{"id":35824640,"url":"https://github.com/solacelabs/solace-agent-mesh","last_synced_at":"2026-04-28T15:00:59.584Z","repository":{"id":271929389,"uuid":"914964527","full_name":"SolaceLabs/solace-agent-mesh","owner":"SolaceLabs","description":"An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.","archived":false,"fork":false,"pushed_at":"2026-04-27T15:57:45.000Z","size":30513,"stargazers_count":3330,"open_issues_count":69,"forks_count":214,"subscribers_count":21,"default_branch":"main","last_synced_at":"2026-04-27T16:18:06.146Z","etag":null,"topics":["a2a","agentframework","agentic","agentic-ai","agentic-framework","agentic-workflow","agenticai","agents","ai","ai-agents","aiagentframework","aiframework","enterprise","event-driven-architecture","framework","mcp","multi-agent","multi-agent-systems","multiagent","rag"],"latest_commit_sha":null,"homepage":"https://solacelabs.github.io/solace-agent-mesh/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SolaceLabs.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-10T17:11:47.000Z","updated_at":"2026-04-27T15:26:09.000Z","dependencies_parsed_at":"2025-01-10T20:30:23.083Z","dependency_job_id":"82c666bf-0d5d-4cf6-9f50-068982c07341","html_url":"https://github.com/SolaceLabs/solace-agent-mesh","commit_stats":null,"previous_names":["solacedev/solace-agent-mesh","solacelabs/solace-agent-mesh"],"tags_count":495,"template":false,"template_full_name":null,"purl":"pkg:github/SolaceLabs/solace-agent-mesh","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolaceLabs%2Fsolace-agent-mesh","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolaceLabs%2Fsolace-agent-mesh/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolaceLabs%2Fsolace-agent-mesh/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolaceLabs%2Fsolace-agent-mesh/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SolaceLabs","download_url":"https://codeload.github.com/SolaceLabs/solace-agent-mesh/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SolaceLabs%2Fsolace-agent-mesh/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32385943,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T14:34:11.604Z","status":"ssl_error","status_checked_at":"2026-04-28T14:32:37.009Z","response_time":56,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["a2a","agentframework","agentic","agentic-ai","agentic-framework","agentic-workflow","agenticai","agents","ai","ai-agents","aiagentframework","aiframework","enterprise","event-driven-architecture","framework","mcp","multi-agent","multi-agent-systems","multiagent","rag"],"created_at":"2026-01-07T19:13:28.546Z","updated_at":"2026-04-28T15:00:59.571Z","avatar_url":"https://github.com/SolaceLabs.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./docs/static/img/logo.png\" alt=\"Solace Agent Mesh Logo\" width=\"100\"/\u003e\n\u003c/p\u003e\n\u003ch2 align=\"center\"\u003e\n  Solace Agent Mesh\n\u003c/h2\u003e\n\u003ch3 align=\"center\"\u003eOpen-source framework for building event driven multi-agent AI systems\u003c/h3\u003e\n\u003ch5 align=\"center\"\u003eStar ⭐️ this repo to stay updated as we ship new features and improvements.\u003c/h5\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/SolaceLabs/solace-agent-mesh/blob/main/LICENSE\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/license/SolaceLabs/solace-agent-mesh\" alt=\"License\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/solace-agent-mesh\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/v/solace-agent-mesh.svg\" alt=\"PyPI - Version\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/solace-agent-mesh\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/pyversions/solace-agent-mesh.svg\" alt=\"PyPI - Python Version\"\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/solace-agent-mesh\"\u003e\n      \u003cimg alt=\"PyPI - Downloads\" src=\"https://img.shields.io/pypi/dm/solace-agent-mesh?color=00C895\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#-key-features\"\u003eKey Features\u003c/a\u003e •\n  \u003ca href=\"#-quick-start-5-minutes\"\u003eQuickstart\u003c/a\u003e •\n  \u003ca href=\"#️-next-steps\"\u003eNext Steps\u003c/a\u003e •\n  \u003ca href=\"https://solacelabs.github.io/solace-agent-mesh/\"\u003eDocs\u003c/a\u003e\n\u003c/p\u003e\n\n\n---\n\n**Solace Agent Mesh** is a framework that supports building AI applications where multiple specialized AI agents work together to solve complex problems. It uses the event messaging of [Solace Platform](https://solace.com) for true scalability and reliability.\n\nWith Solace Agent Mesh (SAM), you can create teams of AI agents, each having distinct skills and access to specific tools. For example, you could have a Database Agent that can make SQL queries to fetch data or a MultiModal Agent that can help create images, audio files and reports.\n\nThe framework handles the communication between agents automatically, so you can focus on building great AI experiences.\n\nSAM creates a standardized communication layer where AI agents can:\n* Delegate tasks to peer agents\n* Share data and artifacts\n* Connect with diverse user interfaces and external systems\n* Execute multi-step workflows with minimal coupling\n\nSAM is built on top of the Solace AI Connector (SAC) which allows Solace Platform Event Brokers to connect to AI models and services and Google's Agent Development Kit (ADK) for AI logic and tool integrations.\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"docs/static/img/Solace_AI_Framework_With_Broker.png\" width=\"640\" alt=\"SAM Architecture Diagram\" /\u003e\n\u003c/p\u003e\n\n\nThe result? A fully asynchronous, event-driven and decoupled AI agent architecture ready for production deployment. It is robust, reliable and easy to maintain. \n\n\n---\n\n## 🔑 Key Features \n- **[Multi-Agent Event-Driven Architecture](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/getting-started/architecture)** – Agents communicate via the Solace Event Mesh for true scalability\n- **[Agent Orchestration](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/components/agents)** – Complex tasks are automatically broken down and delegated by the [Orchestrator](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/components/orchestrator) agent\n- **[Flexible Interfaces](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/components/gateways)** – Integrate with REST API, web UI, [Slack](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/slack-integration), or build your own integration\n- **[Extensible](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/components/plugins)** – Add your own agents, gateways, or services with minimal code\n- **[Agent-to-Agent Communication](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/getting-started/architecture)** – Agents can discover and delegate tasks to each other seamlessly using the Agent2Agent (A2A) Protocol\n- **[Dynamic Embeds](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/components/builtin-tools/embeds)** – Embed dynamic content like real-time data, calculations and file contents in responses\n\n📚 **Want to know more?** Check out the full Solace Agent Mesh [documentation](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/getting-started/introduction/).\n\n---\n\n## 🚀 Quick Start (5 minutes)\n\nSet up Solace Agent Mesh in just a few steps.\n\n### ⚙️ System Requirements\n\nTo run Solace Agent Mesh locally, you'll need:\n\n- **Python 3.10.16 – 3.13.x**\n- **pip** (comes with Python)\n- **OS**: MacOS, Linux, or Windows (with [WSL](https://learn.microsoft.com/en-us/windows/wsl/))\n- **LLM API key** (any major provider or custom endpoint)\n\n### 🎸 Vibe Coding\nTo quickly setup and customize your Agent Mesh, check out the [Vibe Coding Quickstart Guide](docs/docs/documentation/vibe_coding.md). This guide walks you through the essential steps to get Solace Agent Mesh up and running with minimal effort.\n\n### 💻 Setup Steps\n\n#### 1. Create a directory for a new project\n```bash\nmkdir my-sam \u0026\u0026 cd my-sam\n```\n#### 2. Create and activate a Python virtual environment\n```bash\npython3 -m venv .venv \u0026\u0026 source .venv/bin/activate\n```\n#### 3. Install Solace Agent Mesh (SAM)\nCheck if you have a version of SAM already installed.\n```bash\nsam -v\n```\nIf you have an earlier version, uninstall it and **start from scratch**:\n```bash\npip3 uninstall solace-agent-mesh\n```\nNote: Optionally, you can try to upgrade versions but this action is not officially supported at this time. (`pip3 install --upgrade solace-agent-mesh`)\n\nIf no previous version exists, install the latest version with:\n```bash\npip3 install solace-agent-mesh\n```\n#### 4. Initialize the new project via a GUI tool\n```bash\nsam init --gui\n```\nNote: This initialization UI runs on port 5002\n#### 5. Run the project\n```bash\nsam run\n```\n#### 6. Verify SAM is running\nOpen the Web UI at [http://localhost:8000](http://localhost:8000) for the chat interface and ask a question\n\n### 🔧 Customize SAM\n\n#### New agents can be added via a GUI interface\n```bash\nsam add agent --gui\n```\n\n#### Existing plugins can be installed\n```bash\nsam plugin add \u003cyour-component-name\u003e --plugin \u003cplugin-name\u003e\n```\n\n---\n\n## 🏗️ Architecture Overview\n\nSolace Agent Mesh provides a \"Universal A2A Agent Host,\" a flexible and configurable runtime environment built by integrating Google's Agent Development Kit (ADK) with the Solace AI Connector (SAC) framework.\n\nThe system allows you to:\n\n- Host AI agents developed with Google ADK within the SAC framework\n- Define agent capabilities (LLM model, instructions, tools) primarily through SAC YAML configuration\n- Use Solace Platform as the transport for standard Agent-to-Agent (A2A) protocol communication\n- Enable dynamic discovery of peer agents running within the same ecosystem\n- Allow agents to delegate tasks to discovered peers via the A2A protocol over Solace\n- Manage file artifacts using built-in tools with automatic metadata injection\n- Perform data analysis using built-in SQL, JQ, and visualization tools\n- Use dynamic embeds for context-dependent information resolution\n\n### Key Components\n\n- **SAC** handles broker connections, configuration loading, and component lifecycle\n- **ADK** provides the agent runtime, LLM interaction, tool execution, and state management\n- **A2A Protocol** enables communication between clients and agents, and between peer agents\n- **Dynamic Embeds** allow placeholders in responses that are resolved with context-dependent information\n- **File Management** provides built-in tools for artifact creation, listing, loading, and metadata handling\n\n---\n\n## ➡️ Next Steps\n\nWant to go further? Here are some hands-on tutorials to help you get started:\n\n| 🔧 Integration | ⏱️ Est. Time | 📘 Tutorial |\n|----------------|--------------|-------------|\n| 🌤️ **Weather Agent**\u003cbr\u003eLearn how to build an agent that gives Solace Agent Mesh the ability to access real-time weather information.  | **~15 min** | [Weather Agent Plugin](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/custom-agent) |\n| 🗃️ **SQL Database Integration**\u003cbr\u003eEnable Solace Agent Mesh to answer company-specific questions using a sample coffee company database.| **~10–15 min** | [SQL Database Tutorial](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/sql-database) |\n| 🧠 **MCP Integration**\u003cbr\u003eIntegrating a Model Context Protocol (MCP) Servers into Solace Agent Mesh. | **~10–15 min** | [MCP Integration Tutorial](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/mcp-integration) |\n| 💬 **Slack Integration**\u003cbr\u003eChat with Solace Agent Mesh directly from Slack. | **~20–30 min** | [Slack Integration Tutorial](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/slack-integration) |\n| 👔 **Microsoft Teams Integration (Enterprise)**\u003cbr\u003eConnect Solace Agent Mesh Enterprise to Microsoft Teams with Azure AD authentication. | **~30–40 min** | [Teams Integration Tutorial](https://solacelabs.github.io/solace-agent-mesh/docs/documentation/developing/tutorials/teams-integration) |\n\n---\n\n## 👥 Contributors\n\nSolace Agent Mesh is built with the help of our amazing community. Thanks to everyone who has contributed ideas, code and time to make this project better!\n\nView the full list of contributors here: [GitHub Contributors](https://github.com/SolaceLabs/solace-agent-mesh/graphs/contributors) 💚\n\n**Looking to contribute?** Check out [CONTRIBUTING.md](CONTRIBUTING.md) to get started and see how you can help!\n\n---\n\n## 📄 License\n\nThis project is licensed under the **Apache 2.0 License**. See the full license text in the [LICENSE](LICENSE) file.\n\n---\n\n## 🧪 Running Tests\n\nThis project uses `pytest` for testing. You can run tests using either `hatch` or `pytest` directly.\n\n### Using Hatch\n\nThe recommended way to run tests is through the `hatch` environment, which ensures all dependencies are managed correctly.\n\n```bash\n# Run all tests\nhatch test\n\n# Run tests with tags\nhatch test -m \"\u003ctag\u003e\"\n```\n\n### Using Pytest Directly\n\nIf you prefer to use `pytest` directly, you must first install the project with its test dependencies.\n\n```bash\n# Install the project in editable mode with the 'test' extras\npip install -e .[test]\n\n# Run all tests\npytest\n```\n\n---\n\n\u003ch3 align=\"center\"\u003e\n  \u003cimg src=\"./docs/static/img/solace-logo-text.svg\" alt=\"Solace Agent Mesh Logo\" width=\"100\"/\u003e\n\u003c/h3\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolacelabs%2Fsolace-agent-mesh","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsolacelabs%2Fsolace-agent-mesh","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolacelabs%2Fsolace-agent-mesh/lists"}