Your all-in-one SDK to automate multi-agent tasks
Project description
🌟 AmbientAGI: Build Token-Rewarded AI Agents
AmbientAGI merges AI orchestration with crypto token rewards, enabling users to:
- 🚀 Create and deploy specialized AI agents in a multi-tenant environment.
- 💰 Mint tokens on major blockchains (Solana or Ethereum) to reward agent activity.
- 🎨 Generate 3D/visual media for each agent, turning them into branded, interactive personas.
- 🏆 Earn from agent usage, verified on-chain to ensure transparency and authenticity.
- 🔮 Expand into a broad set of real-world and crypto-focused use cases: job search assistance, analyzing trending coins, whale-tracking, yield farming alerts, and more.
✨ Features
- 🏗️ Multi-Tenant Orchestrator: Host and manage user agents with unified logs and a centralized database.
- 🐍 Python Library: Develop custom agent behaviors with built-in schedulers and blockchain hooks.
- 🪙 Token Minting: Reward users by minting tokens on Solana or Ethereum for agent usage.
- 🖼️ 3D/Visual Media Integration: Generate and mint unique 3D/video representations of agents as NFTs.
- 🔗 Crypto Integration: Leverage DeFi, staking, and wallet integration for a seamless crypto experience.
1. 🏢 Multi-Tenant Orchestrator
🛠️ Architecture
- Central Orchestrator: Manages all agents and ensures task scheduling and execution.
- Database: Stores agent configurations (e.g., name, wallet address, schedule, commands).
- Scheduler: Handles task scheduling using tools like APScheduler or Celery.
- On-Chain Usage: Logs agent activities on IPFS and references them in blockchain contracts for transparency.
⚡️ Why AmbientAGI?
- Real-world agent orchestration: Async schedulers, agent state, and custom prompts.
- Multi-agent setups: Plug-and-play modular agents (triage, trading, data fetchers, etc.).
- Web UI: Run agents visually using a Gradio-based interface with streaming feedback.
- Social + On-Chain Output: Agents that tweet, message, browse, or mint tokens—all from Python.
🧱 Core Features
| Feature | Description |
|---|---|
| Agent SDK | AmbientAgentService for creating and managing agents via Python |
| Async Web & Social Bots | Telegram, Twitter, Browser, Email integration |
| Scheduler Support | Schedule agent tasks using APScheduler |
| Token Minting | Mint ETH/SOL tokens tied to agent usage |
| NFT Media Hooks | Attach 3D/video/NFT identity to agents |
| WebUI | Control and visualize browser agents from a Gradio dashboard |
💬 Agent Types
| Type | Description |
|---|---|
| BrowserAgent | Controls a headless browser via Playwright |
| TwitterAgent | Tweets, replies, uploads media |
| TelegramAgent | Posts in groups/channels, responds to mentions |
| FirecrawlAgent | Scrapes and crawls web content |
| EmailAgent | Sends messages via Gmail/SMTP |
| BlockchainAgent | Deploys tokens and interacts with Ethereum/Solana |
Visit https://github.com/AmbientAGI/ambientagi on how to use it with examples.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ambientagi-0.2.0.tar.gz
(3.2 MB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ambientagi-0.2.0.tar.gz.
File metadata
- Download URL: ambientagi-0.2.0.tar.gz
- Upload date:
- Size: 3.2 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.22
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6bb3d88dbf3e4ef5a362c9761481ca1b382b0d4a751137f71330353749c5c5fa
|
|
| MD5 |
1f24844b5d9a9c7cbda2621616c725bd
|
|
| BLAKE2b-256 |
3f1ce1e11e478856e5df95706f76e0f115cf43a7d8a6f30fd77394e4f8c9de3a
|
File details
Details for the file ambientagi-0.2.0-py3-none-any.whl.
File metadata
- Download URL: ambientagi-0.2.0-py3-none-any.whl
- Upload date:
- Size: 3.6 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.22
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
34215d7e54cbb4a1b9d721f3d51f9359c8238439b445bc5ad0208b3c182e45d6
|
|
| MD5 |
2aeb75a1c156088675b425df04ab50d2
|
|
| BLAKE2b-256 |
961f4fe7e531d4a98cc932231c3e9624556cd572b580da753a738c8b5ccb9a32
|