@beforewave/agent-helm

Bring ChatGPT’s reasoning into your local engineering environment.

Agent Helm gives ChatGPT a stable local capability layer for working directly on your codebase:

• understand code and navigate symbols
• make structured code changes and refactors
• inspect diagnostics and recover the language server
• execute local commands
• discover and delegate to native coding agents when needed

ChatGPT remains the reasoning layer. Agent Helm provides the local engineering surface that lets those decisions act on the real project.

Install

npm install -g @beforewave/agent-helm

Run the standalone service:

agent-helm daemon --project /path/to/project

DeepSeek Harness users normally do not install this package directly. Install @beforewave/dsh-with-chatgpt instead; it brings Agent Helm Core with it.

How it works

ChatGPT reasoning
      ↓
  Agent Helm
      ↓
 local project

      or

ChatGPT reasoning
      ↓
  Agent Helm
      ↓
native coding agent

Agent Helm owns the public capability and policy boundary. Serena is currently the internal code-intelligence provider, not a user-facing permission model.

Managed Serena is started with the engineering tools Agent Helm needs, including optional provider tools such as restart_language_server. Agent Helm then decides which stable code_* tools are exposed through codeCapabilities and codeTools.deny.

You do not configure Serena read_only, optional tool lists, context, or mode through Agent Helm. Agent Helm does not accept those legacy provider-policy fields; its public permissions are defined only by codeCapabilities and codeTools.deny. Serena’s own local project configuration remains Serena’s responsibility.

Serena memory, onboarding, dashboard, and other unrelated tools are not exposed through Agent Helm.

Configuration

Agent Helm uses its own configuration namespace:

~/.config/agent-helm/config.yml
<project>/.agent-helm/config.yml

Example:

codeCapabilities:
  - read
  - write
  - execute
  - diagnostic

codeTools:
  deny: []

tunnel:
  enabled: true

codeCapabilities is the provider-neutral capability ceiling. codeTools.deny can only remove individual stable Agent Helm tools from that surface.

Agent Helm permissions are controlled only by codeCapabilities and codeTools.deny. Serena project configuration is not interpreted as Agent Helm policy.

Runtime defaults

Default runtime identifiers:

• MCP: http://127.0.0.1:3457/mcp
• Tunnel Admin UI: http://127.0.0.1:3458/ui
• adapter socket: ~/.agent-helm/run/daemon.sock
• default token path: ~/.agent-helm/token
• token env: AGENT_HELM_TOKEN
• local token env: AGENT_HELM_LOCAL_TOKEN
• managed tunnel auth env: AGENT_HELM_AUTH
• launcher override env: AGENT_HELM_LAUNCHER_CONFIG_JSON

DSH

For direct work plus DSH delegation, use:

dsh plugin --profile web add @beforewave/dsh-with-chatgpt

That package is the user-facing DSH entry and manages the Core lifecycle while registering DSH as a native agent adapter.