{"id":50508967,"url":"https://github.com/aaronlab/agent-bench-lite","last_synced_at":"2026-06-02T18:32:49.584Z","repository":{"id":348485067,"uuid":"1198378909","full_name":"aaronlab/agent-bench-lite","owner":"aaronlab","description":"Lightweight AI Agent evaluation benchmark toolkit — 6 dimensions, 30 tasks, plugin architecture, async execution, beautiful CLI","archived":false,"fork":false,"pushed_at":"2026-04-01T11:19:47.000Z","size":41,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-09T15:53:22.459Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aaronlab.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":null,"dco":null,"cla":null}},"created_at":"2026-04-01T11:19:44.000Z","updated_at":"2026-04-01T11:19:51.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/aaronlab/agent-bench-lite","commit_stats":null,"previous_names":["aaronagent/agent-bench-lite","aaronlab/agent-bench-lite"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/aaronlab/agent-bench-lite","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronlab%2Fagent-bench-lite","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronlab%2Fagent-bench-lite/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronlab%2Fagent-bench-lite/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronlab%2Fagent-bench-lite/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aaronlab","download_url":"https://codeload.github.com/aaronlab/agent-bench-lite/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aaronlab%2Fagent-bench-lite/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33833277,"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":"2026-06-02T02:00:07.132Z","response_time":109,"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":"2026-06-02T18:32:49.023Z","updated_at":"2026-06-02T18:32:49.580Z","avatar_url":"https://github.com/aaronlab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# agent-bench-lite\n\nA lightweight AI Agent evaluation benchmark toolkit.\n\n## Overview\n\n**agent-bench-lite** provides a modular, extensible framework for evaluating AI agents across six core dimensions:\n\n| Dimension | What it measures |\n|---|---|\n| **Tool Calling Accuracy** | Can the agent call the right tools with correct parameters? |\n| **Planning \u0026 Decomposition** | Can the agent break complex tasks into logical steps? |\n| **Context Retention** | Can the agent remember and use earlier context? |\n| **Error Recovery** | Can the agent handle and recover from errors gracefully? |\n| **Instruction Following** | Does the agent follow exact specifications? |\n| **Multi-step Reasoning** | Can the agent chain logical steps to reach a conclusion? |\n\n## Installation\n\n```bash\n# Base install (no LLM adapters)\npip install -e .\n\n# With Anthropic adapter\npip install -e \".[anthropic]\"\n\n# With OpenAI adapter\npip install -e \".[openai]\"\n\n# Everything\npip install -e \".[all]\"\n\n# Development\npip install -e \".[dev]\"\n```\n\n## Quick Start\n\n```python\nimport asyncio\nfrom agent_bench_lite import BenchmarkRunner, EchoAdapter\n\nasync def main():\n    adapter = EchoAdapter()\n    runner = BenchmarkRunner(adapter=adapter)\n    report = await runner.run()\n    report.print_summary()\n    report.save_json(\"results.json\")\n\nasyncio.run(main())\n```\n\nOr use the example script:\n\n```bash\npython examples/run_benchmark.py\n```\n\n## Architecture\n\n- **Adapters** wrap LLM APIs into a common interface (`BaseAdapter`)\n- **Dimensions** define evaluation tasks and scoring logic (`BaseDimension`)\n- **Runner** orchestrates task execution across dimensions\n- **Evaluator** computes scores from raw results\n- **Reporter** formats and exports results\n\n### Adding a new dimension\n\n```python\nfrom agent_bench_lite.dimensions.base import BaseDimension, TaskResult\n\nclass MyDimension(BaseDimension):\n    name = \"my_dimension\"\n    description = \"Evaluates something new\"\n\n    def get_tasks(self):\n        return [...]\n\n    async def evaluate_task(self, task, agent_response):\n        return TaskResult(...)\n```\n\n### Adding a new adapter\n\n```python\nfrom agent_bench_lite.adapters.base import BaseAdapter\n\nclass MyAdapter(BaseAdapter):\n    async def send_message(self, messages, tools=None):\n        ...\n\n    async def send_message_with_tools(self, messages, tools, tool_handler):\n        ...\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaronlab%2Fagent-bench-lite","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faaronlab%2Fagent-bench-lite","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faaronlab%2Fagent-bench-lite/lists"}