{"id":29253504,"url":"https://github.com/maxonary/thesis-topic-evaluator","last_synced_at":"2026-04-27T00:31:39.437Z","repository":{"id":301921535,"uuid":"1010662686","full_name":"maxonary/thesis-topic-evaluator","owner":"maxonary","description":"ReAct Multi-Agent Flow that improves Bachelor Thesis Topic definition ","archived":false,"fork":false,"pushed_at":"2025-06-29T15:37:49.000Z","size":10,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-29T16:37:23.018Z","etag":null,"topics":["agent","agentic-workflow","react-agent","streamlit"],"latest_commit_sha":null,"homepage":"https://thesis-topic-ai.streamlit.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/maxonary.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-06-29T14:52:23.000Z","updated_at":"2025-06-29T15:39:42.000Z","dependencies_parsed_at":"2025-06-29T16:49:04.030Z","dependency_job_id":null,"html_url":"https://github.com/maxonary/thesis-topic-evaluator","commit_stats":null,"previous_names":["maxonary/thesis-topic-evaluator"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/maxonary/thesis-topic-evaluator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxonary%2Fthesis-topic-evaluator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxonary%2Fthesis-topic-evaluator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxonary%2Fthesis-topic-evaluator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxonary%2Fthesis-topic-evaluator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maxonary","download_url":"https://codeload.github.com/maxonary/thesis-topic-evaluator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maxonary%2Fthesis-topic-evaluator/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32318417,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-26T23:26:28.701Z","status":"ssl_error","status_checked_at":"2026-04-26T23:26:25.802Z","response_time":129,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["agent","agentic-workflow","react-agent","streamlit"],"created_at":"2025-07-04T02:03:00.998Z","updated_at":"2026-04-27T00:31:39.419Z","avatar_url":"https://github.com/maxonary.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Thesis Topic Evaluator (Streamlit)\n\nA Streamlit web application that leverages the ReAct (Reasoning + Acting) multi-agent framework to evaluate proposed Bachelor's thesis topics in Software Engineering.\n\n## Features\n\n1. **Scope Agent** – Verifies alignment with Bachelor-level expectations.\n2. **Critic Agent** – Highlights vagueness, over-complexity, or unclear goals.\n3. **Literature Agent** – Estimates availability of supporting academic literature.\n4. **Feasibility Agent** – Assesses practical implementability with common tools and skills.\n5. **Judge Agent** – Synthesises previous feedback, issuing an overall decision.\n\nEach agent operates using an LLM via the OpenAI API, following the ReAct methodology to reason step-by-step before acting.\n\n## Architecture\n\n```mermaid\ngraph TD\n    U[\"User (Streamlit UI)\"] --\u003e SCOPE[\"Scope Agent\"]\n    U --\u003e CRITIC[\"Critic Agent\"]\n    U --\u003e LIT[\"Literature Agent\"]\n    U --\u003e FEAS[\"Feasibility Agent\"]\n    SCOPE --\u003e JUDGE[\"Judge Agent\"]\n    CRITIC --\u003e JUDGE\n    LIT --\u003e JUDGE\n    FEAS --\u003e JUDGE\n    JUDGE --\u003e U\n```\n\n## Setup\n\n1. **Clone \u0026 install dependencies**\n\n```bash\npython -m venv .venv\nsource .venv/bin/activate  # on Windows: .venv\\Scripts\\activate\npip install -r requirements.txt\n```\n\n2. **Configure the OpenAI API key**\n\nCreate a `.env` file in the project root or export the variable directly:\n\n```bash\necho \"OPENAI_API_KEY=YOUR_KEY_HERE\" \u003e .env\n```\n\n3. **Run the application**\n\n```bash\nstreamlit run streamlit_app.py\n```\n\nThen open the provided local URL (e.g. http://localhost:8501) in your browser.\n\n## Notes\n\n* The default model is `gpt-4o`; adjust in `streamlit_app.py` if needed.\n* All agent responses are requested in JSON. If the LLM deviates, the raw output is still shown.\n* This project is a proof-of-concept; production deployments should incorporate stronger error handling and rate-limit resilience. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaxonary%2Fthesis-topic-evaluator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaxonary%2Fthesis-topic-evaluator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaxonary%2Fthesis-topic-evaluator/lists"}