{"data":{"slug":"modelengine-group-nexent","name":"nexent","tagline":"Zero-code platform for auto-generating production-grade AI agents","github_url":"https://github.com/ModelEngine-Group/nexent","owner":"ModelEngine-Group","repo":"nexent","owner_avatar_url":"https://avatars.githubusercontent.com/u/200162819?v=4","primary_language":"Python","stars":5828,"forks":718,"topics":["agent","agentic-ai","agentic-framework","agentic-rag","agentic-workflow","ai","harness","harness-engineering","llm","mcp","multi-agent","rag"],"archived":false,"github_pushed_at":"2026-08-18T13:39:07+00:00","maintenance_label":"Very active","stars_delta_30d":110,"url":"https://www.graphcanon.com/tools/modelengine-group-nexent","markdown_url":"https://www.graphcanon.com/tools/modelengine-group-nexent.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelengine-group-nexent","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelengine-group-nexent","description":"Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.","homepage_url":"http://modelengine-group.github.io/nexent/","license":"MIT","open_issues":227,"watchers":255,"ai_summary":"Nexent is a platform designed to automatically generate production-grade AI agents using principles from Harness Engineering, supporting unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes. The platform can be deployed via Docker or Kubernetes.","readme_excerpt":"### System Requirements\n\n| Resource | Docker | Kubernetes |\n|----------|--------|-------------|\n| **CPU** | 4 cores (min) / 8 cores (rec.) | 4 cores (min) / 8 cores (rec.) |\n| **Memory** | 8 GiB (min) / 16 GiB (rec.) | 16 GiB (min) / 64 GiB (rec.) |\n| **Disk** | 40 GiB (min) / 100 GiB (rec.) | 100 GiB (min) / 200 GiB (rec.) |\n| **Architecture** | x86_64 / ARM64 | x86_64 / ARM64 |\n| **Software** | Docker 24+, Docker Compose v2+ | Kubernetes 1.24+, Helm 3+ |\n\n> **Note:** Recommended configurations ensure optimal performance in production environments.\n\n---\n\n### Docker Deployment (Recommended for Individuals/Small Teams)\n\nQuick and straightforward for most users. Prerequisites: Docker 24+ and Docker Compose v2+:\n\n```bash\ngit clone https://github.com/ModelEngine-Group/nexent.git\ncd nexent\nbash deploy.sh docker\n```\n\nThe root `deploy.sh` only forwards to the target deploy script; the native Docker implementation is `bash deploy/docker/deploy.sh`. The Docker and Kubernetes deploy scripts share the same deployment configuration model. Interactive runs show Bash TUI menus for component selection, port policy, and image source. `infrastructure` is required; `application`, `data-process`, and `supabase` are selected by default and can be disabled when you want a smaller deployment. Use `b`/Backspace to return to the previous TUI step and `q` to quit. Use `--defaults` to skip the TUI and deploy with saved `deploy.options` or built-in defaults. Non-interactive runs can also pass the same choices with `--version`, `--components`, `--port-policy development|production`, and `--image-source general|mainland|local-latest`. Successful deployments save non-sensitive choices to each deploy directory's `deploy.options` for reuse on the next run.\n\nDocker and Kubernetes both use `deploy/env/.env` as the runtime configuration file. Existing `deploy/env/.env` is kept as-is. If it does not exist, the deploy scripts first reuse `docker/.env`, then fall back to `deploy/env/.env.example`. Monitoring-specific settings are generated from `deploy/env/monitoring.env.example` into `deploy/env/monitoring.env`.\n\nDocker uninstall is handled by `bash uninstall.sh docker`. It can preserve or delete data volumes: run it interactively, pass `--delete-volumes true|false`, or use `bash uninstall.sh docker delete-all` to remove containers and persistent data.\n\nOffline image packages can be built with `bash build.sh --package --target docker --compress true` or `bash deploy/offline/build_offline_package.sh --target docker --compress true`. The package includes image tar files, `load-images.sh`, `push-images.sh`, root deploy/uninstall entrypoints, deployment scripts, SQL files, `manifest.yaml`, and `checksums.txt`. Package deploys use saved `deploy.options` or built-in defaults without opening the TUI; add `--config` to configure interactively. Deploy with `bash deploy.sh --load-images docker ...` on the target host, or use `bash deploy.sh --push-images --image-registry-prefix registry.example.com/nexent docker ...` to push loaded images to an internal registry and deploy with that image prefix. When `--push-images` is used without a prefix, `deploy.sh` asks for it before `push-images.sh` prompts for the registry username and password.\n\nFor detailed deployment instructions, see [Docker Installation](https://modelengine-group.github.io/nexent/en/quick-start/installation.html).\n\n---\n\n### Kubernetes Deployment (For Enterprise Production)\n\nIdeal for enterprise scenarios requiring high availability and elastic scaling. Prerequisites: Kubernetes 1.24+ and Helm 3+:\n\n```bash\ngit clone https://github.com/ModelEngine-Group/nexent.git\ncd nexent\nbash deploy.sh k8s\n```\n\nThe native Kubernetes implementation is `bash deploy/k8s/deploy.sh`. It reads the same `deploy/env/.env` as Docker and renders explicit values into Helm ConfigMap and Secret overrides. Use `--persistence-mode local|dynamic|existing`, `--storage-class`/`--sc`, `--local-path`, `--local-node-name`, and `--existing-claim-p","github_created_at":"2025-04-28T10:44:33+00:00","created_at":"2026-07-07T17:37:56.760948+00:00","updated_at":"2026-08-18T18:01:38.547194+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"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"agentic-ai","name":"agentic-ai"},{"slug":"agentic-framework","name":"agentic-framework"},{"slug":"agentic-rag","name":"agentic-rag"},{"slug":"agentic-workflow","name":"agentic-workflow"},{"slug":"ai","name":"ai"},{"slug":"harness","name":"harness"},{"slug":"harness-engineering","name":"harness-engineering"}],"trust":{"provenance":{"is_fork":false,"github_id":974157595,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T18:01:37.540Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":5,"days_since_push":0,"last_release_at":"2026-08-05T08:21:08Z","stars_delta_30d":110,"open_issues_delta_30d":20},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-26T04:00:26.442Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T18:01:38.033Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-18T18:01:38.033Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-18T18:01:38.033Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":8,"requires_docker":true},"constraints":{"min_ram_gb":8,"requires_docker":true},"when_to_use":["When you require unified tools and skills management through its Harness Engineering principles.","For projects needing built-in constraints, feedback loops, and control planes to ensure agent reliability and performance.","If your use case involves creating multi-agent systems or workflows where interconnected AI agents operate with shared memory and orchestrated actions."],"when_not_to_use":["When a simpler, non-production grade solution is sufficient since Nexent's robust infrastructure might add unnecessary complexity.","For environments lacking the recommended system resources such as 8 cores CPU, 16 GiB Memory, and 100 GiB Disk (for Kubernetes deployment), which can limit its performance and reliability."],"source":"enrich:decision_facts","observed_at":"2026-07-12T02:14:37.556Z"},"constraint_facets":{"min_ram_gb":8,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 8 GB RAM; Requires Docker"},{"label":"Adopt for","value":"Nexent offers a zero-code platform for generating production-grade AI agents with Harness Engineering principles built into its framework."}]}}