{"id":51220946,"url":"https://github.com/harbor-framework/harbor-cookbook","last_synced_at":"2026-06-28T07:03:05.426Z","repository":{"id":345127849,"uuid":"1181228935","full_name":"harbor-framework/harbor-cookbook","owner":"harbor-framework","description":"Realistic examples of building evals and optimizing agents with Harbor","archived":false,"fork":false,"pushed_at":"2026-04-23T02:30:06.000Z","size":578,"stargazers_count":62,"open_issues_count":1,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-23T04:18:23.853Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/harbor-framework.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,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-13T22:18:19.000Z","updated_at":"2026-04-23T02:30:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/harbor-framework/harbor-cookbook","commit_stats":null,"previous_names":["harbor-framework/harbor-cookbook"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/harbor-framework/harbor-cookbook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harbor-framework%2Fharbor-cookbook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harbor-framework%2Fharbor-cookbook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harbor-framework%2Fharbor-cookbook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harbor-framework%2Fharbor-cookbook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harbor-framework","download_url":"https://codeload.github.com/harbor-framework/harbor-cookbook/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harbor-framework%2Fharbor-cookbook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34880191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"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":[],"created_at":"2026-06-28T07:03:04.393Z","updated_at":"2026-06-28T07:03:05.418Z","avatar_url":"https://github.com/harbor-framework.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Harbor Cookbook\n\n [![](https://dcbadge.limes.pink/api/server/https://discord.gg/6xWPKhGDbA)](https://discord.gg/6xWPKhGDbA)\n[![Docs](https://img.shields.io/badge/Docs-000000?style=for-the-badge\u0026logo=mdbook\u0026color=105864)](https://harborframework.com/docs)\n\nRealistic examples of building evals and optimizing agents using [Harbor](https://github.com/harbor-framework/harbor). \n\n## Getting Started\n\nInstall Harbor:\n\n```bash\nuv tool install harbor\n```\n\nRun any task recipe:\n\n```bash\nharbor run -p harbor_cookbook/recipes/\u003cname\u003e -a claude-code -m anthropic/claude-opus-4-6\n```\n\n## Task Recipes\n\n| Name | Description |\n|:--|:--|\n| [simple\u0026#8209;task](harbor_cookbook/recipes/simple-task/) | Minimal single-container task. |\n| [multi\u0026#8209;container](harbor_cookbook/recipes/multi-container/) | Docker Compose task where the agent interacts with a locally hosted REST API. |\n| [mcp\u0026#8209;tools](harbor_cookbook/recipes/mcp-tools/) | Giving the agent custom tools via a locally hosted FastMCP server. |\n| [multi\u0026#8209;reward](harbor_cookbook/recipes/multi-reward/) | Multiple independent verifiers each producing their own score. |\n| [simulated\u0026#8209;user](harbor_cookbook/recipes/simulated-user/) | Agent discovers requirements by talking to a simulated user. |\n| [computer\u0026#8209;use\u0026#8209;ubuntu](harbor_cookbook/recipes/computer-use-ubuntu/) | Computer use reference implementation on an Ubuntu virtual desktop. |\n| [computer\u0026#8209;use\u0026#8209;windows](harbor_cookbook/recipes/computer-use-windows/) | Computer use reference implementation on a remote Windows desktop (Daytona). |\n| [dns\u0026#8209;blacklisting](harbor_cookbook/recipes/dns-blacklisting/) | Network-level hostname blacklisting with exact, wildcard, and regex rules. |\n| [skills](harbor_cookbook/recipes/skills/) | Giving agents access to custom skills. |\n| [multi\u0026#8209;step](harbor_cookbook/recipes/multi-step/) | Ordered multi-step task with per-step instructions, tests, workdir uploads, healthcheck, early stopping, and per-step artifacts. |\n\n## Optimization Examples\n\n| Name | Description |\n|:--|:--|\n| [harbor\u0026#8209;rl](harbor_cookbook/harbor_rl/) | RL training on Harbor tasks using harbor.rl + Tinker. |\n| [gepa](harbor_cookbook/gepa/) | Agent harness optimization for MedAgentBench using Harbor+GEPA. |\n| [tinker\u0026#8209;rl](harbor_cookbook/tinker_rl/) | RL training on Harbor tasks using the Tinker Cookbook integration. |\n| [prime\u0026#8209;rl](harbor_cookbook/prime_rl/) | RL training on Harbor tasks using Prime RL and Verifiers. |\n| [sky\u0026#8209;rl](harbor_cookbook/sky_rl/) | RL training on Harbor tasks using SkyRL. |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharbor-framework%2Fharbor-cookbook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharbor-framework%2Fharbor-cookbook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharbor-framework%2Fharbor-cookbook/lists"}