dda8d0f6bf
* Feature/tighten up ci pipeline (#3700) * Fix docker volume mounts (#3710) Co-authored-by: Reinier van der Leer <github@pwuts.nl> Co-authored-by: Nicholas Tindle <nick@ntindle.com> * Feature/enable intuitive logs for community challenge step 1 (#3695) * Feature/enable intuitive logs summarization (#3697) * Move task_complete command out of prompt (#3663) * feat: move task_complete command out of prompt * fix: formatting fixes * Add the shutdown command to the test agents * tests: update test vcrs --------- Co-authored-by: James Collins <collijk@uw.edu> * Allow users to Disable Commands via the .env (#3667) * Document Disabling command categories (#3669) * feat: move task_complete command out of prompt * fix: formatting fixes * feat: add command disabling * docs: document how to disable command categories * Enable denylist handling for plugins (#3688) Co-authored-by: Luke Kyohere <lkyohere@mfsafrica.com> Co-authored-by: Nicholas Tindle <nick@ntindle.com> * Fix call to `plugin.post_planning` (#3414) Co-authored-by: Nicholas Tindle <nick@ntindle.com> * create information retrieval challenge a (#3770) Co-authored-by: Richard Beales <rich@richbeales.net> * fix typos (#3798) * Update run.bat (#3783) Co-authored-by: Richard Beales <rich@richbeales.net> * Update run.sh (#3752) Co-authored-by: Richard Beales <rich@richbeales.net> * ADD: Bash block in the contributing markdown (#3701) Co-authored-by: Richard Beales <rich@richbeales.net> * BUGFIX: Selenium Driver object reference was included in the browsing results for some reason (#3642) * * there is really no need to return the reference to the Selenium driver along with the text summary and list of links. * * removing unused second return value from browse_website() * * updated cassette * * updated YAML cassette for test_browse_website * * after requirements reinstall, another update YAML cassette for test_browse_website * * another update YAML cassette for test_browse_website, only as a placholder commit to trigger re-testing due to some docker TCP timeout issue * * another update YAML cassette for test_browse_website --------- Co-authored-by: batyu <batyu@localhost> * Update CONTRIBUTING.md * Self feedback Improvement (#3680) * Improved `Self-Feedback` * minor tweak * Test: Updated `test_get_self_feedback.py` * community challenges in the wiki (#3764) * Update README.md * Update PULL_REQUEST_TEMPLATE.md Added link to wiki Contributing page * Add link to wiki Contributing page * fix * Add link to wiki page on Contributing * Implement Logging of User Input in logs/Debug Folder (#3867) * Adds USER_INPUT_FILE_NAME * Update agent.py * Update agent.py Log only if console_input is not the authorise_key * Reformatting * add information retrieval challenge to the wiki (#3876) * add code owners policy (#3981) * add code owners * added @ to codeowners * switched to team ownership * Memory Challenge C (#3908) * Memory Challenge C * Working cassettes * Doc fixes * Linting and doc fix * Updated cassette * One more cassette try --------- Co-authored-by: merwanehamadi <merwanehamadi@gmail.com> * memory challenge c inconsistent (#3985) * Improve & fix memory challenge docs. (#3989) Co-authored-by: Kaan Osmanagaoglu <kaano@questps.com.au> * Feature/centralize prompt (#3990) Co-authored-by: xiao.hu <454292663@qq.com> * Use correct reference to prompt_generator in autogpt/llm/chat.py (#4011) * fix typos (#3998) Co-authored-by: Minfeng Lu <minfenglu@Minfengs-MacBook-Pro.local> Co-authored-by: Richard Beales <rich@richbeales.net> * fix typo in the getting started docs (#3997) Co-authored-by: Richard Beales <rich@richbeales.net> * Fix path to workspace directory in setup guide (#3927) Co-authored-by: Nicholas Tindle <nick@ntindle.com> * document that docker-compose 1.29.0 is minimally required (#3963) Co-authored-by: Nicholas Tindle <nick@ntindle.com> * Integrate pytest-xdist Plugin for Parallel and Concurrent Testing (#3870) * Adds pytest-parallel dependencies * Implement pytest-parallel for faster tests * Uses pytest-xdist * Auto number of workers processes * Update ci.yml --------- Co-authored-by: Nicholas Tindle <nick@ntindle.com> * explain temperature setting in env file (#4140) Co-authored-by: Richard Beales <rich@richbeales.net> * Catch JSON error in summary_memory.py (#3996) Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Update duckduckgo dependency - min should be 2.9.5 (#4142) Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Update Dockerfile - add missing scripts and plugins directories. (#3706) Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Updated memory setup links (#3829) Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Parse package versions so upgrades can be forced (#4149) * parse package versions so upgrades can be forced * better version from @collijk * fix typo in autopgt/agent/agent.py (#3747) Co-authored-by: merwanehamadi <merwanehamadi@gmail.com> Co-authored-by: Richard Beales <rich@richbeales.net> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Fix `milvus_memory_test.py` mock `Config` (#3424) Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Implemented showing the number of preauthorised commands left. #1035 (#3322) Co-authored-by: mayubi <marwand@ayubi-it.de> Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Challenge: Kubernetes and documentation (#4121) * challenge_kubes_and_readme * docs * testing * black and isort * revision * lint * comments * blackisort * docs * docs * deleting_cassette * suggestions * misspelling_errors --------- Co-authored-by: merwanehamadi <merwanehamadi@gmail.com> * Make sdwebui tests pass (when SD is running) (#3721) Co-authored-by: Nicholas Tindle <nick@ntindle.com> * Add Edge browser support using EdgeChromiumDriverManager (#3058) Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> * Added --install-plugin-deps to Docker (#4151) Co-authored-by: Nicholas Tindle <nick@ntindle.com> * Feature/basic proxy (#4164) * basic proxy (#54) * basic proxy (#55) * basic proxy * basic proxy * basic proxy * basic proxy * add back double quotes * add more specific files * write file * basic proxy * Put back double quotes * test new CI (#4168) * test new CI * test new CI * remove double quotes * Feature/test new ci pipeline 2 (#4169) * test new CI * remove double quotes * make it a variable * make it a variable * Test New CI Pipeline (#4170) * introduce dummy prompt change * introduce dummy prompt change * empty commit * empty commit * empty commit * push to origin repo * add s to quote * Feature/fix rate limiting issue Step 1 (#4173) * temporarilly remove 3.11 * add back 3.11 (#4185) * Revert "Put back 3.11 until it's removed as a requirement" (#4191) --------- Co-authored-by: Reinier van der Leer <github@pwuts.nl> Co-authored-by: merwanehamadi <merwanehamadi@gmail.com> Co-authored-by: Peter Petermann <ppetermann80@googlemail.com> Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: James Collins <collijk@uw.edu> Co-authored-by: Luke K <2609441+pr-0f3t@users.noreply.github.com> Co-authored-by: Luke Kyohere <lkyohere@mfsafrica.com> Co-authored-by: Robin Richtsfeld <robin.richtsfeld@gmail.com> Co-authored-by: RainRat <rainrat78@yahoo.ca> Co-authored-by: itsmarble <130370814+itsmarble@users.noreply.github.com> Co-authored-by: Ambuj Pawar <pawar.ambuj@gmail.com> Co-authored-by: bszollosinagy <4211175+bszollosinagy@users.noreply.github.com> Co-authored-by: batyu <batyu@localhost> Co-authored-by: Pi <sunfish7@gmail.com> Co-authored-by: AbTrax <45964236+AbTrax@users.noreply.github.com> Co-authored-by: Andres Caicedo <73312784+AndresCdo@users.noreply.github.com> Co-authored-by: Douglas Schonholtz <15002691+dschonholtz@users.noreply.github.com> Co-authored-by: Kaan <kaanixir@gmail.com> Co-authored-by: Kaan Osmanagaoglu <kaano@questps.com.au> Co-authored-by: xiao.hu <454292663@qq.com> Co-authored-by: Tomasz Kasperczyk <tomaszikasperczyk@gmail.com> Co-authored-by: minfeng-ai <42948406+minfenglu@users.noreply.github.com> Co-authored-by: Minfeng Lu <minfenglu@Minfengs-MacBook-Pro.local> Co-authored-by: Shlomi <81581678+jit-shlomi@users.noreply.github.com> Co-authored-by: Itai Steinherz <itaisteinherz@gmail.com> Co-authored-by: Boostrix <119627414+Boostrix@users.noreply.github.com> Co-authored-by: Kristian Jackson <kristian.jackson@gmail.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> Co-authored-by: Eduardo Salinas <edus@microsoft.com> Co-authored-by: prom3theu5 <dave@simcube.co.uk> Co-authored-by: dominic-ks <contact@bedevious.co.uk> Co-authored-by: andrey13771 <51243350+andrey13771@users.noreply.github.com> Co-authored-by: Marwand Ayubi <98717667+xhypeDE@users.noreply.github.com> Co-authored-by: mayubi <marwand@ayubi-it.de> Co-authored-by: Media <12145726+rihp@users.noreply.github.com> Co-authored-by: Cenny <cwenner@gmail.com> Co-authored-by: Abdelkarim Habouch <37211852+karimhabush@users.noreply.github.com>
Auto-GPT: An Autonomous GPT-4 Experiment
💡 Get help - Q&A or Discord 💬
🔴 🔴 🔴 Urgent: USE stable not master 🔴 🔴 🔴
Download the latest stable release from here: https://github.com/Significant-Gravitas/Auto-GPT/releases/latest.
The master branch may often be in a broken state.
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM "thoughts", to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.
Demo April 16th 2023
Demo made by Blake Werlinger
💖 Help Fund Auto-GPT's Development 💖
If you can spare a coffee, you can help to cover the costs of developing Auto-GPT and help to push the boundaries of fully autonomous AI! Your support is greatly appreciated. Development of this free, open-source project is made possible by all the contributors and sponsors. If you'd like to sponsor this project and have your avatar or company logo appear below click here.
🚀 Features
- 🌐 Internet access for searches and information gathering
- 💾 Long-term and short-term memory management
- 🧠 GPT-4 instances for text generation
- 🔗 Access to popular websites and platforms
- 🗃️ File storage and summarization with GPT-3.5
- 🔌 Extensibility with Plugins
Quickstart
- Check out the wiki
- Get an OpenAI API Key
- Download the latest release
- Follow the installation instructions
- Configure any additional features you want, or install some plugins
- Run the app
Please see the documentation for full setup instructions and configuration options.
📖 Documentation
⚠️ Limitations
This experiment aims to showcase the potential of GPT-4 but comes with some limitations:
- Not a polished application or product, just an experiment
- May not perform well in complex, real-world business scenarios. In fact, if it actually does, please share your results!
- Quite expensive to run, so set and monitor your API key limits with OpenAI!
🛡 Disclaimer
This project, Auto-GPT, is an experimental application and is provided "as-is" without any warranty, express or implied. By using this software, you agree to assume all risks associated with its use, including but not limited to data loss, system failure, or any other issues that may arise.
The developers and contributors of this project do not accept any responsibility or liability for any losses, damages, or other consequences that may occur as a result of using this software. You are solely responsible for any decisions and actions taken based on the information provided by Auto-GPT.
Please note that the use of the GPT-4 language model can be expensive due to its token usage. By utilizing this project, you acknowledge that you are responsible for monitoring and managing your own token usage and the associated costs. It is highly recommended to check your OpenAI API usage regularly and set up any necessary limits or alerts to prevent unexpected charges.
As an autonomous experiment, Auto-GPT may generate content or take actions that are not in line with real-world business practices or legal requirements. It is your responsibility to ensure that any actions or decisions made based on the output of this software comply with all applicable laws, regulations, and ethical standards. The developers and contributors of this project shall not be held responsible for any consequences arising from the use of this software.
By using Auto-GPT, you agree to indemnify, defend, and hold harmless the developers, contributors, and any affiliated parties from and against any and all claims, damages, losses, liabilities, costs, and expenses (including reasonable attorneys' fees) arising from your use of this software or your violation of these terms.
🐦 Connect with Us on Twitter
Stay up-to-date with the latest news, updates, and insights about Auto-GPT by following our Twitter accounts. Engage with the developer and the AI's own account for interesting discussions, project updates, and more.
- Developer: Follow @siggravitas for insights into the development process, project updates, and related topics from the creator of Entrepreneur-GPT.
- Entrepreneur-GPT: Join the conversation with the AI itself by following @En_GPT. Share your experiences, discuss the AI's outputs, and engage with the growing community of users.
We look forward to connecting with you and hearing your thoughts, ideas, and experiences with Auto-GPT. Join us on Twitter and let's explore the future of AI together!