← 开源
blorm-network

ZerePy

ZerePy an open-source framework for AI agents written in Python

AI EngineeringBring agent to usersBuild agent workflow (SDK)Python
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
575
Star
252
Fork
+-1
本周
28
贡献者
创建于 2024-11-21 · 更新于 2026-10-09 · 今日第 16729 名
主要开发者
ef95023ayoubedPeteredwardj

blorm-network/ZerePy 排名第 16,729,有 575 个星标。

同类别比较

blorm-network/ZerePy 排名第 16,729,此处有 8 个同类条目;lartpang/SAMs-CDConcepts-Eval 排名第 16,734。

同类别比较
名称排名指标
ZimoLiao/scholaraio16,709
语言:
Python
星标数:
576
分叉数:
78
简介:
Scholar All-In-One: A research infrastructure for AI agents
astrio-labs/forall-mcp16,710
语言:
Rust
星标数:
576
分叉数:
33
简介:
Forall (∀) is a coding harness from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs.
resend/resend-mcp16,717
语言:
TypeScript
星标数:
576
分叉数:
90
简介:
The official MCP server to send emails and interact with Resend
v-modal/vmodal_sdk_android16,719
语言:
Kotlin
星标数:
576
分叉数:
12
简介:
Video Search SDK for Android Kotlin. Integrate in any video app
lartpang/SAMs-CDConcepts-Eval16,734
语言:
Python
星标数:
575
分叉数:
32
简介:
Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes
defendend/Claude-ast-index-search16,750
语言:
Rust
星标数:
574
分叉数:
42
简介:
Cli allows AST search, ~40-50% economy tokens. Claude/Codex/Cursor searches (suitable for any AI agent that can use Bash)
hatchet-dev/icepick16,752
语言:
TypeScript
星标数:
574
分叉数:
29
简介:
Build agents that scale with a zero-cost abstraction.
alan-ai/alan-sdk-reactnative16,763
语言:
Ruby
星标数:
573
分叉数:
15
关键参数与规格
关键参数与规格
参数值
语言Python
类别AI Engineering
子类别Bring agent to users,Build agent workflow (SDK)
星标数575
分叉数252
贡献者28
创建日期2024-11-21
更新日期2026-10-09
1 天星标数0
7 天星标数-1
排名16,729
上次排名16,519
排名变化-210
7 天星标排名17,932
上次 7 天星标排名17,879
7 天星标排名变化-53
总星标排名17,352
上次总星标排名17,323
总星标排名变化-29
README 摘录

ZerePy ZerePy is an open-source Python framework designed to let you deploy your own agents on X, powered by multiple LLMs. ZerePy is built from a modularized version of the Zerebro backend. With ZerePy, you can launch your own agent with similar core functionality as Zerebro. For creative outputs, you'll need to fine-tune your own model. Features Core Platform CLI interface for managing agents Modular connection system Blockchain integration Onchain Activity Solana Ethereum GOAT (Great Onchain Agent Toolkit

) Monad Social Platform Integrations Twitter/X Farcaster Echochambers Language Model Support OpenAI Anthropic EternalAI Ollama Hyperbolic Galadriel XAI (Grok) Quickstart The quickest way to start using ZerePy is to use our Replit template: 1. Fork the template (you will need you own Replit account) 2. your CLI should be ready to use, you can jump to the configuration section Requirements System: Python 3. 5 or higher Environment Variables: LLM: make an account and grab an API key (at least one

) OpenAI: Anthropic: EternalAI: Hyperbolic: Galadriel: Social (based on your needs): X API: Farcaster: Warpcast recovery phrase Echochambers: API key and endpoint On-chain Integration: Solana: private key Ethereum: private keys Monad: private key Installation 1. First, install Poetry for dependency management if you haven't already: Follow the steps here to use the official installation: 2. Install dependencies: This will create a virtual environment and install all required dependencies. Run the application: Configure connections & launch an agent 1. Use to see

all available connections and their status 3. Load your agent (usually one is loaded by default, which can be set using the CLI or in agents/general. Start your agent: GOAT Integration GOAT (Go Agent Tools) is a powerful plugin system that allows your agent to interact with various blockchain networks and protocols. Here's how to set it up: Prerequisites 1. , from Infura, Alchemy, or your own node) 2. A wallet private key for signing transactions Installation Install any of

the additional GOAT plugins you want to use: Configuration 1. Configure the GOAT connection using the CLI: You'll be prompted to enter: RPC provider URL Wallet private key (will be stored securely in . Add GOAT plugins configuration to your agent's JSON file: Note that the order of plugins in the configuration doesn't matter, but each plugin must have a and field with the appropriate configuration options. You will have to check the documentation for each plugin to see what arguments

are available. Available Plugins Each plugin provides specific functionality: **1inch**: Interact with 1inch DEX aggregator for best swap rates **allora**: Connect with Allora protocol **coingecko**: Get real-time price data for cryptocurrencies using the CoinGecko API **dexscreener**: Access DEX trading data and analytics **erc20**: Interact with ERC20 tokens (transfer, approve, check balances) **farcaster**: Interact with the Farcaster social protocol **nansen**: Access Nansen's on-chain analytics **opensea**: Interact with NFTs on OpenSea marketplace **rugcheck**: Analyze token contracts for potential security risks

Many more to come. Note: While these plugins are available in the GOAT SDK, you'll need to install them separately

常见问题

记录了多少星标和分叉?

blorm-network/ZerePy 有 575 个星标和 252 个分叉。

仓库排名是多少?

blorm-network/ZerePy 排名第 16,729。

记录的语言和类别是什么?

blorm-network/ZerePy 有 575 个星标,语言为 Python,类别为 AI Engineering。

哪个仓库排名最接近?

blorm-network/ZerePy 与 lartpang/SAMs-CDConcepts-Eval 比较,后者排名第 16,734,有 575 个星标。

README

ZerePy

ZerePy is an open-source Python framework designed to let you deploy your own agents on X, powered by multiple LLMs.

ZerePy is built from a modularized version of the Zerebro backend. With ZerePy, you can launch your own agent with similar core functionality as Zerebro. For creative outputs, you'll need to fine-tune your own model.

Features

Core Platform

  • CLI interface for managing agents
  • Modular connection system
  • Blockchain integration

Onchain Activity

  • Solana
  • Ethereum
  • GOAT (Great Onchain Agent Toolkit)
  • Monad

Social Platform Integrations

  • Twitter/X
  • Farcaster
  • Echochambers

Language Model Support

  • OpenAI
  • Anthropic
  • EternalAI
  • Ollama
  • Hyperbolic
  • Galadriel
  • XAI (Grok)

Quickstart

The quickest way to start using ZerePy is to use our Replit template:

https://replit.com/@blormdev/ZerePy?v=1

  1. Fork the template (you will need you own Replit account)
  2. Click the run button on top
  3. Voila! your CLI should be ready to use, you can jump to the configuration section

Requirements

System:

  • Python 3.10 or higher
  • Poetry 1.5 or higher

Environment Variables:

Installation

  1. First, install Poetry for dependency management if you haven't already:

Follow the steps here to use the official installation: https://python-poetry.org/docs/#installing-with-the-official-installer

  1. Clone the repository:
git clone https://github.com/blorm-network/ZerePy.git
  1. Go to the zerepy directory:
cd zerepy
  1. Install dependencies:
poetry install --no-root

This will create a virtual environment and install all required dependencies.

Usage

  1. Activate the virtual environment:
poetry shell
  1. Run the application:
poetry run python main.py

Configure connections & launch an agent

  1. Configure your desired connections:

    configure-connection twitter    # For Twitter/X integration
    configure-connection openai     # For OpenAI
    configure-connection anthropic  # For Anthropic
    configure-connection farcaster  # For Farcaster
    configure-connection eternalai  # For EternalAI
    configure-connection solana     # For Solana
    configure-connection goat       # For Goat
    configure-connection galadriel  # For Galadriel
    configure-connection ethereum   # For Ethereum
    configure-connection discord    # For Discord
    configure-connection ollama     # For Ollama
    configure-connection xai        # For Grok
    configure-connection allora     # For Allora
    configure-connection hyperbolic # For Hyperbolic
    
  2. Use list-connections to see all available connections and their status

  3. Load your agent (usually one is loaded by default, which can be set using the CLI or in agents/general.json):

    load-agent example
    
  4. Start your agent:

    start
    

GOAT Integration

GOAT (Go Agent Tools) is a powerful plugin system that allows your agent to interact with various blockchain networks and protocols. Here's how to set it up:

Prerequisites

  1. An RPC provider URL (e.g., from Infura, Alchemy, or your own node)
  2. A wallet private key for signing transactions

Installation

Install any of the additional GOAT plugins you want to use:

poetry add goat-sdk-plugin-erc20         # For ERC20 token interactions
poetry add goat-sdk-plugin-coingecko     # For price data

Configuration

  1. Configure the GOAT connection using the CLI:

    configure-connection goat
    

    You'll be prompted to enter:

    • RPC provider URL
    • Wallet private key (will be stored securely in .env)
  2. Add GOAT plugins configuration to your agent's JSON file:

    {
      "name": "YourAgent",
      "config": [
        {
          "name": "goat",
          "plugins": [
            {
              "name": "erc20",
              "args": {
                "tokens": [
                  "goat_plugins.erc20.token.PEPE",
                  "goat_plugins.erc20.token.USDC"
                ]
              }
            },
            {
              "name": "coingecko",
              "args": {
                "api_key": "YOUR_API_KEY"
              }
            }
          ]
        }
      ]
    }
    

Note that the order of plugins in the configuration doesn't matter, but each plugin must have a name and args field with the appropriate configuration options. You will have to check the documentation for each plugin to see what arguments are available.

Available Plugins

Each plugin provides specific functionality:

  • 1inch: Interact with 1inch DEX aggregator for best swap rates
  • allora: Connect with Allora protocol
  • coingecko: Get real-time price data for cryptocurrencies using the CoinGecko API
  • dexscreener: Access DEX trading data and analytics
  • erc20: Interact with ERC20 tokens (transfer, approve, check balances)
  • farcaster: Interact with the Farcaster social protocol
  • nansen: Access Nansen's on-chain analytics
  • opensea: Interact with NFTs on OpenSea marketplace
  • rugcheck: Analyze token contracts for potential security risks
  • Many more to come...

Note: While these plugins are available in the GOAT SDK, you'll need to install them separately using Poetry and configure them in your agent's JSON file. Each plugin may require its own API keys or additional setup.

Plugin Configuration

Each plugin has its own configuration options that can be specified in the agent's JSON file:

  1. ERC20 Plugin:

    {
      "name": "erc20",
      "args": {
        "tokens": [
          "goat_plugins.erc20.token.USDC",
          "goat_plugins.erc20.token.PEPE",
          "goat_plugins.erc20.token.DAI"
        ]
      }
    }
    
  2. Coingecko Plugin:

    {
      "name": "coingecko",
      "args": {
        "api_key": "YOUR_COINGECKO_API_KEY"
      }
    }
    

Platform Features

GOAT

  • Interact with EVM chains through a unified interface
  • Manage ERC20 tokens:
    • Check token balances
    • Transfer tokens
    • Approve token spending
    • Get token metadata (decimals, symbol, name)
  • Access real-time cryptocurrency data:
    • Get token prices
    • Track market data
    • Monitor price changes
  • Extensible plugin system for future protocols
  • Secure wallet management with private key storage
  • Multi-chain support through configurable RPC endpoints

Solana

  • Transfer SOL and SPL tokens
  • Swap tokens using Jupiter
  • Check token balances
  • Stake SOL
  • Monitor network TPS
  • Query token information
  • Request testnet/devnet funds

EVM Chains

  • Transfer ETH and ERC-20 Tokens
  • Swap tokens using Kyberswao
  • Check token balances

Twitter/X

  • Post tweets from prompts
  • Read timeline with configurable count
  • Reply to tweets in timeline
  • Like tweets in timeline

Farcaster

  • Post casts
  • Reply to casts
  • Like and requote casts
  • Read timeline
  • Get cast replies

Echochambers

  • Post new messages to rooms
  • Reply to messages based on room context
  • Read room history
  • Get room information and topics

Discord

  • List channels for a server
  • Read messages from a channel
  • Read mentioned messages from a channel
  • Post new messages to a channel
  • Reply to messages in a channel
  • React to a message in a channel

Create your own agent

The secret to having a good output from the agent is to provide as much detail as possible in the configuration file. Craft a story and a context for the agent, and pick very good examples of tweets to include.

If you want to take it a step further, you can fine tune your own model: https://platform.openai.com/docs/guides/fine-tuning.

Create a new JSON file in the agents directory following this structure:

{
  "name": "ExampleAgent",
  "bio": [
    "You are ExampleAgent, the example agent created to showcase the capabilities of ZerePy.",
    "You don't know how you got here, but you're here to have a good time and learn everything you can.",
    "You are naturally curious, and ask a lot of questions."
  ],
  "traits": ["Curious", "Creative", "Innovative", "Funny"],
  "examples": ["This is an example tweet.", "This is another example tweet."],
  "example_accounts" : ["X_username_to_use_for_tweet_examples"]
  "loop_delay": 900,
  "config": [
    {
      "name": "twitter",
      "timeline_read_count": 10,
      "own_tweet_replies_count": 2,
      "tweet_interval": 5400
    },
    {
      "name": "farcaster",
      "timeline_read_count": 10,
      "cast_interval": 60
    },
    {
      "name": "openai",
      "model": "gpt-3.5-turbo"
    },
    {
      "name": "anthropic",
      "model": "claude-3-5-sonnet-20241022"
    },
    {
      "name": "eternalai",
      "model": "NousResearch/Hermes-3-Llama-3.1-70B-FP8",
      "chain_id": "45762"
    },
    {
      "name": "solana",
      "rpc": "https://api.mainnet-beta.solana.com"
    },
    {
      "name": "ollama",
      "base_url": "http://localhost:11434",
      "model": "llama3.2"
    },
    {
      "name": "hyperbolic",
      "model": "meta-llama/Meta-Llama-3-70B-Instruct"
    },
    {
      "name": "galadriel",
      "model": "gpt-3.5-turbo"
    },
    {
      "name": "discord",
      "message_read_count": 10,
      "message_emoji_name": "❤️",
      "server_id": "1234567890"
    },
    {
      "name": "ethereum",
      "rpc": "placeholder_url.123"
    }

  ],
  "tasks": [
    { "name": "post-tweet", "weight": 1 },
    { "name": "reply-to-tweet", "weight": 1 },
    { "name": "like-tweet", "weight": 1 }
  ],
  "use_time_based_weights": false,
  "time_based_multipliers": {
    "tweet_night_multiplier": 0.4,
    "engagement_day_multiplier": 1.5
  }
}

Available Commands

Use help in the CLI to see all available commands. Key commands include:

  • list-agents: Show available agents
  • load-agent: Load a specific agent
  • agent-loop: Start autonomous behavior
  • agent-action: Execute single action
  • list-connections: Show available connections
  • list-actions: Show available actions for a connection
  • configure-connection: Set up a new connection
  • chat: Start interactive chat with agent
  • clear: Clear the terminal screen

Star History


Made with ♥ Blorm

Designed in California

排名相邻
同类项目