A Python AI agent platform with CLI and Web UI, multi-provider models, MCP extensions, permission modes, print workflows, and optional desktop installers. README evidence does not establish native DeepSeek Harness support.
DSH integration
Ecosystem-related
Safety audit
Unaudited
Last verified
2026-09-13
License
MIT
01What can it help you accomplish?
Run an AI agent from the terminal or browser
Interactive CLI sessions, a browser-based Web UI, non-interactive print mode, and a shared backend runtime
Developers and power users who want both terminal and browser interfaces on Windows, macOS, or Linux
Use multiple model providers through one agent platform
A multi-provider LLM gateway with Anthropic, OpenAI, Copilot, Codex, and compatible endpoints
Users who need to switch among hosted or compatible model providers
Extend agent workflows with tools and automation
MCP dynamic tools, plugins, hooks, skills, specialized sub-agents, permissions, and cron scheduling
Automation-focused users who need configurable tools and unattended workflows
02How to install into DeepSeek Harness
Prerequisites
- Python >= 3.10
- Windows, macOS, or Linux; Node.js 18+ is needed only for source installation
Installation steps
- 01
Recommended: run `pip install illusion-agent` from PyPI; the README says this does not require Node.js
- 02
For a source install, run `git clone https://github.com/YunTaiHua/illusion-agent.git`, `cd illusion-agent`, then `pip install .`
$ git clone https://github.com/YunTaiHua/illusion-agent.git
- 03
Configure authentication and the working directory with `illusion auth login`, then start an interactive session with `illusion`
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
README documents a standalone terminal and browser AI agent platform, but does not document a native DeepSeek Harness integration or DSH-specific installation path
Terminal and Web UI interfaces
Interactive prompts, print-mode prompts, or browser sessions→Terminal sessions through `illusion` and browser chat through `illusion web`
Multi-agent and MCP extensions
Agent tasks that need specialized sub-agents or additional tools→Specialized agents, MCP dynamic tools, plugins, hooks, and skills
Permission and reasoning controls
Agent requests that need bounded permissions or a selected reasoning effort→Three permission modes with fine-grained rules and low/medium/high/xhigh/max effort levels
04Who is it for? When not to use it?
Good for
- Developers and power users who want both terminal and browser interfaces on Windows, macOS, or Linux
- Users who need to switch among hosted or compatible model providers
- Automation-focused users who need configurable tools and unattended workflows
Not for
- The README requires Python 3.10 or newer; Node.js 18 or newer is required for source installation but not for the PyPI package.
- Print mode is read-only by default, while full_auto can allow file writes and command execution without interactive approval.
- In print mode, the prompt must be the last argument because Typer parses `-p` greedily.
05Compatibility, maintenance and safety notes
- The README requires Python 3.10 or newer; Node.js 18 or newer is required for source installation but not for the PyPI package.
- Print mode is read-only by default, while full_auto can allow file writes and command execution without interactive approval.
- In print mode, the prompt must be the last argument because Typer parses `-p` greedily.
MIT · latest release v0.4.13
06Frequently asked questions
Does IllusionAgent provide a native DeepSeek Harness integration?
The README does not document a native DeepSeek Harness runtime, DSH adapter, or DSH-specific setup command. Treat it as an adjacent AI-agent platform rather than a confirmed native DSH plugin.
Can a DeepSeek Harness user still evaluate IllusionAgent?
Yes, as a separate Python agent platform: install it from PyPI or source, run `illusion auth login`, and use the terminal or `illusion web`. The README does not describe an in-process DSH connection.
What is the smallest installation path?
Use Python 3.10+ and run `pip install illusion-agent`; the README explicitly says the PyPI install does not require Node.js. Source installation requires Node.js 18+.
What should I check before enabling autonomous actions?
Start with the default read-only permission mode. The README also documents a `full_auto` mode that permits file writes and command execution without interactive approval, so review that choice carefully.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-13. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.