{"id":32829751,"url":"https://github.com/xpressai/xaibo","last_synced_at":"2025-11-07T20:02:28.475Z","repository":{"id":294709522,"uuid":"947391341","full_name":"XpressAI/xaibo","owner":"XpressAI","description":"Xaibo is a modular agent framework designed for building flexible AI systems with clean protocol-based interfaces.","archived":false,"fork":false,"pushed_at":"2025-09-17T13:30:42.000Z","size":1780,"stargazers_count":11,"open_issues_count":4,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-19T04:11:27.033Z","etag":null,"topics":["agent","agent-framework","agentic","agents","ai","dependency-injection","rag","ui"],"latest_commit_sha":null,"homepage":"https://xaibo.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/XpressAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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}},"created_at":"2025-03-12T16:02:49.000Z","updated_at":"2025-08-25T20:30:15.000Z","dependencies_parsed_at":"2025-07-17T13:53:39.228Z","dependency_job_id":"bde37247-4665-4a84-b685-2005a56228ab","html_url":"https://github.com/XpressAI/xaibo","commit_stats":null,"previous_names":["xpressai/xaibo"],"tags_count":12,"template":false,"template_full_name":null,"purl":"pkg:github/XpressAI/xaibo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XpressAI%2Fxaibo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XpressAI%2Fxaibo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XpressAI%2Fxaibo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XpressAI%2Fxaibo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XpressAI","download_url":"https://codeload.github.com/XpressAI/xaibo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XpressAI%2Fxaibo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":283249415,"owners_count":26804613,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-07T02:00:06.343Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agent","agent-framework","agentic","agents","ai","dependency-injection","rag","ui"],"created_at":"2025-11-07T20:00:58.940Z","updated_at":"2025-11-07T20:02:28.461Z","avatar_url":"https://github.com/XpressAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Xaibo: The Modular AI Agent Framework\n\n**Build flexible, observable, and production-ready AI agents with clean, swappable components.**\n\nXaibo is a modular framework designed to help you build sophisticated AI systems that are easy to test, debug, and evolve. Move beyond monolithic agent scripts and start creating with components you can trust.\n\n\u003cdiv style=\"display: flex; gap: 10px; margin: 20px 0;\"\u003e\n  \u003cdiv style=\"flex: 1;\"\u003e\n    \u003cimg src=\"docs/images/sequence-diagram.png\" alt=\"Xaibo Debug UI - Sequence Diagram Overview\" width=\"100%\"\u003e\n    \u003cp\u003e\u003cem\u003eSequence Diagram Overview\u003c/em\u003e\u003c/p\u003e\n  \u003c/div\u003e\n  \u003cdiv style=\"flex: 1;\"\u003e\n    \u003cimg src=\"docs/images/detail-view.png\" alt=\"Xaibo Debug UI - Detail View\" width=\"100%\"\u003e\n    \u003cp\u003e\u003cem\u003eDetail View of Component Interactions\u003c/em\u003e\u003c/p\u003e\n  \u003c/div\u003e\n\u003c/div\u003e\n\n_Visually trace every step of your agent's operation in the debug UI._\n\n## Why Use Xaibo?\n\n### Build with Confidence, Not Concrete\nXaibo's protocol-driven architecture lets you define how components interact without locking you into specific\nimplementations. Swap LLMs, vector stores, or tools without rewriting your agent's core logic.\n\n### Understand Your Agent's Every Thought\nEvery component is automatically wrapped in a transparent proxy that observes all inputs, outputs, and errors. The\nbuilt-in debug UI provides a sequence diagram of your agent's inner workings, making complex interactions easy to\nunderstand and debug.\n\n### Test, Don't Guess\nWith first-class support for dependency injection, you can easily swap in mock components to write fast, deterministic\ntests for your agent's logic. Ensure your agent behaves as expected before you ever hit a real LLM API.\n\n\n## Quick Start\n\nGet your first Xaibo agent running in under a minute.\n\n**Prerequisites:** Python 3.10+ and `pip`.\n\n1.  **Install `uv`:** _(if you don't already have it)_\n\n    ```bash\n    pip install uv\n    ```\n\n2.  **Initialize a new project:**\n\n    ```bash\n    uvx xaibo init my-agent-project\n    ```\n    You will be asked what dependencies you want to install. That way you don't need to install half the internet, if you\n    are going to use just third-party APIs.\n\n3.  **Start the development server:**\n\n    ```bash\n    cd my-agent-project\n    uv run xaibo dev\n    ```\n    This starts the development server with an OpenAI compatible chat completions API at `http://localhost:9001/openai`\n    and the debugging ui at `http://localhost:9001`. \n\n4.  **Interact with the example agent:**\n    You can now send requests to your agent using any OpenAI-compatible client.\n\n    ```bash\n    # Send a simple chat completion request to the Xaibo OpenAI-compatible API\n    curl -X POST http://127.0.0.1:9001/openai/chat/completions \\\n      -H \"Content-Type: application/json\" \\\n      -d '{\n        \"model\": \"example\",\n        \"messages\": [\n          {\"role\": \"user\", \"content\": \"Hello, what time is it now?\"}\n        ]\n      }'\n    ```\n\n    ```bash\n    # Same request using HTTPie (a more user-friendly alternative to curl)\n    http POST http://127.0.0.1:9001/openai/chat/completions \\\n      model=example \\\n      messages:='[{\"role\": \"user\", \"content\": \"Hello, what time is it now?\"}]'\n    ```\n\n### What You Get\n\nThe `init` command sets up a clean, organized project structure for you:\n\n```\nmy-agent-project/\n├── agents/\n│   └── example.yml    # Your agent's configuration\n├── modules/\n│   └── __init__.py\n├── tools/\n│   └── example.py     # An example tool implementation\n├── tests/\n│   └── test_example.py\n└── .env               # Environment variables\n```\n\n## Core Features\n\n  * **Protocol-Driven Architecture:** Enforces clean separation between components.\n  * **Built-in Debug UI:** Visually trace and inspect your agent's execution flow.\n  * **Dependency Injection:** Easily swap implementations and write mockable, testable code.\n  * **Extensible Module System:** Ships with modules for major LLM providers (OpenAI, Anthropic, Google), local embeddings, vector memory, and more.\n  * **Tool Support:** Create tools with simple python, use MCP servers or integrate whatever fits your needs. \n  * **OpenAI-Compatible API:** Use your agent with a wide range of existing tools and libraries out-of-the-box.\n  * **MCP Adapter:** Expose your agents as tools to any [Model Context Protocol](https://modelcontextprotocol.io/)-compatible client.\n\n## Dive Deeper: Full Documentation\n\nFor detailed guides on agent configuration, core concepts, available protocol implementations, and creating your own\nmodules, please see our **[full documentation](https://xaibo.ai)**.\n\n## Get Involved\n\nXaibo is actively developed and we welcome contributors!\n\n  * **GitHub Repository:** [github.com/xpressai/xaibo](https://github.com/xpressai/xaibo) - Report issues, suggest features, or submit a pull request.\n  * **Discord Community:** [Join our Discord Server](https://discord.gg/uASMzSSVKe) - Ask questions, share what you're building, and connect with the community.\n  * **Contact Us:** hello@xpress.ai\n\n## Development\n\n### Roadmap\n\nXaibo is actively developing:\n- Enhanced visual configuration UI\n- Visual tool definition with Xircuits\n- More API adapters beyond OpenAI standard\n- Multi-user aware agents\n\nThe core principles and APIs are stable for production use.\n\n### Contributing\n\n#### Running Tests\nTests are implemented using pytest.\n\n```bash\n# From the root xaibo directory\nuv sync --all-extras\nuv run pytest\n```\n\nIf you are using PyCharm to run them, you will need to configure it to also show logging output. That way some failures will be a lot easier to debug.\n\nGo to File \u003e Settings \u003e Advanced Settings \u003e Python and check the option \n`Pytest: do not add \"--no-header --no-summary -q\"`.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxpressai%2Fxaibo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxpressai%2Fxaibo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxpressai%2Fxaibo/lists"}