{"id":23777303,"url":"https://github.com/agiflow/agiflow-sdks","last_synced_at":"2026-03-02T21:08:35.476Z","repository":{"id":245790843,"uuid":"819251193","full_name":"AgiFlow/agiflow-sdks","owner":"AgiFlow","description":"LLM QA, Observability, Evaluation and User Feedback","archived":false,"fork":false,"pushed_at":"2024-08-06T11:11:09.000Z","size":2622,"stargazers_count":21,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-12-15T04:35:45.657Z","etag":null,"topics":["agents","llm-agent","llm-evaluation","llmops","llms","machine-learning","python","typescript"],"latest_commit_sha":null,"homepage":"https://agiflow.io","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AgiFlow.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}},"created_at":"2024-06-24T06:25:54.000Z","updated_at":"2024-08-18T18:51:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"de94aa8d-32e0-4874-ae6c-a5ed138ae923","html_url":"https://github.com/AgiFlow/agiflow-sdks","commit_stats":null,"previous_names":["agiflow/agiflow-sdks"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgiFlow%2Fagiflow-sdks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgiFlow%2Fagiflow-sdks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgiFlow%2Fagiflow-sdks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AgiFlow%2Fagiflow-sdks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AgiFlow","download_url":"https://codeload.github.com/AgiFlow/agiflow-sdks/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232061692,"owners_count":18467102,"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","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":["agents","llm-agent","llm-evaluation","llmops","llms","machine-learning","python","typescript"],"created_at":"2025-01-01T08:24:12.142Z","updated_at":"2026-03-02T21:08:35.434Z","avatar_url":"https://github.com/AgiFlow.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n![Logo of AGIFlow](./docs/agiflow_logo.png)\n\n# **AGIFlow**\n\n🤖 **AGIFlow**: LLM QA and Observability. We streamline LLM and Agentic Workflow development with real-time tracing and a visual debugger. Easily test prompt and model performance while continuously monitoring performance in production.\n\n[Homepage](https://agiflow.io/) | [Documentation](https://docs.agiflow.io/) | [Architecture and Data Security](./docs/architecture.md) | [Discord](https://discord.gg/vejg6tkBUu) | [Newsletter](https://mailchi.mp/agiflow/agiflow-sub)\n\n\u003c/div\u003e\n\n## Table of contents\n\n- [Why AGIFlow?](#why-agiflow)\n- [Getting Started](#getting-started)\n- [Key Features](#key-features)\n- [Contribution](#contribution)\n- [License](#license)\n- [Support](#support)\n\n## Why AGIFLow?\n\n\n[\u003cimg src=\"./docs/overview.png\"\u003e](https://www.loom.com/share/d2e4fcb3b7c847ec8bc752f48a644570)\n\nIf you are developing a complex LLM workflow, you might have some difficulties with:  \n- Understand how output from one LLM affect the other LLM inference  \n- Disect LLM execution dependencies to improve performance  \n- Communicate with QA and non-technical users on how the workflow works  \n...and more\n\nAGIFlow solves these issues by visualising LLM workflow automatically for you based on telemetry data. With a few integration lines of code, you can get AGIFlow up and running from development environment to production. We understand the challenges of bringing your LLM app to production and want to ensure you have a [scalable, trustworthy infrastructure](./docs/architecture.md) to do so.\n\n## Getting Started\n\nThe simpliest way to get start is to use [AGIFlow's control-plane dashboard](https://app.agiflow.io). If you wish to keep your workflow and data private, you can also run Agiflow app locally using `docker compose` and start tracing your application by:\n\n1. **Clone the Repository**:\n```bash\ngit clone https://github.com/AgiFlow/agiflow-sdks.git\ncd agiflow-sdks\n```\n\n2. **Run the development app**: \n```bash\ncd dockers/dev\ndocker-compose up\n```\n\n3. **Integrate with your application**:\n- Go to `localhost:3000` to get the API key and follow [this documentation](https://docs.agiflow.io/python) to get telemetry from your LLM app to Agiflow dashboard.   \n\n- With `docker compose` development setup, the `AGIFLOW_BASE_URL` or `api_endpoint` option is `http://localhost:3000/api/dataplane`; same url applied for [frontend analytics sdk](https://docs.agiflow.io/web)'s `endpoint`.\n\n## Key Features\n\nThis mono-repo is designed for fullstack developers and product teams to develop scalable LLM product. To learn more about why and how we use mono-repo, please visit [Nx, PNPM and Poetry Mono-Repo documentation](./docs/mono-repo.md).  \n\nWe're making sources available on a rolling basis from our internal repo. For comprehensive documentation, please visit [AGIFlow's docs](https://docs.agiflow.io). Here is an overview of our packages:\n\n- [x] **dockers**: Docker compose to run and self-host AGIFlow.\n- [x] **apps/agiflow-controlplane**: The AGIFlow's controlplane dashboard built with Vitejs + React\n- [x] **[llm-mocks](https://docs.agiflow.io/llm-mocks)**: Mocking library for LLM providers, simplifying TDD, reducing CI/CD costs on regression testing, and facilitating API development.\n- [x] **[agiflow-eval](https://docs.agiflow.io/python-agiflow-eval)**: Python SDK for LLM evaluations, supporting custom templates and multiple models.\n- [x] **[agiflow-sdk](https://docs.agiflow.io/python)**: Python SDK built on top of Open-Telemetry to collect LLM metrics, supporting prompt and model registry synchronization for multiple LLM usages.\n- [x] **[@agiflow/js-sdk](https://docs.agiflow.io/web)**: Web SDK for frontend analytics on how users interact with LLM apps, allowing full-stack traceability.\n- [ ] **[@agiflow/web-feedback](https://docs.agiflow.io/web/feedback)**: Feedback widget with session replay and workflow visualization to get high-quality feedback from simple chat apps to complex agentic workflows.\n\n\n## Contribution\n\nWe welcome contributions from the community! If you would like to contribute, please follow [this guide](./Contribution.md).\n\n## License\n\nThis repository is a mono-repo that contains various packages, modules, and applications, each of which may be governed by different licenses. Unless otherwise explicitly stated within the respective package, module, or application subdirectory, the code in this repository is licensed under the Business Source License (BSL). For more details, refer to the [License Notice](./LICENSE).\n\n## Support\n\nIf you have any questions or need support, please open an issue in this repository or contact our support team at vuong@agiflow.com.\n\nTo stay updated, get support, and engage with fellow developers, join our [Discord community](https://discord.gg/vejg6tkBUu). Click the link below to connect with us and be part of the conversation!\n\nThank you for using AGIFlow SDKs! We look forward to seeing the amazing things you build.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagiflow%2Fagiflow-sdks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fagiflow%2Fagiflow-sdks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fagiflow%2Fagiflow-sdks/lists"}