{"full_name":"assafelovic/gpt-researcher","owner":"assafelovic","name":"gpt-researcher","shard":"1","url":"https://github.com/assafelovic/gpt-researcher","description":"An autonomous agent that conducts deep research on any data using any LLM providers","homepage":"https://gptr.dev","topics":["ai","python","agent","automation","research","search","webscraping","llms","deepresearch","mcp","mcp-server"],"tag_pages":["agent","ai","automation","llms","mcp","mcp-server","python","research","search","webscraping"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/13554167?u=088b1f16835af9f77f78fd326f629a26bd6c74a4&v=4","created_at":"2023-05-12T10:33:54Z","pushed_at":"2026-11-12T19:34:46Z","metrics":{"stars":30708,"forks":4227,"watchers":168,"issues":762,"prs":1301,"releases":75,"issues_open":4,"issues_closed":758,"prs_open":40,"prs_closed":581,"prs_merged":680,"discussions":197},"growth":{"day":{"stars":19,"forks":5,"base_day":"2026-11-15"},"week":{"stars":241,"forks":61,"base_day":"2026-11-04"},"month":{"stars":663,"forks":124,"base_day":"2026-10-17"}},"history":{"dates":["2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[29649,29708,29806,29861,29876,29894,29922,29931,29940,29956,29977,30005,30045,30076,30095,30114,30132,30144,30179,30196,30224,30246,30265,30277,30304,30315,30334,30363,30384,30433,30467,30612,30629,30645,30650,30672,30689,30708],"forks":[4054,4055,4069,4072,4077,4081,4084,4085,4087,4095,4096,4097,4103,4106,4128,4130,4170,4205,4311,4280,4128,4134,4136,4134,4137,4138,4143,4147,4156,4167,4166,4207,4210,4210,4213,4220,4222,4227],"watchers":[176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,176,175,175,175,175,175,169,169,169,169,169,169,169,168,null,168,168,168,168,168,168],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,3,3,4,4,4,4],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,15,21,29,31,32,40]},"boards":{},"same_owner":[],"issues":[{"number":1764,"title":"Research is getting stucked every other time while giving no meaningful logs / ui hints indicating what it was attempting to do","comments":6,"created_at":"2026-05-07T20:55:41Z"},{"number":1582,"title":"GPL License Alternative PDF Scraper Implementation","comments":2,"created_at":"2026-01-05T10:37:43Z"},{"number":2277,"title":"PyMuPDFScraper returns empty titles for PDFs without document metadata","comments":0,"created_at":"2026-11-09T17:50:46Z"},{"number":2295,"title":"security: SSRF guard from #1818 (0.16.1+/0.17.0) is bypassable via HTTP redirect - internal content still reaches the report","comments":0,"created_at":"2026-11-12T15:18:02Z"}],"discussions":[{"number":2304,"title":"Exploring Moli with GPT Researcher","comments":0,"category":"General","created_at":"2026-11-13T08:17:24Z"},{"number":2297,"title":"Hi from a new contributor 👋","comments":0,"category":"General","created_at":"2026-11-12T17:29:45Z"},{"number":2288,"title":"An invitation from Civitas — a city for AI agents (founding citizen № 003 reserved for GPT Researcher)","comments":0,"category":"General","created_at":"2026-11-12T04:52:28Z"},{"number":2244,"title":"GPT Researcher on an OpenAI-compatible endpoint: OPENAI_BASE_URL, the three LLM slots, embeddings, and why custom model IDs can trip temperature/reasoning handling","comments":0,"category":"Show and tell","created_at":"2026-10-30T03:45:16Z"},{"number":2241,"title":"Before researching podcast notes: keep the interview corpus separate from corroboration","comments":0,"category":"Show and tell","created_at":"2026-10-29T04:28:43Z"},{"number":2235,"title":"Provider-portability notes: 21 places where OpenAI/Gemini specifics leak past the LLM abstraction","comments":1,"category":"Ideas","created_at":"2026-10-28T02:50:06Z"},{"number":2223,"title":"Design partner invite: independent judge for GPT Researcher agents","comments":0,"category":"Show and tell","created_at":"2026-10-21T06:45:34Z"},{"number":2211,"title":"Showcase: ATS Zero-Browser Gateway — Fast protocol scraper & MCP server for career & talent research","comments":0,"category":"Show and tell","created_at":"2026-10-15T20:46:46Z"}],"latest_release":{"name":"New paper UI, detailed reports in 3:27, and 53 community fixes","tag":"v3.8.0","published_at":"2026-11-09T15:12:43Z","body":"## A new UI, and detailed reports in under 4 minutes\n\n<a href=\"https://github.com/user-attachments/assets/4d3f26cf-8ccc-413a-b17c-80aa9e1b52d1\">\n  <img src=\"https://github.com/user-attachments/assets/3a56a008-fcbd-4373-9e40-8d6027120cfb\" alt=\"GPT Researcher turning a question into a cited report\" width=\"800\">\n</a>\n\nThe Next.js app has a new paper design that matches [gptr.dev](https://gptr.dev). Settings live in one modal with tabs for Research, MCP, Documents and Backend; a run shows a plain-language feed, and the sources margin slides in once writing starts. The previous UI is still available at `/classic`.\n\nDetailed reports now finish in **3:27 instead of 9:11**. Sections are researched in parallel, and the default writer is now `gpt-6-sol`, which starts writing within seconds instead of reasoning for close to a minute per section first. Measurements and the model comparison are in #2272.\n\n## ⚠️ Changes to note\n- **Default writer model:** `SMART_LLM` is now `openai:gpt-6-sol` (was `openai:gpt-5.4`). Set `SMART_LLM` to keep the previous model.\n- **LLM idle timeout:** an LLM call that sends nothing for 300 seconds now fails with a clear error instead of hanging the run. Tune it with `LLM_TIMEOUT` (`0` disables it). (#2220)\n- **Docker:** the root `.env` is no longer copied into images. `docker compose` loads it at runtime (needs Compose 2.24+); with `docker run`, pass `--env-file .env`. If you ever pushed an image you built locally, rotate the keys that were in your `.env`.\n- `generate_report` now raises when every LLM attempt fails, instead of returning an empty report. (#2219)\n\n## Also in this release\n- **Prebuilt Docker images** for `linux/amd64` and `linux/arm64` on GHCR: `ghcr.io/assafelovic/gpt-researcher` and `ghcr.io/assafelovic/gpt-researcher-frontend-nextjs`, tagged with the version and `latest` (#1517)\n- **Research observer:** an optional lifecycle observer for integrations that want structured progress events (#2232)\n- **MiniMax** regional providers and Flash defaults (#1924), a configurable TypeSafe base URL (#2243), and **Deploy on Render** with a `render.yaml` blueprint (#2184)\n- Multi-agent plan review feedback from the web UI works again, and the multi-agent writer uses `SMART_TOKEN_LIMIT` and `REASONING_EFFORT` (#2272)\n- Deep research honors reasoning budgets, counts retries and nested researchers in costs, and keeps cited learnings at the word limit (#2260, #2209, #2208)\n- MCP search no longer blocks the event loop, and the `max_tools` cap is enforced (#2262, #2263)\n- Configuration: `reasoning_effort` from JSON config files, `DOC_PATH` / `REPORT_SOURCE` env overrides, UTF-8 config files, and image generation settings are all honored again (#2230, #2248, #2249, #2199, #2246)\n- Retriever, scraper and document loader fixes across Exa, Google, Bing, Bocha, PubMed Central, arXiv, online documents and Windows text files\n- Retriever plugins: a community list with Keenable and Sciverse (#2176, #2225)\n\n53 community pull requests went into this release. Thank you to everyone who contributed.\n\n**Install:** `pip install -U gpt-researcher` (0.17.0)\n\n## What's Changed\n* fix(readme): point star history chart back to official star-history.com by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2204\n* docs: drop STORM references and describe current research approach by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2205\n* fix(config): preserve loaded MCP settings by @imharjot in https://github.com/assafelovic/gpt-researcher/pull/2193\n* fix(config): stop sharing mutable defaults between Config instances by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2206\n* fix(ci): cap pytest below 9.2 so --forked tests stop crashing by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2269\n* docs: use a single black tile logo in the READMEs by @assafelovic in https://github.com/assafelovic/gpt-researcher/pull/2270\n* New paper UI, and detailed reports in 3:27 inste","is_prerelease":false},"readme":true,"readme_zh":true,"news":[{"title":"GPT-Researcher：AI 自動代理幫你深入研究任何主題","url":"https://www.techritual.com/2026/08/23/527533/","source":"techritual","lang":"zh","date":"2026-08-23"},{"title":"GitHub Copilot CLI vs GPT Researcher","url":"https://opentools.ai/compare/githubcopilotcli-vs-gpt-researcher","source":"opentools.ai","lang":"en","date":"2026-05-05"},{"title":"AutoGPT (Hugging Face) vs GPT Researcher","url":"https://opentools.ai/compare/autogpt-hugging-face-vs-gpt-researcher","source":"opentools.ai","lang":"en","date":"2026-05-04"},{"title":"The Modern OSINT Stack: From Search Tools to Agentic Intelligence Systems","url":"https://news.google.com/rss/articles/CBMiuAFBVV95cUxNMTJ5S0g4RGxmdml4RDNXR191MDZhUTQzZjIyT0t1RlVWUFZBanZyWUM1bUpmeU1uTnVzOGs0QVFjTDc1aFFDR0ZyVEY5WXZzV3VEYnRXZzNWZXBkSklqQzNPbHNsU0FhUzNIRW04bkd4ZXNDY0syVkEzVThhYzA5YzBWSlBTUXR3WVhLMUp5Q3gxVGtPN3dTcWRNZXhpOXNBaEEzZDBfRzZRYTFxMTB2OTA0QUNSbTYz?oc=5","source":"Medium","lang":"en","date":"2026-07-10"},{"title":"Anthropic won't own MCP 'design flaw' putting 200K servers at risk, researchers say","url":"https://news.google.com/rss/articles/CBMirAFBVV95cUxOcXFwYU0yVlJmZFZobnh0UlNBOFg0RVJNTE02TVMzT05Gc1hXU0QyS01kVmhMYlViOHF1dnV0SjI4TElXSHE0enNUUkpLNkc5c1NTWThsUy15VGxwMkxXbnFPZDJlOU5HMTVSVXI4TERFUjJRTzBnN09VWTBKeFJadGx3dmdmamJSUWpUbFdqdmZ2UG1FMEZUVXFHLUZJeXI2SUxvT1FCd3RIMUN0?oc=5","source":"The Register","lang":"en","date":"2026-04-16"},{"title":"MCP Supply Chain Advisory: RCE Vulnerabilities Across the AI Ecosystem","url":"https://news.google.com/rss/articles/CBMioAFBVV95cUxNTU5iSmR0UnY4OTJCTXVXWTlTTWZnOWo2MHJINTRTR1hVaTZyc255QTBraFBmanJTcldySWtnMTlyTzFVaFBTbHlNUVdPb1dCS3BWaGR5YWZuU0JEcU1UR09qdTVVZTl6NTBPMW1YRjVXaGpUMi1sQU5lOGFsQVR2TFRTTURYUzdNRWVJR2RSUVFlTk1DNjBUdWVRdlBlSzlm?oc=5","source":"OX Security","lang":"en","date":"2026-04-15"},{"title":"60个精选Skills、工作流与开源项目，最全Claude进阶清单","url":"https://news.google.com/rss/articles/CBMiU0FVX3lxTE81X2JJTnhsbVVGYmlKeUpkdTMwS2R5d0ZHMXR6U0Z4TlQ5TVRnTHdTTE5iX0U3enc5Ulc5eWc2QnlQc1hXRWN2V2hucGU5dHNCT213?oc=5","source":"BlockBeats","lang":"zh","date":"2026-03-30"},{"title":"20 AI Agent Examples in 2025","url":"https://news.google.com/rss/articles/CBMiVEFVX3lxTE1qT2hnX01tTzB1MmFZRVl4Uk4xRFlMdWx4elVBaDVaYTB6Vm92RV9xN19iRUdLVHhTdlZfdFZ1REVJV2hKRktxTTMxTTQ5Z3RuVE5YaA?oc=5","source":"AutoGPT","lang":"en","date":"2025-03-13"},{"title":"STORM AI can write basic Wikipedia-esque articles in minutes","url":"https://news.google.com/rss/articles/CBMib0FVX3lxTE5WbU1SUGVWaHpsbDlXcmtwaFlpTkV1QW9hckxpTFdDOElLVHZNQnZVQUh1cVJIV25sWVVfRFhiNGZjZ3EtcW5uVTZBNnBIUUV2cDBzemJ3aGVvbDFDMUFNMGYtQXdncGlJRnVacFltZw?oc=5","source":"R&D World","lang":"en","date":"2024-07-24"},{"title":"‘GPT Researcher’: An Autonomous AI Agent Designed for Comprehensive Online Research on a Variety of Tasks","url":"https://news.google.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?oc=5","source":"MarkTechPost","lang":"en","date":"2024-06-19"},{"title":"拆解多基于LangGraph的多Agent项目设计和技术细节","url":"https://news.google.com/rss/articles/CBMiXEFVX3lxTE91dHdWZlFnWEM2YWE1UDliWHRPSXRFT0cxVDB0amVYUG9kUk5NQ1BVeFJhTDRkbTlSaktsczNLV180Q09XTVVIZWJSU0c4QUV1NzNmbmkxS3Yxd19t?oc=5","source":"53AI","lang":"zh","date":"2024-05-16"},{"title":"哥大｜GPT Researcher智能体，生成详细论文","url":"https://news.google.com/rss/articles/CBMiSEFVX3lxTE96V3ZCbEVlVU1Cc0dHNVd1SVBRMGQyaXRaTEUxT18xTHIyaEFhc3hBemRfOW1FWUNWZHBrZndiZGRXOG9YeXJuZA?oc=5","source":"智源社区","lang":"zh","date":"2023-08-04"}],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}