Deebo

Deebo

What is Deebo about?

Deebo acts as a multi‑threaded debugging assistant for AI coding agents. It automates the investigation of software errors, maintains session state, and surfaces concise findings so agents can resolve issues faster.

How to use Deebo?

1. Install – run npx deebo-setup@latest to set up the core binaries.
2. Configure – create a JSON config (usually placed in ~/.deebo/config.json) that defines the deebo and optional deebo-guide servers with node command, args, and environment variables such as API keys and model selections.
3. Start a Session – instruct the primary AI agent to delegate a bug to Deebo, providing the error details, repository path, and any relevant context.
4. Monitor Progress – query the session ID after a short delay to receive a pulse summarizing current investigations.
5. Guide or Cancel – optionally send observations to steer the investigation or cancel the session when the issue is resolved.

Key Features

• Automated Debugging Sessions – launches independent investigations for each bug.
• Multi‑Model Support – works with OpenAI‑compatible SDKs, Anthropic, Gemini, and OpenRouter.
• Memory Bank – persists logs per project hash for later review.
• Guide Server – optional help server that provides documentation even if the main install fails.
• Configurable Environment – select mother and scenario models, set API keys, and toggle memory‑bank usage.

Use Cases

• Accelerating bug resolution for AI‑driven code generation pipelines.
• Providing continuous debugging assistance in CI/CD environments.
• Enhancing autonomous agents with a secondary “debugging thread” to handle complex errors.
• Allowing developers to supervise and intervene in AI‑initiated debugging workflows.

FAQ

Q: Do I need an OpenRouter API key? A: Yes, the default configuration expects OPENROUTER_API_KEY for model access, though you can switch to any OpenAI‑compatible endpoint.

Q: Can I run Deebo without the guide server? A: The guide server is optional; the core deebo server functions independently.

Q: How are sessions stored? A: Session logs are written under ~/.deebo/memory-bank/[project-hash]/sessions/[session-id]/logs/.

Q: Is Deebo still maintained? A: The repository states it is not actively maintained; use at your own risk.

Q: What models are used by default? A: Mother model anthropic/claude-3.5-sonnet and scenario model deepseek/deepseek-chat via OpenRouter, but these are configurable.

Deebo: Your AI Agent's Debugging Copilot

www.bojack.ai From the creators of Deebo.

Bojack is a unified, AI-native DevOps platform based in the browser and terminal. No more dashboards, just answers.

Deebo is not maintained actively. Install at your own risk. Deebo is an agentic debugging copilot for your AI coding agent that speeds up time-to-resolution by 10x. If your main coding agent is like a single-threaded process, Deebo introduces multi-threadedness to your development workflow.

As seen on PulseMCP, @cline on X, and the official MCP directory.

Quick Install (legacy)

npx deebo-setup@latest

After installing with deebo-setup, create a configuration file at your coding agent's specified location with the following content. First, add the guide server (which provides help documentation even if the main installation fails):

{
  "servers": {
    "deebo-guide": {
      "command": "node",
      "args": [
        "--experimental-specifier-resolution=node",
        "--experimental-modules",
        "/Users/[your-name]/.deebo/guide-server.js"
      ],
      "env": {},
      "transportType": "stdio"
    },
    "deebo": {
      "command": "node",
      "args": [
        "--experimental-specifier-resolution=node",
        "--experimental-modules",
        "--max-old-space-size=4096",
        "/Users/[your-name]/.deebo/build/index.js"
      ],
      "env": {
        "NODE_ENV": "development",
        "USE_MEMORY_BANK": "true",
        "MOTHER_HOST": "openrouter",
        "MOTHER_MODEL": "anthropic/claude-3.5-sonnet",
        "SCENARIO_HOST": "openrouter",
        "SCENARIO_MODEL": "deepseek/deepseek-chat",
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

Deebo works with any OpenAI-compatible SDK, Anthropic, Gemini, and OpenRouter.

Deebo helps your AI agent debug real software errors by launching automated investigations. Here's how to use it effectively.

---

1. Start a Debugging Session

When you hit a tough bug, ask your agent to delegate the task to Deebo.

What to include in your request:

• 🔧 The error (message, stack trace, or behavior)
• 📁 The absolute path to your Git repository
• 💡 Any helpful context, such as:
  • What you’ve already tried
  • Relevant files or code snippets
  • How to reproduce the issue
  • The language or environment

Example instruction to your agent:

“This error is happening in /path/to/repo, possibly related to auth logic. I already checked the session token parser. Can you delegate this to Deebo?”

Your agent will start a Deebo session and give you a session ID (e.g. session-1745...). Save it.

---

2. Check Investigation Progress

After ~30 seconds, ask your agent to check the status of the Deebo session using that session ID.

You’ll get a session pulse, which shows:

• Whether the investigation is in progress or completed
• What the system is currently exploring
• Summaries of findings, if any

---

3. Add Observations (Optional)

If you notice something important — or think Deebo is heading the wrong way — you can guide the investigation.

Ask your agent to pass a short observation to Deebo.

Example:

“Let Deebo know that the file size warnings might be a red herring — the issue is probably with the CI env vars.”

This may shift the direction of the investigation.

4. Cancel a Session (Optional)

If you fixed the issue or no longer need the investigation, tell your agent to cancel the Deebo session.

For AI Agents: Memory Bank Access

When asked to check debug session progress, look in: ~/.deebo/memory-bank/[project-hash]/sessions/[session-id]/logs/

The project hash is a unique identifier for each repository, and session IDs are provided when starting a debug session.

Want More?

We're piloting enterprise features that unlock unprecedented productivity gains for your team. Reach out if interested!

---

Watch the full work session with Cline + Deebo here (3 mins, sped up)

License

Apache License 2.0 — see LICENSE for details.