{"id":25315684,"url":"https://github.com/as2811-project/local-deep-research","last_synced_at":"2026-04-29T01:02:27.641Z","repository":{"id":275896526,"uuid":"927521048","full_name":"as2811-project/local-deep-research","owner":"as2811-project","description":"An OpenAI/Gemini Deep Research equivalent that you can run locally","archived":false,"fork":false,"pushed_at":"2025-02-13T05:40:08.000Z","size":76,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-02T20:04:06.617Z","etag":null,"topics":["agent","deepseek","llama3","local-llm","phi4","research"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/as2811-project.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":"2025-02-05T05:02:01.000Z","updated_at":"2025-05-13T07:47:55.000Z","dependencies_parsed_at":"2025-02-13T06:27:42.455Z","dependency_job_id":null,"html_url":"https://github.com/as2811-project/local-deep-research","commit_stats":null,"previous_names":["as2811-project/local-deep-research"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/as2811-project/local-deep-research","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/as2811-project%2Flocal-deep-research","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/as2811-project%2Flocal-deep-research/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/as2811-project%2Flocal-deep-research/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/as2811-project%2Flocal-deep-research/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/as2811-project","download_url":"https://codeload.github.com/as2811-project/local-deep-research/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/as2811-project%2Flocal-deep-research/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32405904,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T19:38:08.556Z","status":"ssl_error","status_checked_at":"2026-04-28T19:37:55.688Z","response_time":56,"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","deepseek","llama3","local-llm","phi4","research"],"created_at":"2025-02-13T18:24:44.371Z","updated_at":"2026-04-29T01:02:27.625Z","avatar_url":"https://github.com/as2811-project.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"### Local Deep Research\n\nThis is a very basic attempt to recreate the Deep Research functionalities introduced by OpenAI/Google Gemini, locally. Running the notebook will let you provide your research objectives\nand specify how wide you want the research to be. Depending upon the model, you will see a 'research_report.md' file in your project directory within minutes.\n\n#### Prerequisites\n\nOllama running with any language model\nAPI keys from SERP API and Firecrawl\n\n#### How to run\n\n1. Clone the repo\n2. Run `pip install -r requirments`\n3. Create a .env file with the following: SERP_API_KEY, FIRECRAWL_API_KEY, MODEL (use the model's name from Ollama as is)\n4. Open the jupyter notebook and click run all\n\n#### Performance\n\nThis notebook was written and tested on a Macbook Pro M1Pro with 16GB RAM. Deepseek R1 7b, Llama 3.1 8b, Phi3 3.8b produced truly terrible outputs. None of them fully adhered to the\ninstructions. Phi4 (14b) however stays relatively close to my prompts and produces an output that some might consider 'usable'. I personally thought it was acceptable but not detailed\nenough. This might have to do with model sizes or the way they were trained. Bigger models might result in better results. \n\n#### TODO\n\n[] Improve naming: Variables could be renamed to be more descriptive/precise\n\n[] Clean up: Remove logging statements\n\n[] Shift away from a single Jupyter notebook to a full blown FastAPI endpoint\n\n[] Add a front-end\n\n**Local Deep Research is released under the MIT license. Feel free to use it or build on it or contribute!**","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fas2811-project%2Flocal-deep-research","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fas2811-project%2Flocal-deep-research","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fas2811-project%2Flocal-deep-research/lists"}