{"id":45084,"library":"harbor-rewardkit","title":"Harbor Rewardkit","description":"Lightweight grading toolkit for environment-based tasks, part of the Harbor framework. Current version 0.1.4, updated Apr 2025. Pre-release with monthly releases.","status":"active","version":"0.1.4","language":"python","source_language":"en","source_url":"https://github.com/harbor-framework/harbor","tags":["reward","grading","reinforcement-learning","python312"],"install":[{"cmd":"pip install harbor-rewardkit","lang":"bash","label":"PyPI"}],"dependencies":[],"imports":[{"wrong":"from harbor_rewardkit import Aggregator","symbol":"AgentCLI","correct":"from rewardkit import AgentCLI"},{"symbol":"LLMJudge","correct":"from rewardkit import LLMJudge"},{"symbol":"Reward","correct":"from rewardkit import Reward"}],"quickstart":{"code":"from harbor_rewardkit import Aggregator\nfrom harbor_rewardkit.scores import EpsilonGreedyScore\nfrom harbor_rewardkit.rewards import BinaryReward\n\nagg = Aggregator(score=EpsilonGreedyScore(), reward=BinaryReward())\nresult = agg.grade(trajectory=[(\"state1\", \"action1\", 1.0), (\"state2\", \"action2\", 0.0)])\nprint(result)","lang":"python","description":"Creates an Aggregator with default score and reward, then grades a trajectory."},"warnings":[{"fix":"Upgrade Python to 3.12 or later.","message":"Python 3.12+ required. Install on 3.11 or earlier will fail with syntax errors due to new language features.","severity":"breaking","affected_versions":"all"},{"fix":"Use from harbor_rewardkit import ...","message":"Import paths use underscores (harbor_rewardkit) not hyphens (harbor-rewardkit). This is a common mistake when copy-pasting from the project name.","severity":"gotcha","affected_versions":"all"},{"fix":"Check documentation before upgrade; wrap trajectory creation in a helper.","message":"The `grade` method signature may change. Currently it accepts `trajectory` as a list of tuples; future versions may require a structured dict.","severity":"deprecated","affected_versions":"<=0.1.4"},{"fix":"Instantiate with explicit arguments: EpsilonGreedyScore(epsilon=0.1)","message":"Default score and reward classes may change defaults in minor versions (e.g. EpsilonGreedyScore epsilon value). Always specify parameters explicitly.","severity":"gotcha","affected_versions":">=0.1.0"}],"env_vars":null,"search_vec":"'0.1.4':18 '2025':21 'apr':20 'base':9 'current':16 'environ':8 'environment-bas':7 'framework':15 'grade':4,29 'harbor':1,14 'learn':32 'lightweight':3 'month':26 'part':11 'pre':23 'pre-releas':22 'python312':33 'reinforc':31 'reinforcement-learn':30 'releas':24,27 'reward':28 'rewardkit':2 'task':10 'toolkit':5 'updat':19 'version':17","created_at":"2026-06-07T12:53:17.242220+00:00","updated_at":"2026-06-07T12:53:17.242220+00:00","problems":null,"ecosystem":"pypi","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":null,"cli_version":null,"type":"library","homepage":"https://github.com/harbor-framework/harbor","github":"https://github.com/harbor-framework/harbor","docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["ai-ml","testing"],"base_url":null,"auth_type":null,"provenance":{"verified_status":"passing","verified_at":"2026-07-03","last_verified":"2026-07-03","next_check":"2026-08-02","install_tag":null}}