OnIt

OnIt — the AI is working on the given task and will deliver the results shortly.

OnIt is an intelligent agent for task automation and assistance. It connects to any OpenAI-compatible LLM (private vLLM servers or OpenRouter.ai) and uses MCP tools for web search, file operations, and more. It also supports the A2A protocol for multi-agent communication.

Getting Started

1. Install

pip install onit

Or from source:

git clone https://github.com/sibyl-oracles/onit.git
cd onit
pip install -e ".[all]"

2. Setup

onit setup

The setup wizard walks you through configuring your LLM endpoint, API keys, and preferences. Secrets are stored securely in your OS keychain. Settings are saved to ~/.onit/config.yaml.

To review your configuration at any time:

onit setup --show

3. Run

onit

That's it. MCP tools start automatically, and you get an interactive chat with tool access.

Other interfaces

onit --web                          # Web UI on port 9000
onit --gateway                      # Telegram/Viber bot gateway
onit --a2a                          # A2A server on port 9001
onit --client --task "your task"    # Send a task to an A2A server

Configuration

onit setup is the recommended way to configure OnIt. It stores:

Settings in ~/.onit/config.yaml (LLM endpoint, theme, ports, timeout)
Secrets in your OS keychain (API keys, bot tokens)

You can also use environment variables or a project-level YAML config:

# Environment variables
export ONIT_HOST=https://openrouter.ai/api/v1
export OPENROUTER_API_KEY=sk-or-v1-...

# Or a custom config file
onit --config configs/default.yaml

Priority order: CLI flags > environment variables > ~/.onit/config.yaml > project config file.

Example config (`configs/default.yaml`)

serving:
  host: https://openrouter.ai/api/v1
  host_key: sk-or-v1-your-key-here   # or set OPENROUTER_API_KEY env var
  # model: auto-detected from endpoint. Set explicitly for OpenRouter:
  # model: google/gemini-2.5-pro
  think: true
  max_tokens: 262144

verbose: false
timeout: 600

web: false
web_port: 9000

mcp:
  servers:
    - name: PromptsMCPServer
      url: http://127.0.0.1:18200/sse
      enabled: true
    - name: ToolsMCPServer
      url: http://127.0.0.1:18201/sse
      enabled: true

CLI Reference

General:

Flag	Description	Default
`--config`	Path to YAML configuration file	`configs/default.yaml`
`--host`	LLM serving host URL	—
`--verbose`	Enable verbose logging	`false`
`--timeout`	Request timeout in seconds (`-1` = none)	`600`
`--template-path`	Path to custom prompt template YAML file	—
`--documents-path`	Path to local documents directory	—
`--topic`	Default topic context (e.g. `"machine learning"`)	—
`--prompt-intro`	Custom system prompt intro	—
`--no-stream`	Disable token streaming	`false`
`--think`	Enable thinking/reasoning mode (CoT)	`false`

Text UI:

Flag	Description	Default
`--text-theme`	Text UI theme (`white` or `dark`)	`dark`
`--show-logs`	Show execution logs	`false`

Web UI:

Flag	Description	Default
`--web`	Launch Gradio web UI	`false`
`--web-port`	Gradio web UI port	`9000`

Gateway (Telegram / Viber):

Flag	Description	Default
`--gateway`	Auto-detect gateway (Telegram or Viber based on env vars)	—
`--gateway telegram`	Run as a Telegram bot	—
`--gateway viber`	Run as a Viber bot	—
`--viber-webhook-url`	Public HTTPS URL for Viber webhook	—
`--viber-port`	Local port for Viber webhook server	`8443`

A2A (Agent-to-Agent):

Flag	Description	Default
`--a2a`	Run as an A2A protocol server	`false`
`--a2a-port`	A2A server port	`9001`
`--client`	Send a task to a remote A2A server	`false`
`--a2a-host`	A2A server URL for client mode	`http://localhost:9001`
`--task`	Task string for A2A client or loop mode	—
`--file`	File to upload with the task	—
`--image`	Image file for vision processing	—
`--loop`	Enable A2A loop mode	`false`
`--period`	Seconds between loop iterations	`10`

MCP (Model Context Protocol):

Flag	Description	Default
`--mcp-host`	Override host/IP in all MCP server URLs	—
`--mcp-sse`	URL of an external MCP server (can be repeated)	—

Features

Interactive Chat

Rich terminal UI with input history, theming, and execution logs. Press Enter or Ctrl+C to interrupt any running task.

Web UI

Gradio-based browser interface with file upload and real-time streaming:

onit --web

Supports optional Google OAuth2 authentication — see docs/WEB_AUTHENTICATION.md.

MCP Tool Integration

MCP servers start automatically. Tools are auto-discovered and available to the agent.

Server	Description
PromptsMCPServer	Prompt templates for instruction generation
ToolsMCPServer	Web search, bash commands, file operations, and document tools

Connect to additional external MCP servers:

onit --mcp-sse http://localhost:8080/sse --mcp-sse http://192.168.1.50:9090/sse

Messaging Gateways

Chat with OnIt from Telegram or Viber. Configure bot tokens via onit setup or environment variables, then:

onit --gateway telegram
onit --gateway viber --viber-webhook-url https://your-domain.com/viber

Install the gateway dependency separately if not using [all]:

pip install "onit[gateway]"

A2A Protocol

Run OnIt as an A2A server so other agents can send tasks:

onit --a2a

The agent card is available at http://localhost:9001/.well-known/agent.json.

Send a task via CLI:

onit --client --task "what is the weather in Manila"
onit --client --task "describe this" --image photo.jpg

Send a task via Python (A2A SDK):

from a2a.client import ClientFactory, create_text_message_object
from a2a.types import Role
import asyncio

async def main():
    client = await ClientFactory.connect("http://localhost:9001")
    message = create_text_message_object(role=Role.user, content="What is the weather?")
    async for event in client.send_message(message):
        print(event)

asyncio.run(main())

Loop Mode

Repeat a task on a configurable timer (useful for monitoring):

onit --loop --task "Check the weather in Manila" --period 60

Custom Prompt Templates

onit --template-path my_template.yaml

See example templates in src/mcp/prompts/prompt_templates/.

Model Serving

Private vLLM

Serve models locally with vLLM:

CUDA_VISIBLE_DEVICES=0,1,2,3 vllm serve Qwen/Qwen3-30B-A3B-Instruct-2507 \
  --max-model-len 262144 --port 8000 \
  --enable-auto-tool-choice --tool-call-parser hermes \
  --reasoning-parser qwen3 --tensor-parallel-size 4 \
  --chat-template-content-format string

onit --host http://localhost:8000/v1

OpenRouter.ai

OpenRouter gives access to models from OpenAI, Google, Meta, Anthropic, and others through a single API.

onit --host https://openrouter.ai/api/v1

Browse available models at openrouter.ai/models.

Architecture

┌─────────────────────────────────────────────────────┐
│                       onit CLI                      │
│                  (argparse + YAML config)           │
└────────────────────────┬────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────┐
│                     OnIt (src/onit.py)              │
│                                                     │
│  ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌────────┐ ┌──────┐ │
│  │ ChatUI  │ │ WebChatUI│ │ Telegram │ │ Viber  │ │ A2A  │ │
│  │(terminal│ │ (Gradio) │ │ Gateway  │ │Gateway │ │Server│ │
│  └────┬────┘ └────┬─────┘ └────┬─────┘ └───┬────┘ └──┬───┘ │
│       └─────────┬─┘            │             │       │
│                 ▼                 ▼                 │
│          client_to_agent()  /  process_task()       │
│                 │                                   │
│                 ▼                                   │
│        MCP Prompt Engineering (FastMCP)             │
│                 │                                   │
│                 ▼                                   │
│         chat() ◄──── Tool Registry                  │
│    (vLLM / OpenRouter)  (auto-discovered)           │
└─────────────────────────────────────────────────────┘
                         │
            ┌────────────┼────────────┐
            ▼            ▼            ▼
     ┌───────────┐ ┌──────────┐ ┌──────────┐
     │  Prompts  │ │  Tools   │ │ External │  ...
     │ MCP Server│ │MCP Server│ │MCP (SSE) │
     └───────────┘ └──────────┘ └──────────┘

Project Structure

onit/
├── configs/
│   └── default.yaml            # Agent configuration
├── pyproject.toml              # Package configuration
├── src/
│   ├── cli.py                  # CLI entry point
│   ├── setup.py                # Setup wizard (onit setup)
│   ├── onit.py                 # Core agent class
│   ├── lib/
│   │   ├── text.py             # Text utilities
│   │   └── tools.py            # MCP tool discovery
│   ├── mcp/
│   │   ├── prompts/            # Prompt engineering (FastMCP)
│   │   └── servers/            # MCP servers (tools, web, bash, filesystem)
│   ├── model/
│   │   └── serving/
│   │       └── chat.py         # LLM interface (vLLM + OpenRouter)
│   ├── ui/
│   │   ├── text.py             # Rich terminal UI
│   │   ├── web.py              # Gradio web UI
│   │   ├── telegram.py         # Telegram bot gateway
│   │   └── viber.py            # Viber bot gateway
│   └── test/                   # Test suite (pytest)

Documentation

Gateway Quick Start — Telegram and Viber bot setup
Testing — Running the test suite
Docker — Docker and Docker Compose setup
Web Authentication — Web UI authentication reference
Web Deployment — Production deployment with HTTP/HTTPS

License

Apache License 2.0. See LICENSE for details.

Name		Name	Last commit message	Last commit date
Latest commit History 135 Commits
.github/workflows		.github/workflows
assets		assets
docs		docs
src		src
.dockerignore		.dockerignore
.gitignore		.gitignore
Dockerfile		Dockerfile
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
README.md		README.md
RELEASE.md		RELEASE.md
docker-compose.yml		docker-compose.yml
pyproject.toml		pyproject.toml

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

OnIt

Getting Started

1. Install

2. Setup

3. Run

Other interfaces

Configuration

Example config (`configs/default.yaml`)

CLI Reference

Features

Interactive Chat

Web UI

MCP Tool Integration

Messaging Gateways

A2A Protocol

Loop Mode

Custom Prompt Templates

Model Serving

Private vLLM

OpenRouter.ai

Architecture

Project Structure

Documentation

License

About

Uh oh!

Releases 7

Packages

Uh oh!

Contributors

Uh oh!

Languages

Folders and files

Latest commit

History

Repository files navigation

OnIt

Getting Started

1. Install

2. Setup

3. Run

Other interfaces

Configuration

Example config (configs/default.yaml)

CLI Reference

Features

Interactive Chat

Web UI

MCP Tool Integration

Messaging Gateways

A2A Protocol

Loop Mode

Custom Prompt Templates

Model Serving

Private vLLM

OpenRouter.ai

Architecture

Project Structure

Documentation

License

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases 7

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Example config (`configs/default.yaml`)

Packages