{"id":25626485,"url":"https://github.com/versionhq/exp-agent-performance","last_synced_at":"2025-04-14T12:05:09.604Z","repository":{"id":275687439,"uuid":"926321204","full_name":"versionHQ/exp-agent-performance","owner":"versionHQ","description":"AI agents - performance comparison using major LLMs.","archived":false,"fork":false,"pushed_at":"2025-02-12T14:11:18.000Z","size":11,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-14T12:05:02.203Z","etag":null,"topics":["agentic-ai","deepseek-r1","gemini","gpt-4o","pydantic","qwen2-5","versionhq"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/versionhq/","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/versionHQ.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}},"created_at":"2025-02-03T03:09:52.000Z","updated_at":"2025-02-12T14:11:22.000Z","dependencies_parsed_at":"2025-02-04T03:19:09.096Z","dependency_job_id":"62c5411c-cbf0-4c5c-a61a-86057cd96383","html_url":"https://github.com/versionHQ/exp-agent-performance","commit_stats":null,"previous_names":["versionhq/exp-agent-performance"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/versionHQ%2Fexp-agent-performance","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/versionHQ%2Fexp-agent-performance/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/versionHQ%2Fexp-agent-performance/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/versionHQ%2Fexp-agent-performance/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/versionHQ","download_url":"https://codeload.github.com/versionHQ/exp-agent-performance/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248877983,"owners_count":21176243,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["agentic-ai","deepseek-r1","gemini","gpt-4o","pydantic","qwen2-5","versionhq"],"created_at":"2025-02-22T16:07:52.114Z","updated_at":"2025-04-14T12:05:09.572Z","avatar_url":"https://github.com/versionHQ.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Overview\n\n![MIT license](https://img.shields.io/badge/License-MIT-green)\n![python ver](https://img.shields.io/badge/Python-3.11/3.12-orange)\n\n\nExperiment on AI agent performance using `versionhq` and `pydantic`.\n\n\n**Visit:**\n\n- [PyPI](https://pypi.org/project/versionhq/)\n- [Github](https://github.com/versionHQ/multi-agent-system)\n- [Docs](https://docs.versi0n.io)\n- [Process (Medium story)](https://medium.com/@kuriko-iwai/48d42fc57b71)\n\n\u003chr /\u003e\n\n## Key Features\n\nGenerate multi-agent systems based on the task complexity, execute tasks, and evaluate output based on the given criteria. \n\nAgents are model-agnostic, and can handle and share RAG tools, knowledge, memory, and callbacks among other agents.\n\n\n\u003chr /\u003e\n\n## Quick Start\n\n1. Install `uv` package manager:\n\n   For MacOS:\n\n   ```\n   brew install uv\n   ```\n\n   For Ubuntu/Debian:\n\n   ```\n   sudo apt-get install uv\n   ```\n\n2. Install dependencies:\n   ```\n   uv venv\n   source .venv/bin/activate\n   uv pip install -r requirements.txt\n   ```\n\n* In case of AssertionError/module mismatch, run Python version control using `.pyenv`\n   ```\n   pyenv install 3.12.8\n   pyenv global 3.12.8  (optional: `pyenv global system` to get back to the system default ver.)\n   uv python pin 3.12.8\n   echo 3.12.8 \u003e .python-version\n   ```\n\n3. Set up environment variables:\n   Create `.env` file in the project root and add the following:\n   ```\n   OPENAI_API_KEY=your-openai-api-key\n   GEMINI_API_KEY=your-gemini-api-key\n   OPENROUTER_API_KEY=your-openrouter-api-key\n   ```\n\n4. Run:\n   ```\n   uv run main.py\n   ```\n\n\u003chr /\u003e\n\n## Customizing\n\n- To add or refine an agent, use `src/agents.py`.\n\n- To add or refine a task, use `src/tasks.py`.\n\n\n\u003chr /\u003e\n\n## Results\n\n\u003cimg src=\"https://res.cloudinary.com/dfeirxlea/image/upload/v1738634968/pj_m_test/ulzp0wi0rptq61vkirkq.png\"\u003e\n\n(Feb 3, 2025)\n\n\u003chr /\u003e\n\n## Trouble Shooting\n\nCommon issues and solutions:\n- API key errors: Ensure all API keys in the `.env` file are correct and up to date. Make sure to add `load_dotenv()` on the top of the python file to apply the latest environment values.\n- Database connection issues: Check if the Chroma DB is properly initialized and accessible.\n- Memory errors: If processing large contracts, you may need to increase the available memory for the Python process.\n- Issues related to the Python version: Use Python 3.12.x as default by running `uv venv --python 3.12.8` and `uv python pin 3.12.8`.\n- Issues related to dependencies: `uv cache clean`, `uv venv`, and run `uv pip install -r requirements.txt -v`.\n- `reportMissingImports` error from pyright after installing the package: This might occur when installing new libraries while VSCode is running. Open the command pallete (ctrl + shift + p) and run the Python: Restart language server task.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fversionhq%2Fexp-agent-performance","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fversionhq%2Fexp-agent-performance","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fversionhq%2Fexp-agent-performance/lists"}