`

- **Research**: `aider --model openai/gemini/1.5-pro` (requires `GOOGLE_API_KEY`)

- **Power Burst**: `aider --model openai/xai/grok-code-fast-1` (requires `XAI_API_KEY`)

Configuration Details

Requirements

Example Workflow

```bash

Start with default architect agent

aider

Switch to security review agent for audit

aider --model openai/local/llama-cpu /add src/auth/*.py

Quick fix with lightweight agent

aider --model openai/local/llama-small "Fix the linting errors in components/"

```