Skip to main content

ANIMYST — Breathe Life Into Code. Agent Development Environment for the Terminal.

Project description

◬ ANIMYST

 █████╗ ███╗   ██╗██╗███╗   ███╗██╗   ██╗███████╗████████╗
██╔══██╗████╗  ██║██║████╗ ████║╚██╗ ██╔╝██╔════╝╚══██╔══╝
███████║██╔██╗ ██║██║██╔████╔██║ ╚████╔╝ ███████╗   ██║
██╔══██║██║╚██╗██║██║██║╚██╔╝██║  ╚██╔╝  ╚════██║   ██║
██║  ██║██║ ╚████║██║██║ ╚═╝ ██║   ██║   ███████║   ██║
╚═╝  ╚═╝╚═╝  ╚═══╝╚═╝╚═╝     ╚═╝   ╚═╝   ╚══════╝   ╚═╝

Breathe Life Into Code

Python 3.10+ Textual License: MIT

Manifest agents. Bind MCPs. Ship code. All from your terminal.

animystlab.com


What is Animyst?

Animyst is an agent development environment for the terminal. A cyberpunk TUI for building, configuring, and managing AI agents — not just running them.

Unlike tools that act as session managers for existing coding agents, Animyst lets you define custom agents from scratch — choosing models, attaching MCP servers, writing incantations (system prompts), and composing multi-agent workflows.

Think of it as the difference between Spotify (playing music) and Ableton (creating music).

┌──────────────┬────────────────────────────────┬──────────────────┐
│  REGISTRY    │        CONSOLE                 │   GIT            │
│              │                                │                  │
│ ⚡ Agents    │  animyst › manifest scout       │  ⎇ main          │
│  ● scout     │  [scout] Channeling will...    │  2 files changed │
│  ● coder     │  [scout] Loading incantation   │                  │
│ ◈ MCPs       │  [scout] ⚡ Awakened            │  a3f2d manifest  │
│  ▸ GitHub    │                                │  b1c4e bind mcp  │
│  ▸ Filesystem│                                ├──────────────────┤
│ ▣ Models     │                                │   AGENT MIND     │
│  ▸ Sonnet 4.5│                                │                  │
│  ▸ Opus 4.5  │                                │  AWAKEN scout    │
│              │  animyst › _                   │  MANIFEST coder  │
└──────────────┴────────────────────────────────┴──────────────────┘

Features

⚡ Agent Manifest — Define agents with custom incantations, model selection, temperature, and token limits. All configs stored as JSON in ~/.animyst/.

◈ MCP Binding (coming in v0.2) — Register and manage Model Context Protocol servers (filesystem, GitHub, Slack, custom APIs). Bind them to agents with a keystroke.

⎇ Git Integration — Built-in git panel showing branch, changed files, recent commits. Quick actions for push, PR, and diff without leaving the TUI.

◬ Agent Mind — Real-time feed of all agent operations — manifestations, awakenings, banishments, exports. Your mission control.

⌨ Command Console — Full REPL with commands for managing agents, MCPs, models, and git operations. Keyboard shortcuts included.

🌆 Cyberpunk Theme — Fuchsia-violet, electric cyan, and deep purple on void black. Because dev tools should look as good as they work.

Install

# Clone the repo
git clone https://github.com/CreatorGodMode/animystcli.git
cd animystcli

# Install with pip
pip install -e .

# Run
animyst

Or install directly:

pip install animyst

Quick Start

# Launch animyst
animyst

# Inside the console:
help              # See all commands
manifest          # Manifest a new agent (or Ctrl+N)
bind mcp          # Bind a new MCP server (coming in v0.2)
agents            # List all agents
awaken scout      # Awaken an agent
inspect scout     # View agent configuration
banish scout      # Remove an agent
export scout      # Export agent config as JSON
git status        # Run git commands
status            # System overview

Keyboard Shortcuts

Key Action
Ctrl+N Manifest new agent
Ctrl+G Git status
Ctrl+R Refresh all panels
Ctrl+L Clear console
Ctrl+Q Quit

Architecture

~/.animyst/
├── agents.json    # Agent configurations
├── mcps.json      # Bound MCP server registry
└── models.json    # Available model definitions

Animyst uses a file-based config system. Agent configs are portable JSON files that can be version-controlled, shared, and composed into pipelines.

Agent Config Format

{
  "name": "scout",
  "model": "claude-sonnet-4-5-20250929",
  "incantation": "You are a research agent that finds and summarizes information.",
  "mcps": ["web-search", "filesystem"],
  "temperature": 0.7,
  "max_tokens": 4096,
  "status": "dormant"
}

Language

Animyst uses intentional language to distinguish itself:

Generic Animyst
Create agent Manifest agent
Running Awakened
Idle Dormant
Delete Banish
System prompt Incantation
Register MCP Bind MCP

Tech Stack

  • Textual — Python TUI framework with CSS-like styling
  • Rich — Terminal formatting and markup
  • GitPython — Git integration
  • Anthropic SDK — Claude model integration
  • OpenAI SDK — GPT model integration
  • Google GenAI SDK — Gemini model integration
  • Python 3.10+ — Async-native, type-hinted

Roadmap

  • Live agent execution with streaming output
  • MCP server connection & health checking
  • Multi-agent pipeline composer
  • Agent conversation history
  • Akira-style telemetry HUD in Agent Mind panel
  • Plugin system for custom panels
  • Remote agent deployment
  • Cost tracking per agent run
  • Import/export agent packs

License

MIT


Built with ◬ by Abhi — CEO @ Famished.ai Animystlab.com

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

animyst-0.1.0.tar.gz (32.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

animyst-0.1.0-py3-none-any.whl (18.1 kB view details)

Uploaded Python 3

File details

Details for the file animyst-0.1.0.tar.gz.

File metadata

  • Download URL: animyst-0.1.0.tar.gz
  • Upload date:
  • Size: 32.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for animyst-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b374221999f920c7d208fa37682ba403aa411809ea658680c9ba7f4a3b02669a
MD5 ea92fe9be5320dffd96e9f4f98cd8a3b
BLAKE2b-256 65a3c3e9ac5019dc1620958f219e8f77d87ee9ee0c577fdce8893de825281939

See more details on using hashes here.

File details

Details for the file animyst-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: animyst-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 18.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for animyst-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5a869fc9fac85a4170bd9686abd4d713f649498b168114f7c902992bc05a0a4b
MD5 5c9247bad60062d4d5551dd16a08161b
BLAKE2b-256 bbbe65b38233d59c33a4e5ad896867d2881b7840723d688d995ed12da73708c1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page