{"data":{"slug":"coze-dev-coze-loop","name":"coze-loop","tagline":"Next-generation AI Agent Optimization Platform","github_url":"https://github.com/coze-dev/coze-loop","owner":"coze-dev","repo":"coze-loop","owner_avatar_url":"https://avatars.githubusercontent.com/u/157483752?v=4","primary_language":"Go","stars":5697,"forks":791,"topics":["agent","agent-evaluation","agent-observability","agentops","ai","coze","eino","evaluation","langchain","llm-observability","llmops","monitoring","observability","open-source","openai","playground","prompt-management"],"archived":false,"github_pushed_at":"2026-08-20T11:57:50+00:00","maintenance_label":"Very active","stars_delta_30d":77,"url":"https://www.graphcanon.com/tools/coze-dev-coze-loop","markdown_url":"https://www.graphcanon.com/tools/coze-dev-coze-loop.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/coze-dev-coze-loop","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=coze-dev-coze-loop","description":"Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.  ","homepage_url":null,"license":"Apache-2.0","open_issues":72,"watchers":34,"ai_summary":"Cozeloop offers full-lifecycle management for AI agents including development, debugging, evaluation, and monitoring.","readme_excerpt":"## Quick Start\n>\n> Refer to [Quick Start](https://github.com/coze-dev/coze-loop/wiki/2.-Quickstart) to learn in detail how to install and deploy the latest version of Coze Loop.\n\n---\n\n### Deployment method 1: Docker deployment (Docker Compose)\n>\n> Please install and start Docker Engine before you start.\n\nProcedure:\n\n1. Clone the source code.\n   Run the following command to obtain the latest version of the Coze Loop source code.\n\n   ```Bash\n   # Clone the code\n   git clone https://github.com/coze-dev/coze-loop.git\n\n   # Enter the coze-loop directory\n   cd coze-loop\n   ```\n\n2. Configure a model.\n   1. Enter the `coze-loop` directory.\n   2. Edit the file `release/deployment/docker-compose/conf/model_config.yaml`.\n   3. Modify the api_key and model fields. Take Volcengine Ark as an example:\n      * api_key: Volcengine Ark API Key. Users in China can refer to the [Volcengine Ark documentation](https://www.volcengine.com/docs/82379/1541594), while users outside China can refer to the [BytePlus ModelArk documentation](https://docs.byteplus.com/en/docs/ModelArk/1361424?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).\n      * model: The Endpoint ID of the Volcengine Ark model access point. Users within China can refer to [the Volcengine Ark documentation](https://www.volcengine.com/docs/82379/1099522); users outside China can refer to [the BytePlus ModelArk documentation](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).\n3. Start the service.\n   Run the following commands to quickly deploy the open-source version of Coze Loop using Docker Compose.\n\n   ```Bash\n   # Start the service (default: development mode)\n   # Run in the coze-loop/ directory\n   make compose-up\n   ```\n\n4. Access the Coze Loop open-source version through your browser `http://localhost:8082`.\n\n---\n\n### Deployment method 2: Kubernetes deployment using Helm Chart\n\n> * The Kubernetes cluster has been prepared, the Nginx Ingress add-ons have been enabled, and the Kubectl and Helm tools have been installed.\n> * To quickly try it out locally, you can deploy a Kubernetes cluster using Minikube. For detailed steps, refer to [Quick Start](https://github.com/coze-dev/coze-loop/wiki/2.-Quickstart).\n\nProcedure:\n\n1. Run the following command to obtain the Helm Chart package.\n\n   ```Bash\n   helm pull oci://docker.io/cozedev/coze-loop --version 1.0.0-helm\n   tar -zxvf coze-loop-1.0.0-helm.tgz && cd coze-loop && rm -f ../coze-loop-1.0.0-helm.tgz\n   ```\n\n2. Configure a model.\n   Go to the `coze-loop` directory and edit the `release/deployment/helm-chart/umbrella/conf/model_config.yaml` file. Configure the following fields, using Volcengine Ark as an example:\n   * api_key: Volcengine Ark API Key. Users in mainland China can refer to the [Volcengine Ark documentation](https://www.volcengine.com/docs/82379/1541594), while users outside mainland China can refer to the [BytePlus ModelArk documentation](https://docs.byteplus.com/en/docs/ModelArk/1361424?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).\n   * model: The Endpoint ID of the Volcengine Ark model access point. Users in China can refer to the [Volcengine Ark documentation](https://www.volcengine.com/docs/82379/1099522), while users outside China can refer to the [BytePlus ModelArk documentation](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).\n3. Configure Ingress rules.\n   Ingress is used to expose services to external networks. You need to configure the `templates/ingress.yaml` file in the project directory according to the actual cluster situation, manually modify parameters such as ingressClassName, and configure elements such as class, instance, host, and IP allocation.\n4. Deploy and start the service.\n   Execute the following commands to quickly deploy the open-source version of Coze Loop using Helm.\n\n   ```Bash\n   # Run in the coze-loop/ directory","github_created_at":"2025-06-24T00:26:28+00:00","created_at":"2026-07-07T17:42:03.778334+00:00","updated_at":"2026-08-20T12:01:42.684641+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"evaluation","name":"evaluation"},{"slug":"observability","name":"observability"},{"slug":"open-source","name":"open-source"}],"trust":{"provenance":{"is_fork":false,"github_id":1007406267,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-20T12:01:41.906Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":0,"last_release_at":"2026-01-20T12:35:01Z","stars_delta_30d":77,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:20:00.725Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-20T12:01:42.396Z"},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-08-20T12:01:42.396Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-20T12:01:42.396Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you are developing AI agents and need full-lifecycle support from initial setup through deployment","For users preferring Go and looking for an open-source solution with a permissive license"],"when_not_to_use":["If your primary agent development language is not Go, or if you do not wish to use Docker or Kubernetes for deployment","Avoid if you are unwilling to configure the Volcengine Ark API Key and Endpoint ID manually through YAML files during setup"],"source":"enrich:decision_facts","observed_at":"2026-07-14T20:33:18.228Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Coze-loop provides comprehensive lifecycle management for AI agents leveraging Go, under Apache-2.0 license, ideal for robust agent optimization from development to monitoring."}]}}