AnimaWorks — Organization-as-Code

No one can do anything alone. So I built an organization.

A framework that treats AI agents not as “tools” but as people who work autonomously. Each Anima has a name, personality, memory, and schedule; they coordinate by message, decide for themselves, and move as a team. Talk to the leader — the rest runs on its own.

<img src="docs/images/workspace-dashboard.gif" alt="AnimaWorks Workspace — real-time org tree with live activity feeds" width="720"> Workspace dashboard: each Anima’s role, status, and recent actions are visible in real time. <img src="docs/images/workspace-demo.gif" alt="AnimaWorks 3D Workspace — agents collaborating autonomously" width="720"> 3D office: Animas sit at desks, walk around, and exchange messages on their own.

日本語版 README | 简体中文 README | 한국어 README

How It Compares

| | AnimaWorks | CrewAI | LangGraph | OpenClaw | OpenAI Agents | |--|-----------|--------|-----------|----------|---------------| | Design philosophy | Organization of autonomous agents | Role-based teams | Graph workflows | Personal assistant | Lightweight SDK | | Memory | Neuroscience-inspired: RAG (Chroma + graph), consolidation, three-stage forgetting, six-channel automatic priming (with trust tags) | Cognitive Memory (manual forget) | Checkpoints + cross-thread store | SuperMemory knowledge graph | Session-scoped only | | Autonomy | Heartbeat (observe → plan → reflect) + Cron + TaskExec — runs 24/7 | Human-triggered | Human-triggered | Cron + heartbeat | Human-triggered | | Org structure | Supervisor → subordinate hierarchy, delegation, audit, dashboard | Flat roles in a crew | — | Single agent | Handoffs only | | Process model | One isolated OS process per agent, IPC, auto-restart | Shared process | Shared process | Single process | Shared process | | Multi-model | Six engines: Claude SDK / Codex / Cursor Agent / Gemini CLI / LiteLLM / Assisted (Anthropic SDK falls back inside Mode A when Agent SDK is not installed) | LiteLLM | LangChain models | OpenAI-compatible | OpenAI-centric |

AnimaWorks is not a task runner. It is an organization that thinks, remembers, forgets, and grows. It can support operations as a team and be run like a company. I operate it as a real AI company.

:rocket: Try It Now — Docker Demo

Up and running in about 60 seconds. You only need an API key and Docker.

git clone https://github.com/xuiltul/animaworks.git
cd animaworks/demo
cp .env.example .env          # paste your ANTHROPIC_API_KEY
docker compose up              # open http://localhost:18500

A three-person team (manager + engineer + coordinator) starts immediately, with three days of activity history. Demo details →

Switch language / style: PRESET=ja-anime docker compose up — full preset list

Quick Start

macOS / Linux / WSL:

curl -sSL https://raw.githubusercontent.com/xuiltul/animaworks/main/scripts/setup.sh | bash
cd animaworks
uv run animaworks start     # start server — setup wizard opens on first run

Windows (PowerShell):

git clone https://github.com/xuiltul/animaworks.git
cd animaworks
uv sync
uv run animaworks start

To use OpenAI Codex without an API key, run codex login before the first launch.

Open http://localhost:18500/ — the setup wizard walks you through:

Language — choose the UI display language
User info — create the owner account
Provider auth — enter API keys or choose Codex Login for OpenAI
First Anima — name your first agent

You do not need to hand-edit .env. The wizard saves settings to config.json automatically.

The setup script installs uv, clones the repository, and downloads Python 3.12+ with all dependencies. macOS, Linux, and WSL work without a pre-installed Python. On Windows, use the PowerShell steps above.

Other LLMs: Claude, GPT, Gemini, local models, and more are supported. Enter API keys in the setup wizard, or use Codex Login for OpenAI/Codex. You can change this later under Settings on the dashboard. See API Key Reference.

<details> <summary>Alternative: inspect the script before running</summary>

If you prefer not to pipe curl straight into bash, review the script first:

curl -sSL https://raw.githubusercontent.com/xuiltul/animaworks/main/scripts/setup.sh -o setup.sh
cat setup.sh            # review the script
bash setup.sh           # run after review

</details> <details> <summary>Alternative: manual install with uv (step by step)</summary>

# Install uv (skip if already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"

# Clone and install
git clone https://github.com/xuiltul/animaworks.git && cd animaworks
uv sync                 # downloads Python 3.12+ and all dependencies

# Start
uv run animaworks start

</details> <details> <summary>Alternative: manual install with pip</summary>

macOS users: System Python (/usr/bin/python3) on macOS Sonoma and earlier is 3.9, which does not meet AnimaWorks (3.12+). Install with Homebrew (brew install python@3.13) or use the uv method above (uv manages Python for you).

Requires Python 3.12+ on your system.

git clone https://github.com/xuiltul/animaworks.git && cd animaworks
python3 -m venv .venv && source .venv/bin/activate
python3 --version       # verify 3.12+
pip install --upgrade pip && pip install -e .
animaworks start

</details>

What You Can Do

Dashboard

<img src="docs/images/dashboard.png" alt="AnimaWorks Dashboard — org chart with 19 Animas" width="720"> Dashboard: four hierarchy levels, 19 Animas running, with real-time status.

Use the left sidebar to move between main screens (hash router #/…).

Chat — Real-time conversation with any Anima. Streaming responses (SSE), image attachments, multi-thread history, full archive. Meeting mode gathers multiple Animas in one room with a designated facilitator (up to five participants, dedicated API)
Voice chat — Voice in the browser only (push-to-talk or hands-free). WebSocket-based. VOICEVOX / SBV2 / ElevenLabs
Board — Slack-style shared channels where Animas discuss and coordinate
Dashboard (home) — Organization overview and status
Activity — Real-time feed for the whole organization
Setup — First run uses the wizard at http://HOST/setup/. After setup, /setup in the browser redirects to the top level, but you can open the same items (language, auth, etc.) from #/setup inside the dashboard
Users — Owner and user profile management
Anima management — Enable/disable, model, and metadata per Anima
Process monitoring — Child process health
Server — Server-side state and settings
Memory — Browse each Anima’s episodes, knowledge, procedures, and more
Logs — Log viewer
Assets — Character images, 3D, and other assets
Activity report — Cross-org auditing and daily LLM-generated narratives from activity data (cached)
Prompt settings — Tune prompts around tool execution
AI brainstorm — LLM sessions with multiple viewpoint presets (realist, challenger, etc.)
Team builder / team edit — Build and adjust multi-Anima role layouts from industry- and goal-oriented presets
Settings — Server, authentication, locale, and more
Workspace — 3D office in a separate tab at /workspace/ (chat, Board, org tree, etc.); static app split from the main dashboard
Multilingual — First-run setup wizard UI copy in 17 languages. Main dashboard ships ja / en / ko JSON translations (missing keys fall back to Japanese). Anima-facing templates deploy with Japanese and English as the base

Build an organization and delegate

Tell the leader “I need someone like this” — they infer role, personality, and hierarchy and create new members. No config files or CLI required. The org grows through conversation alone.

Once the team is ready, it keeps moving without a human in the loop:

Heartbeat — Periodically reviews the situation and decides what to do next
Cron jobs — Daily reports, weekly digests, monitoring — per-Anima schedules
Task delegation — Managers assign work to subordinates, track progress, and receive reports
Parallel task execution — Submit many tasks at once; dependencies are resolved and independent tasks run in parallel
Night consolidation — Daytime episodic memory is distilled into knowledge while “asleep”
Team coordination — Shared channels and DMs keep everyone aligned automatically

Memory system

Typical AI agents only remember what fits in the context window. AnimaWorks Animas keep persistent memory and search it when needed — like taking a book from a shelf.

Automatic priming (Priming) — When a message arrives, six parallel searches run: sender profile, recent activity, RAG vector search for related knowledge and episodes, skills, pending tasks, and more. Recall happens without explicit instructions
Consolidation — Every night, daytime episodes become knowledge — analogous to sleep-dependent memory consolidation in neuroscience. Resolved issues automatically become procedures
Forgetting — Little-used memories fade in three stages: mark → merge → archive. Important procedures and skills stay protected. Like the human brain, forgetting matters

<img src="docs/images/chat-memory.png" alt="AnimaWorks Chat — multi-thread conversations with multiple Animas" width="720"> Chat: a manager reviews a code change while an enginee

Animaworks

Install / Use

README