{"id":28256929,"url":"https://github.com/sl-mar/quantcoder-legacy","last_synced_at":"2025-08-04T03:34:34.100Z","repository":{"id":259668727,"uuid":"865952589","full_name":"SL-Mar/quantcoder-legacy","owner":"SL-Mar","description":"The legacy version of QuantCoder, containing core workflows for transforming finance research into trading strategies and generating code for QuantConnect. Code is no longer maintained.","archived":false,"fork":false,"pushed_at":"2025-04-01T15:55:38.000Z","size":4350,"stargazers_count":70,"open_issues_count":1,"forks_count":19,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-17T12:42:06.233Z","etag":null,"topics":["llm","openai","pair-programming","quantconnect","trading","trading-algorithms","trading-strategies"],"latest_commit_sha":null,"homepage":"","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/SL-Mar.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":"2024-10-01T11:56:38.000Z","updated_at":"2025-06-12T06:38:46.000Z","dependencies_parsed_at":"2024-10-27T08:19:28.372Z","dependency_job_id":"208cd323-f03c-4034-a1da-ae137dac76a9","html_url":"https://github.com/SL-Mar/quantcoder-legacy","commit_stats":null,"previous_names":["sl-mar/pair-programming_from_articles","sl-mar/quant_coder","sl-mar/quantcoder","sl-mar/quantcoder-fs","sl-mar/quantcoder-legacy"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/SL-Mar/quantcoder-legacy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SL-Mar%2Fquantcoder-legacy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SL-Mar%2Fquantcoder-legacy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SL-Mar%2Fquantcoder-legacy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SL-Mar%2Fquantcoder-legacy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SL-Mar","download_url":"https://codeload.github.com/SL-Mar/quantcoder-legacy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SL-Mar%2Fquantcoder-legacy/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268644545,"owners_count":24283346,"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","status":"online","status_checked_at":"2025-08-04T02:00:09.867Z","response_time":79,"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":["llm","openai","pair-programming","quantconnect","trading","trading-algorithms","trading-strategies"],"created_at":"2025-05-19T23:14:33.779Z","updated_at":"2025-08-04T03:34:34.091Z","avatar_url":"https://github.com/SL-Mar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# QuantCoder (Legacy CLI Version)\n\n\u003e ⚠️ This is the original CLI-only version of QuantCoder, preserved in the `quantcoder-legacy` branch.\n\nQuantCoder is a command-line tool that allows users to generate QuantConnect trading algorithms from research articles using natural language processing and large language models (LLMs). It was initiated in November 2023 and based on a cognitive architecture inspired by the article [\"Dual Agent Chatbots and Expert Systems Design\"](https://towardsdev.com/dual-agent-chatbots-and-expert-systems-design-25e2cba434e9)\n\nThe initial version successfully coded a blended momentum and mean-reversion strategy as described in [\"Outperforming the Market (1000% in 10 years)\"](https://medium.com/coinmonks/how-to-outperform-the-market-fe151b944c77?sk=7066045abe12d5cf88c7edc80ec2679c), which received over 10,000 impressions on LinkedIn.\n\n---\n\n## 🚀 First-Time Installation\n\n\u003e ✅ Requires **Python 3.8 or later**\n\n### 🛠 Setup Instructions\n\n```bash\n# Clone the repository and switch to the legacy branch\ngit clone https://github.com/SL-Mar/QuantCoder.git\ncd QuantCoder\ngit checkout quantcoder-legacy\n\n# Create and activate a virtual environment\npython -m venv .venv-legacy\n\n# On Windows:\n.\\.venv-legacy\\Scripts\\activate\n# On macOS/Linux:\nsource .venv-legacy/bin/activate\n\n# Install dependencies and the CLI\npip install -e .\npython -m spacy download en_core_web_sm\npip install openai==0.28\n```\n\nYou may also freeze dependencies:\n\n```bash\npip freeze \u003e requirements-legacy.txt\n```\n\n---\n🧠 LLM Configuration\nBy default, this project uses the OpenAI gpt-4o-2024-11-20 model for generating trading code from research articles.\n\n## 💡 Usage\n\nTo launch the CLI tool in interactive mode:\n\n```bash\npython -m quantcli.cli interactive\n```\n\nOr if `quantcli` is recognized as a command:\n\n```bash\nquantcli interactive\n```\n\n---\n\n## ⚠️ OpenAI SDK Compatibility\n\nThis legacy version uses the **OpenAI SDK v0.28**. Newer versions (`\u003e=1.0.0`) are **not supported**.\n\nIf you encounter this error:\n\n```\nYou tried to access openai.ChatCompletion, but this is no longer supported...\n```\n\nFix it by running:\n\n```bash\npip install openai==0.28\n```\n\n---\n\n## 📁 Articles and Strategies\n\nThe folder 'Strategies and publications' contains articles and trading strategies generated using this CLI tool. These strategies may have been manually refined or enhanced using LLM-based methods. Use them at your own discretion — conduct thorough research and validate before live use.\n\n---\n\n## 📜 License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsl-mar%2Fquantcoder-legacy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsl-mar%2Fquantcoder-legacy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsl-mar%2Fquantcoder-legacy/lists"}