@j-o-r/hello-dave

'Hello, Dave.' — A calm, reliable ESM toolkit for building and running AI agents with unified access to Grok (xAI), OpenAI, Kimi, z.ai (GLM), MiniMax, and Ollama.

Requirements

• Node.js >= 20
• At least one provider API key (see Setup)

Install

npm install -g @j-o-r/hello-dave

Setup

Agents call LLM providers via API keys read from environment variables. Export the key for the provider your agent uses:

| Provider | API.chat.* | Environment variable | |-----------------|--------------|---------------------------------------------| | xAI (Grok) | xai | XAIKEY | | OpenAI (GPT) | openai | OPENAIKEY | | Moonshot (Kimi) | kimi | KIMIKEY | | z.ai (GLM) | zai | ZAIKEY | | MiniMax | minimax | MINIMAX_API_KEY | | Ollama | ollama | none for local; OLLAMA_API_KEY for remote |

export KIMIKEY=<your key>   # ask_agent, code_agent and several others default to Kimi

Verify the install:

dave --list-agents   # prints the bundled agents (ask_agent, code_agent, grok_agent, ...)

A missing key fails fast with an error like Missing KIMIKEY! export KIMIKEY=<KIMI_API_KEY> — export the named variable and retry.

Quick Start

dave --help
dave --list-agents
dave ask_agent
dave code_agent "Refactor lib/Session.js"
echo "Explain this error" | dave ask_agent

Core Usage

dave <agent_name>                 # interactive
dave <agent_name> "your message"  # one-shot
echo "message" | dave <agent_name>
dave <agent_name> --info
dave --list-agents
dave --toolsets                   # list toolsets (--json, or --toolsets --help)

Session utilities:

dave --list                       # list saved sessions
dave --search "keyword"           # search session logs
dave --inspect <session-log>      # format a session log
dave --clear                      # clear saved sessions

Agents are *_agent.js files discovered via AgentLauncher from the agents/ directory of the package the CLI belongs to (the @j-o-r/hello-dave package itself when dave is installed globally). You can also pass a direct path, e.g. dave agents/my_agent.js.

Agent Handoffs (Current Multi-Agent Model)

Use the built-in hand_over / load_agent tools for clean in-process delegation to specialists (or self-reset with fresh context).

• Always fresh: target gets only its own system prompt + short task-focused context.
• No history is copied.
• Use list_agents first when unsure.

This replaced the older WebSocket server/client/swarm/CodeServer model (which has been abandoned).

See docs/creating-agents.md for details.

Creating Agents

dave agent_creator "Create a weather_agent..."
dave agent_creator "Improve code_agent..."

Follow the current standard: docs/creating-agents.md

Key pattern:

• export default agent;
• new Agent({ prompt, api, call_name, call_description, ... })
• Register tools + toolset.borrow(API.toolset.generic.handoff)

Documentation

• docs/creating-agents.md — Canonical guide (read this first for agent work).
• docs/bin-dave.md
• docs/project-overview.md
• docs/docs-organization.md
• docs/creating-toolsets.md etc.

Programmatic Usage

import { Agent, API, AgentLauncher } from '@j-o-r/hello-dave';

const agent = new Agent({
  prompt: "...",
  api: API.chat.xai,
  call_name: 'my_agent',
  call_description: '...'
});

const launcher = new AgentLauncher();
await launcher.load('code_agent');
await launcher.run();

Development

npm install
npm run link-self

License

Apache-2.0

Repository: https://codeberg.org/duin/hello-dave

Putting itself to the fullest possible use.