I Turned helix-agent into helix-agents: One MCP Server for Ollama, Codex, and OpenAI-Compatible Models

If you use Claude Code heavily, you eventually hit the same wall:

• some tasks are cheap enough for local models

• some tasks want a stronger coding agent

• some tasks are better sent to an API model

But many MCP servers still force one provider and one execution style.

So I evolved helix-agent into helix-agents.

It now lets Claude Code delegate work across:

• ollama

• codex

• openai-compatible

from one MCP server.

What changed

The original project was focused on one thing: sending routine work to local Ollama models with automatic routing.

The new version keeps that path, but adds:

• multi-provider switching

• Codex-backed code delegation

• OpenAI-compatible chat API support

• Claude Code-style background agents

Under the hood, the runtime now supports two different delegation styles:

• a built-in ReAct loop for ollama and openai-compatible

• an autonomous Codex-backed path for repo-heavy work

That means the workflow is no longer:

Claude Code -> one tool call -> one reply

Enter fullscreen mode

Exit fullscreen mode

It can now be:

Claude Code  -> spawn a worker  -> send follow-up instructions  -> wait for completion  -> inspect and close

Claude Code  -> spawn a worker  -> send follow-up instructions  -> wait for completion  -> inspect and close

Enter fullscreen mode

Exit fullscreen mode

Why this matters

Different providers are good at different things.

• ollama: local reasoning, low-cost drafts, vision

• codex: code-heavy implementation and repo work

• openai-compatible: hosted chat models behind standard APIs

Instead of wiring three separate MCP servers with different interaction models, I wanted one consistent runtime.

New tools

Core tools:

• think

• agent_task

• see

• providers

• models

• config

Background agent tools:

• spawn_agent

• send_agent_input

• wait_agent

• list_agents

• close_agent

Example flows

1. Code review via Codex

think(  task="Review this diff for regressions",  provider="codex",  cwd="/repo" )

think(  task="Review this diff for regressions",  provider="codex",  cwd="/repo" )

Enter fullscreen mode

Exit fullscreen mode

2. Local summarization via Ollama

think(  task="Summarize this build log",  provider="ollama" )

think(  task="Summarize this build log",  provider="ollama" )

Enter fullscreen mode

Exit fullscreen mode

3. Persistent investigation worker

spawn_agent(  description="Investigate flaky tests",  provider="codex",  agent_type="explorer" )

spawn_agent(  description="Investigate flaky tests",  provider="codex",  agent_type="explorer" )

Enter fullscreen mode

Exit fullscreen mode

Then:

send_agent_input(...) wait_agent(...) close_agent(...)

send_agent_input(...) wait_agent(...) close_agent(...)

Enter fullscreen mode

Exit fullscreen mode

Setup

git clone https://github.com/tsunamayo7/helix-agent.git cd helix-agent uv sync uv run python server.py

git clone https://github.com/tsunamayo7/helix-agent.git cd helix-agent uv sync uv run python server.py

Enter fullscreen mode

Exit fullscreen mode

Add to Claude Code:

{  "mcpServers": {  "helix-agents": {  "command": "uv",  "args": ["run", "--directory", "/path/to/helix-agent", "python", "server.py"]  }  } }

{  "mcpServers": {  "helix-agents": {  "command": "uv",  "args": ["run", "--directory", "/path/to/helix-agent", "python", "server.py"]  }  } }

Enter fullscreen mode

Exit fullscreen mode

Notes

• Codex requires codex on PATH

• OpenAI-compatible mode requires an API key

• The generic OpenAI-compatible path is currently text-first

• Vision is currently centered on the Ollama path

GitHub: helix-agent