
pebble
A secure and open protocol for decentralized agent-to-agent communication. Built for speed, scale, extensibility and the AI-native internet. π§πβ¨
Stars: 100

Pebbling is an open-source protocol for agent-to-agent communication, enabling AI agents to collaborate securely using Decentralised Identifiers (DIDs) and mutual TLS (mTLS). It provides a lightweight communication protocol built on JSON-RPC 2.0, ensuring reliable and secure conversations between agents. Pebbling allows agents to exchange messages safely, connect seamlessly regardless of programming language, and communicate quickly and efficiently. It is designed to pave the way for the next generation of collaborative AI systems, promoting secure and effortless communication between agents across different environments.
README:
β¨ Imagine a world where AI agents collaborate effortlessly and securelyβno passport π«, no boundaries π.
Thatβs Pebbling π§.An open source, secured protocol for agent-to-agent communication.
π Powered by Decentralised Identifiers (DIDs) π, secured conversations with mutual TLS (mTLS) π, and a lightweight yet powerful communication protocol built on JSON-RPC 2.0 β‘οΈβPebbling is paving the way for the next generation of collaborative AI systems. ππ€
Pebbling helps your AI agents talk to each other seamlessly:
π Super Secure - Your agents exchange secrets safely (with built-in mTLS)
π§© Plug-and-Play - Just decorate your agent and it's ready to communicate
β‘ Lightning Fast - Quick connections without the weight
π Works Everywhere - Connect any agents, regardless of their programming language
π Reliable Communication - Messages always arrive correctly and in order
# Using pip
pip install pebbling
# Using uv (recommended)
uv add pebbling
The fastest way to get started with Pebbling is using our cookiecutter template:
# Create a new Pebbling project
uv tool run cookiecutter cookiecutter-pebbling/
Follow the interactive prompts:
[1/4] name (pebble_project): my_weather_agent
[2/4] description (): A weather forecasting agent
[3/4] pebbling_email (): [email protected]
[4/4] Select agent_framework
1 - none
2 - agno
3 - crew
4 - langchain
Choose from [1/2/3/4] (1): 2
After project creation:
π Project created successfully!
π§ Welcome to Pebbling β powered by the Pebble CLI.
Next steps:
1οΈβ£ cd 'my_weather_agent'
2οΈβ£ Set it up using uv: π¦
uv sync
3οΈβ£ Run your agent locally: π»
PYTHONPATH=src python3 -m my_weather_agent
or
python3 src/<filename.py>
4οΈβ£ Deploy your agent: π
pebble launch
π€ Selected agent framework: agno
Need help? See README.md for details. β¨
Setup and run your agent:
# Navigate to your project
cd my_weather_agent
# Create virtual environment
uv venv --python 3.12.9
source .venv/bin/activate
# Install dependencies
uv sync
# Run your agent
uv run src/pebble_agent.py
Your agent will start with full Pebbling capabilities:
- β Automatic DID identity generation
- β Security setup with mTLS certificates
- β Agent manifest creation
- β Local server running on http://localhost:8030
- β OpenInference observability integration
π Template Repository: cookiecutter-pebbling
from pebbling import pebblify
@pebblify(name="My Agent", description="A simple agent", version="1.0.0")
def my_agent(message: str) -> str:
return "Hello, Agent!"
# You're now ready to communicate securely between agents!
Pebblify a Agno Agent
from pebbling import pebblify
from agno.agent import Agent
from agno.models.openai import OpenAIChat
@pebblify(name="Agno Agent", description="A helpful assistant", version="1.0.0")
def agno_agent(message: str) -> str:
agent = Agent(
model=OpenAIChat(id="gpt-4o"),
instructions="You are a helpful assistant.",
)
result = agent.run(message)
return result.to_dict()["content"]
# You're now ready to communicate securely between agents!
Open the interactive version of this sequence diagram in MermaidChart |
Open the interactive version of this orchestration diagram in MermaidChart |
Pebbling is tested and integrated with popular agent frameworks:
- β Agno
- π CrewAI (Coming soon)
- π AutoGen (Coming soon)
- π LangChain (Coming soon)
- π LlamaIndex (Coming soon)
Want integration with your favorite framework? Let us know on Discord!
For comprehensive documentation, visit docs.pebbling.ai
Pebbling is thoroughly tested with a test coverage of over 83%:
# Run tests with coverage
make test
make coverage
We welcome contributions! Here's how to get started:
# Clone the repository
git clone https://github.com/Pebbling-ai/pebble.git
cd pebble
# Install development dependencies
uv sync --dev
# Install pre-commit hooks
pre-commit install
# Run tests
make test
Please see our Contributing Guidelines for more details.
For more details about maintainership, including how to become a maintainer, see our MAINTAINERS.md file.
Pebbling is proudly open-source and licensed under the MIT License.
Pebbling is ideal for:
- Multi-Agent Collaboration: Enable efficient, secure teamwork between LLM-driven agents.
- Decentralized Autonomous Systems: Build reliable decentralized AI networks.
- Secure Agent Ecosystems: Create ecosystems where agents from different providers interact seamlessly.
- Distributed AI Workflows: Coordinate agents across distributed computing environments.
We π contributions! Whether you're fixing bugs, improving documentation, or building demos β your contributions make Pebbling better.
- Join our Discord for discussions and support
- Star the repository if you find it useful!
Here's what's next for pebbling:
- [ ] GRPC transport support
- [ ] Integration with Hibiscus (DiD - Decentralized Identifiers, mTLS)
- [ ] Detailed tutorials and guides
- [ ] Expanded multi-framework support
Suggest features or contribute by joining our Discord!
Can Pebble be deployed locally? Yes! Pebble supports local development as well as cloud-based deployments.
Does Pebble support other languages besides Python? Absolutely! Any language that can implement JSON-RPC and mTLS is compatible.
How scalable is Pebble? Pebble's minimal dependencies and protocol simplicity ensure scalability across complex agent ecosystems.
Built with β€οΈ by the Pebbling team from Amsterdam π·.
Weβre excited to see what youβll build with Pebble! Our dream is a world where agents across the internet communicate securely, openly, and effortlessly.
Have questions, ideas, or just want to chat? Join our Discord communityβ weβd love to hear from you! Together, letβs lay the foundation for the next generation of AI agent collaboration.
Happy Pebbling! π§πβ¨
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for pebble
Similar Open Source Tools

pebble
Pebbling is an open-source protocol for agent-to-agent communication, enabling AI agents to collaborate securely using Decentralised Identifiers (DIDs) and mutual TLS (mTLS). It provides a lightweight communication protocol built on JSON-RPC 2.0, ensuring reliable and secure conversations between agents. Pebbling allows agents to exchange messages safely, connect seamlessly regardless of programming language, and communicate quickly and efficiently. It is designed to pave the way for the next generation of collaborative AI systems, promoting secure and effortless communication between agents across different environments.

llama-assistant
Llama Assistant is an AI-powered assistant that helps with daily tasks, such as voice recognition, natural language processing, summarizing text, rephrasing sentences, answering questions, and more. It runs offline on your local machine, ensuring privacy by not sending data to external servers. The project is a work in progress with regular feature additions.

panko-gpt
PankoGPT is an AI companion platform that allows users to easily create and deploy custom AI companions on messaging platforms like WhatsApp, Discord, and Telegram. Users can customize companion behavior, configure settings, and equip companions with various tools without the need for coding. The platform aims to provide contextual understanding and user-friendly interface for creating companions that respond based on context and offer configurable tools for enhanced capabilities. Planned features include expanded functionality, pre-built skills, and optimization for better performance.

pipecat
Pipecat is an open-source framework designed for building generative AI voice bots and multimodal assistants. It provides code building blocks for interacting with AI services, creating low-latency data pipelines, and transporting audio, video, and events over the Internet. Pipecat supports various AI services like speech-to-text, text-to-speech, image generation, and vision models. Users can implement new services and contribute to the framework. Pipecat aims to simplify the development of applications like personal coaches, meeting assistants, customer support bots, and more by providing a complete framework for integrating AI services.

DeepResearch
Tongyi DeepResearch is an agentic large language model with 30.5 billion total parameters, designed for long-horizon, deep information-seeking tasks. It demonstrates state-of-the-art performance across various search benchmarks. The model features a fully automated synthetic data generation pipeline, large-scale continual pre-training on agentic data, end-to-end reinforcement learning, and compatibility with two inference paradigms. Users can download the model directly from HuggingFace or ModelScope. The repository also provides benchmark evaluation scripts and information on the Deep Research Agent Family.

llama-assistant
Llama Assistant is a local AI assistant that respects your privacy. It is an AI-powered assistant that can recognize your voice, process natural language, and perform various actions based on your commands. It can help with tasks like summarizing text, rephrasing sentences, answering questions, writing emails, and more. The assistant runs offline on your local machine, ensuring privacy by not sending data to external servers. It supports voice recognition, natural language processing, and customizable UI with adjustable transparency. The project is a work in progress with new features being added regularly.

glide
Glide is a cloud-native LLM gateway that provides a unified REST API for accessing various large language models (LLMs) from different providers. It handles LLMOps tasks such as model failover, caching, key management, and more, making it easy to integrate LLMs into applications. Glide supports popular LLM providers like OpenAI, Anthropic, Azure OpenAI, AWS Bedrock (Titan), Cohere, Google Gemini, OctoML, and Ollama. It offers high availability, performance, and observability, and provides SDKs for Python and NodeJS to simplify integration.

Windows-Use
Windows-Use is a powerful automation agent that interacts directly with the Windows OS at the GUI layer. It bridges the gap between AI agents and Windows to perform tasks such as opening apps, clicking buttons, typing, executing shell commands, and capturing UI state without relying on traditional computer vision models. It enables any large language model (LLM) to perform computer automation instead of relying on specific models for it.

pyspur
PySpur is a graph-based editor designed for LLM (Large Language Models) workflows. It offers modular building blocks, node-level debugging, and performance evaluation. The tool is easy to hack, supports JSON configs for workflow graphs, and is lightweight with minimal dependencies. Users can quickly set up PySpur by cloning the repository, creating a .env file, starting docker services, and accessing the portal. PySpur can also work with local models served using Ollama, with steps provided for configuration. The roadmap includes features like canvas, async/batch execution, support for Ollama, new nodes, pipeline optimization, templates, code compilation, multimodal support, and more.

bagofwords
Bag of words is an open-source AI platform that helps data teams deploy and manage chat-with-your-data agents in a controlled, reliable, and self-learning environment. It enables users to create charts, tables, and dashboards by chatting with their data, capture AI decisions and user feedback, automatically improve AI quality, integrate with various data sources and APIs, and ensure governance and integrations. The platform supports self-hosting in VPC via VMs, Docker/Compose, or Kubernetes, and offers additional integrations for AI Analyst in Slack, Excel, Google Sheets, and more. Users can start in minutes and scale to org-wide analytics.

Learn_Prompting
Learn Prompting is a platform offering free resources, courses, and webinars to master prompt engineering and generative AI. It provides a Prompt Engineering Guide, courses on Generative AI, workshops, and the HackAPrompt competition. The platform also offers AI Red Teaming and AI Safety courses, research reports on prompting techniques, and welcomes contributions in various forms such as content suggestions, translations, artwork, and typo fixes. Users can locally develop the website using Visual Studio Code, Git, and Node.js, and run it in development mode to preview changes.

Free-GPT4-WEB-API
FreeGPT4-WEB-API is a Python server that allows you to have a self-hosted GPT-4 Unlimited and Free WEB API, via the latest Bing's AI. It uses Flask and GPT4Free libraries. GPT4Free provides an interface to the Bing's GPT-4. The server can be configured by editing the `FreeGPT4_Server.py` file. You can change the server's port, host, and other settings. The only cookie needed for the Bing model is `_U`.

BodhiApp
Bodhi App runs Open Source Large Language Models locally, exposing LLM inference capabilities as OpenAI API compatible REST APIs. It leverages llama.cpp for GGUF format models and huggingface.co ecosystem for model downloads. Users can run fine-tuned models for chat completions, create custom aliases, and convert Huggingface models to GGUF format. The CLI offers commands for environment configuration, model management, pulling files, serving API, and more.

fastserve-ai
FastServe-AI is a machine learning serving tool focused on GenAI & LLMs with simplicity as the top priority. It allows users to easily serve custom models by implementing the 'handle' method for 'FastServe'. The tool provides a FastAPI server for custom models and can be deployed using Lightning AI Studio. Users can install FastServe-AI via pip and run it to serve their own GPT-like LLM models in minutes.

quickvid
QuickVid is an open-source video summarization tool that uses AI to generate summaries of YouTube videos. It is built with Whisper, GPT, LangChain, and Supabase. QuickVid can be used to save time and get the essence of any YouTube video with intelligent summarization.

genius-ai
Genius is a modern Next.js 14 SaaS AI platform that provides a comprehensive folder structure for app development. It offers features like authentication, dashboard management, landing pages, API integration, and more. The platform is built using React JS, Next JS, TypeScript, Tailwind CSS, and integrates with services like Netlify, Prisma, MySQL, and Stripe. Genius enables users to create AI-powered applications with functionalities such as conversation generation, image processing, code generation, and more. It also includes features like Clerk authentication, OpenAI integration, Replicate API usage, Aiven database connectivity, and Stripe API/webhook setup. The platform is fully configurable and provides a seamless development experience for building AI-driven applications.
For similar tasks

pebble
Pebbling is an open-source protocol for agent-to-agent communication, enabling AI agents to collaborate securely using Decentralised Identifiers (DIDs) and mutual TLS (mTLS). It provides a lightweight communication protocol built on JSON-RPC 2.0, ensuring reliable and secure conversations between agents. Pebbling allows agents to exchange messages safely, connect seamlessly regardless of programming language, and communicate quickly and efficiently. It is designed to pave the way for the next generation of collaborative AI systems, promoting secure and effortless communication between agents across different environments.

AgentNetworkProtocol
AgentNetworkProtocol (ANP) aims to define how agents connect with each other, building an open, secure, and efficient collaboration network for billions of intelligent agents. It addresses challenges in interconnectivity, native interfaces, and efficient collaboration by providing protocol layers for identity and encrypted communication, meta-protocol negotiation, and application protocol management. The project is developing an open-source implementation available on GitHub, with a vision to become the HTTP of the Intelligent Agent Internet era and establish ANP as an industry standard through a standardization committee. Contact the author Gaowei Chang via email, Discord, website, or GitHub for contributions or inquiries.

agentgateway
Agentgateway is an open source data plane optimized for agentic AI connectivity within or across any agent framework or environment. It provides drop-in security, observability, and governance for agent-to-agent and agent-to-tool communication, supporting leading interoperable protocols like Agent2Agent (A2A) and Model Context Protocol (MCP). Highly performant, security-first, multi-tenant, dynamic, and supporting legacy API transformation, agentgateway is designed to handle any scale and run anywhere with any agent framework.

flock
Flock is a workflow-based low-code platform that enables rapid development of chatbots, RAG applications, and coordination of multi-agent teams. It offers a flexible, low-code solution for orchestrating collaborative agents, supporting various node types for specific tasks, such as input processing, text generation, knowledge retrieval, tool execution, intent recognition, answer generation, and more. Flock integrates LangChain and LangGraph to provide offline operation capabilities and supports future nodes like Conditional Branch, File Upload, and Parameter Extraction for creating complex workflows. Inspired by StreetLamb, Lobe-chat, Dify, and fastgpt projects, Flock introduces new features and directions while leveraging open-source models and multi-tenancy support.

swarmgo
SwarmGo is a Go package designed to create AI agents capable of interacting, coordinating, and executing tasks. It focuses on lightweight agent coordination and execution, offering powerful primitives like Agents and handoffs. SwarmGo enables building scalable solutions with rich dynamics between tools and networks of agents, all while keeping the learning curve low. It supports features like memory management, streaming support, concurrent agent execution, LLM interface, and structured workflows for organizing and coordinating multiple agents.
For similar jobs

sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.