Skip to content

Releases: Significant-Gravitas/AutoGPT

AutoGPT Platform v0.3.3

20 Nov 23:33
@Pwuts Pwuts
autogpt-platform-beta-v0.3.3
13da8af
This commit was signed with the committer’s verified signature.
Pwuts Reinier van der Leer
GPG key ID: BEB9E26CB6F21336
Learn about vigilant mode.
Compare
Choose a tag to compare
AutoGPT Platform v0.3.3 Latest
Latest

UI/UX Improvements 💻

  • fix(frontend): Allow importing agent file with empty description by @Pwuts in #8670
  • fix(backend): Improve input typing for blocks StepThroughItemsBlock, CountdownTimerBlock, AddToListBlock, AddToDictionaryBlock by @majdyz in #8713
  • feat(frontend): Show Agent Output on Monitor page by @kcze in #8501
  • feat(platform): Updates to Runner Output UI by @Bentlybro in #8717

Technical Improvements ⚙️

  • refactor(platform): Remove settings endpoint by @aarushik93 in #8715
  • fix(frontend): Fix duplicate API calls on Monitor Page by @majdyz in #8727
  • fix(block): Renamed model_version input to prevent conflicts with Pydantic naming by @Swiftyos in #8729
  • test(frontend): Add simple auth tests by @ntindle in #8709

DX improvements 👷🏼

  • dx(backend): Fix pre-commit isort step by @Pwuts in #8726
  • docs(platform): update docs for security ssrf by @ntindle in #8675
  • docs: replace docker-compose with docker compose by @simoneb in #8502

New Contributors 🎉

How to Get This Update 📥

To update to this version, use:

git pull origin agpt-platform-beta-v0.3.3

Or download it directly from the Releases page.

Feedback and Issues 📝

If you encounter any issues or have suggestions, please join our Discord and let us know!

Full Changelog: autogpt-platform-beta-v0.3.2...autogpt-platform-beta-v0.3.3

Contributors

simoneb, dagelf, and 7 other contributors
Assets 2
Loading

autogpt-platform-beta-v0.3.2

18 Nov 21:01
@aarushik93 aarushik93
autogpt-platform-beta-v0.3.2
8fccf2e
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
autogpt-platform-beta-v0.3.2

🚀 What's New in v0.3.2?

🌟 New Features

  • feat(backend): Enable JSON parsing with typing & conversion (#8578) by @majdyz
  • feat(blocks): Add Open Router integration with a large selection of new models (#8653) by @Torantulino

🛠 Fixes & Improvements

  • fix(backend): Add migrations to fix credentials inputs (#8674) by @Pwuts
  • fix(backend): Resolve Pydantic warning about missing secrets_dir (#8692) by @Pwuts
  • fix(backend): Define executionmanager hostname for local docker-mode (#8681) by @majdyz
  • fix(frontend): Typing in the NodeKeyValueInput field no longer unfocuses the field (#8680) by @majdyz
  • fix(frontend): Avoid displaying overly long description text for blocks (#8688) by @majdyz
  • fix(platform/builder): Add heartbeat mechanism (#8665) by @aarushik93
  • fix(backend): Add a lower cap of zero for user credits (#8682) by @majdyz
  • fix(backend): Avoid falling back to default user unless ENABLED_AUTH is set to False (#8691) by @majdyz

📚 Documentation Updates

🛠 Build & Refactor

  • refactor(frontend): Updated buttons for editing agents in Monitor (#8687) by @kcze
  • build(frontend): Optimize Docker build time and image size (#8695) by @Pwuts

🔗 Full Changelog: Compare v0.3.1...v0.3.2

Contributors

Pwuts, Torantulino, and 3 other contributors
Assets 2
Loading

AutoGPT Platform v0.3.1

18 Nov 11:19
@Pwuts Pwuts
autogpt-platform-beta-v0.3.1
bff0dc3
This commit was signed with the committer’s verified signature.
Pwuts Reinier van der Leer
GPG key ID: BEB9E26CB6F21336
Learn about vigilant mode.
Compare
Choose a tag to compare
AutoGPT Platform v0.3.1

v0.3.1 is a patched re-release of v0.3.0.

Highlights ✨

  • Agent Execution Block 🤖
    The Agent Execution Block has been introduced, allowing users to use agents as blocks within other agents. This powerful new feature makes it possible to build modular complex agents.

  • Scheduling Agent Runner ⏰
    Users can now schedule agents to run at specific times using the new scheduling functionality in the UI. Monitor and manage your scheduled agents easily from the dedicated monitor page.

New Blocks and Enhancements 🧩

  • AI Image Generator Block 🖼️
    The AI Image Generator Block has been added, providing a unified interface for generating images using various AI models. Users can now easily generate images within their workflows.

  • AI Music Generator Block 🎵
    Introducing the AI Music Generator Block, powered by Meta Music Gen. Users can now generate music directly within the AutoGPT platform, opening up exciting possibilities for audio-based workflows.

  • YouTube Video Block Enhancements 🌍
    The YouTube Video Block now supports additional languages, expanding its capabilities for a broader range of users and use cases.

UI/UX Improvements 💻

  • Centered Initial Canvas 🎨
    The initial canvas in the UI is now centered, providing a more visually appealing and user-friendly experience.

  • Client-side Validation 🚦
    Client-side validation has been implemented for the Agent Executor Block, ensuring a smoother and more reliable user experience.

  • Credentials Input Enhancements 🔒
    The credentials input UI has been enhanced to provide a more intuitive and streamlined experience. Double titles have been removed, and credentials are now automatically selected when there is only one option available.

  • Authentication Checks 🔐
    Authentication checks have been added to ensure that only authorized users can perform certain actions within the platform.

  • Improved Error Transparency ⚠️
    Communication of errors in the front end has been improved, to help users understand and resolve issues with their graphs.

Bug Fixes and Optimizations 🐛

  • Input Field Updates 📝
    Fixed an issue where newly typed text in input fields would vanish on scroll, providing a more stable editing experience.

  • Block Cost Configuration 💰
    The block cost configuration has been refactored and centralized into a single file, making it easier to manage and update costs for various blocks.

  • Dependency Updates 📦
    Several dependencies have been updated to their latest versions, enhancing security, performance, and compatibility.

  • Error Handling and Logging 💡
    Improved error handling and logging mechanisms have been implemented across various components, facilitating better debugging and troubleshooting.

Miscellaneous Changes 🌟

  • The project's version has been bumped to v0.3.1.
  • Default credentials are now mapped to actual provider names (e.g., anthropic) for better clarity.
  • Hidden credentials have been introduced for default system keys, ensuring they are not visible in the user profile.

📥 How to Get This Update

To update to this version, use:

git pull origin agpt-platform-beta-v0.3.1

Or download it directly from the Releases page.

📝 Feedback and Issues

If you encounter any issues or have suggestions, please join our Discord and let us know!

Full Changelist

  • feat(block): Add AI Music Generator Block with Meta Music Gen by @Torantulino in #8532
  • build(deps): bump peter-evans/repository-dispatch from 2 to 3 by @dependabot in #8609
  • [Snyk] Security upgrade python from 3.11-slim-buster to 3.11.10-slim-bookworm by @ntindle in #8619
  • build(deps): bump supabase from 2.9.1 to 2.10.0 in /autogpt_platform/autogpt_libs in the production-dependencies group by @dependabot in #8617
  • build(deps-dev): bump ruff from 0.7.2 to 0.7.3 in /autogpt_platform/autogpt_libs in the development-dependencies group by @dependabot in #8618
  • build(deps-dev): bump the development-dependencies group in /autogpt_platform/market with 2 updates by @dependabot in #8612
  • build(deps): bump the production-dependencies group in /autogpt_platform/backend with 2 updates by @dependabot in #8610
  • build(deps-dev): bump the development-dependencies group in /autogpt_platform/frontend with 12 updates by @dependabot in #8615
  • build(deps): bump the production-dependencies group in /autogpt_platform/frontend with 8 updates by @dependabot in #8614
  • build(deps-dev): bump the development-dependencies group in /autogpt_platform/backend with 3 updates by @dependabot in #8611
  • [Snyk] Security upgrade urllib3 from 2.0.7 to 2.2.2 by @ntindle in #8620
  • build(deps): bump cookie from 0.7.0 to 1.0.1 in /autogpt_platform/frontend by @dependabot in #8616
  • [Snyk] Security upgrade zipp from 3.15.0 to 3.19.1 by @ntindle in #8622
  • fix: show error toast on Run failure when inputs or credentials are i… by @Abhi1992002 in #8391
  • feat(platform): Introduced Agent Execution Block by @majdyz in #8533
  • refactor(backend): Centralize Block Cost into a Single File by @majdyz in #8623
  • feat(platform): Simplify Credentials UX by @kcze in #8524
  • fix(frontend): Unbreak credentials input on single-provider blocks by @Pwuts in #8636
  • tweak(backend): Update all block costs by @Torantulino in #8639
  • Adding Google Analytics to docs site by @kbarnard10 in #8640
  • fix(frontend): Fix client-side validation for Agent Executor Block by @majdyz in #8643
  • fix(classic): update docs for security deprecation by @ntindle in #8632
  • fix(frontend): Remove double title on credentials input by @Pwuts in #8638
  • Create SECURITY.md by @ntindle in #8645
  • fix(platform): Remove migrate and encrypt function by @aarushik93 in #8646
  • fix(frontend): Fix input-field update on empty & default value by @majdyz in #8647
  • feat(frontend): Center initial canvas by @majdyz in #8644
  • Add provision for other languages in Youtube Video Block by @vishesh10 in #8630
  • tweak(frontend): Add jina and unreal to hidden credentials list in frontend by @Torantulino in #8642
  • feat(frontend): check auth before allowing actions to run by @ntindle in #8633
  • feat(blocks): Add AIImageGeneratorBlock by @Torantulino in #8525
  • feat(platform): Add api generator functions and endpoints by @Abhi1992002 in #8597
  • feat(platform) : scheduling agent runner by @Abhi1992002 in #8634
  • Feat(Builder/tutorial): Updates to fix tutorial by @Bentlybro in #8655
  • Revert "fix(platform): Remove migrate and encrypt function" by @Pwuts in #8654
  • ci: fix classic ci by @ntindle in #8338
  • fix(frontend): Newly typed text in Input fields vanishes on scroll by @majdyz in #8657
  • fix(backend): Add execution persistence for execution scheduler service by @majdyz in #8649
  • fix(backend): Add migrations to fix credentials inputs with invalid provider "llm" by @Pwuts in #8674

Full Changelog: autogpt-platform-beta-v0.2.2...autogpt-platform-beta-v0.3.1

Contributors

vishesh10, ntindle, and 9 other contributors
Assets 2
Loading

autogpt-platform-beta-v0.2.2

11 Nov 00:34
@aarushik93 aarushik93
autogpt-platform-beta-v0.2.2
e6e4737
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
autogpt-platform-beta-v0.2.2

What's Changed 🚀

DX Improvements
🛠️ Fix pre-commit configuration #8584 by @Pwuts
🧹 Clean up PR template #8541 by @Pwuts

New Features
🔍 Pinecone blocks added #8535 by @aarushik93
🔐 API key database table introduced #8593 by @aarushik93
⚙️ Default credentials for Jina blocks #8603 by @aarushik93

Build Enhancements
🐛 Add launch.json for VSCode debugging #8496 by @ntindle

Full Changelog: Compare v0.2.1...v0.2.2

Assets 2
Loading

autogpt-platform-beta-v0.2.1

08 Nov 04:49
@aarushik93 aarushik93
autogpt-platform-beta-v0.2.1
d6ecf80
Compare
Choose a tag to compare
autogpt-platform-beta-v0.2.1

🚀 What's Changed

🎉 New Contributors

Full Changelog: compare v0.2.0...v0.2.1

Contributors

ntindle, Swiftyos, and 5 other contributors
Assets 2
Loading

agpt-platform-beta-v0.2.0

31 Oct 02:50
@aarushik93 aarushik93
agpt-platform-beta-v0.2.0
74d8aa6
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
agpt-platform-beta-v0.2.0

What's Changed

Infrastructure & Security

  • Updated Secrets Management: Implemented a new approach to secrets handling, including secret rotation and resealing, to enhance security (#8505, #8506).
  • Infrastructure Update: Improved environment configuration with updated variable names (#8447) and fixed production workload identity pool (#8456).

Feature Enhancements

  • Blocks System: Added support for Pinecone and Jina blocks to improve modularity (#8401).
  • Platform Improvements: Added default secrets (#8452) and removed dotenv for a streamlined configuration process (#8459).

Dependency Updates

  • Frontend: Updated react-day-picker to 9.2.0 (#8442) and several other development dependencies.
  • Backend: Bumped versions for websockets (#8477), sentry-sdk (#8475), psutil (#8473), tenacity (#8472), and other libraries to improve stability and performance.
  • CI & Build Tools: Updated several GitHub Actions and build dependencies, including setup-python, setup-helm, create-pull-request, and others for better CI/CD performance and compatibility.

Fixes & Optimizations

  • Backend Optimization: Refined the RedisEventQueue to use Pub/Sub and optimized FastAPI event handling to prevent blocking (#8387, #8429).
  • Frontend Security: Addressed an object pollution issue for better security (#8499).

Documentation

  • Improved Navigation: Updated documentation navigation to enhance platform usability (#8448).

New Contributors

Thanks to our new contributor!

Full Changelog: View all changes

Contributors

niranjan-kurhade
Assets 2
Loading

agpt-platform-beta-v0.1.1

24 Oct 18:55
@aarushik93 aarushik93
agpt-platform-beta-v0.1.1
08a8abe
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
agpt-platform-beta-v0.1.1

What's Changed

New Contributors

Full Changelog: agpt-platform-beta-v0.1.0...agpt-platform-beta-v0.1.1

Contributors

ntindle, Pwuts, and 7 other contributors
Assets 2
Loading

agpt-platform-beta-v0.1.0

17 Oct 11:55
@aarushik93 aarushik93
agpt-platform-beta-v0.1.0
fca8d61
Compare
Choose a tag to compare
agpt-platform-beta-v0.1.0

🚀 Release agpt-platform-beta-v0.1.0

Date: October 21, 2024

🔥 What's New?

  • New Features
    - Copy and Paste Blocks: Added the ability to copy and paste blocks between different flows, improving user efficiency (#8346).
    - Shared DB Connection: Introduced a shared DB connection for executors, optimizing resource management (#8340).
    - Credential Management: Listed and revoked credentials in the user profile for easier account management (#8207).
    - Configmap Usage: Introduced usage of configmap for enhanced builder configuration management (#8343).
    - Updated Block UI: Improved the block UI for a better user interface experience (#8260).

  • Enhancements
    - Behave Variable: Added behave as a variable for enhanced flexibility in Platform/Frontend (#8365).
    - Health Router: Included a health router for improved monitoring in Platform (#8362).
    - Backend Health Check: Updated backend server health check endpoint for better reliability (#8351).
    - Node Workers Optimization: Reduced the number of node workers to optimize database connections (#8331).
    - Health Endpoint: Added a health endpoint to enhance security in Platform/Backend (#8341).

    • Sealed Secrets: Implemented sealed secrets to improve security around sensitive data (#8342).

  • 🐛 Bug Fixes

    • Market URL Resealing: Resolved the issue with market URL resealing (#8363).
    • Agent Pagination and Search: Fixed pagination and search errors for agents (#8336).
    • Sealed Secret Names: Fixed sealed secret names to ensure proper handling (#8350).
    • Input Styling: Fixed styling inconsistencies in input elements for a more consistent user experience (#8337).
    • Dynamic Pin Links: Fixed connection clash on dynamic pin links with the same keys (#8252).
    • Secret Value Leakage: Prevented marketplace from leaking secret values (#8281).
    • Secret Value Deletion: Updated deletion process for secret values to ensure proper handling (#8284).
    • OAuth Credential Validation: Ensured the validity of OAuth credentials during graph execution (#8191).

  • 🧱 New Blocks
    - Block Documentation: Added comprehensive documentation for all available blocks, improving clarity and usability (#8289).

🎉 Thanks to Our Contributors!

A special shoutout to all the amazing contributors who made this release possible:

  • 👏 All contributors involved in the mentioned pull requests

📥 How to Get This Update

To update to this version, use:

git pull origin agpt-platform-beta-v0.1.0

Or download it directly from the Releases page.

📝 Feedback and Issues

If you encounter any issues or have suggestions, please join our Discord and let us know!

Assets 2
Loading

AutoGPT v0.5.1

26 Apr 20:15
@Pwuts Pwuts
autogpt-v0.5.1
26324f2
Compare
Choose a tag to compare
AutoGPT v0.5.1

New Features ✨

  • New OpenAI Models 🤖

    • gpt-4-turbo is now supported and set as the default SMART_LLM model.
    • Default FAST_LLM changed from gpt-3.5-turbo-16k to gpt-3.5-turbo.
    • Default EMBEDDING_MODEL changed from text-embedding-ada-002 to text-embedding-3-small.
    • Added support for gpt-4-0125-preview and gpt-4-turbo models.

  • Agent Protocol Server Enhancements 🌐

    • Made API server port configurable via AP_SERVER_PORT environment variable.
    • Added documentation for configuring the API port.
    • Implemented task cost tracking and logging in the AgentProtocolServer.

  • CLI Usability Improvements 💻

    • Added a check to ensure the specified API server port is available before running.
    • Improved handling of invalid or empty tasks provided by the user.
    • Display information on whether code execution is enabled or not on CLI startup.

  • Web Browsing Enhancements 🌐

    • Added browser extensions to handle cookie walls and ads when using Selenium.
    • Added extract_information function to extract pieces of information from webpage content based on a list of topics of interest. The read_webpage command now supports topics_of_interest and get_raw_content parameters to leverage this capability.

  • Telemetry & Error Tracking 📊

    • Integrated Sentry for telemetry and error tracking.
    • Added configuration flow and opt-in prompt for enabling telemetry.
    • Distinguish between production and dev environments based on VCS state.
    • Capture exceptions for LLM parsing errors and command failures.

  • File Storage Abstraction 📂

    • Fully abstracted file storage access with the FileStorage class.
    • Renamed FileWorkspace to FileStorage and updated associated classes and methods.
    • Updated AgentManager and AgentProtocolServer to use the new FileStorage system.

  • History Compression 📜

    • Implemented history compression to reduce token usage and increase longevity when using models with limited context windows.

Fixes 🔧

  • JSON Parsing Robustness

    • Implemented json_loads for more tolerant JSON parsing of llm responses.
    • Updated extract_dict_from_response to handle both json and JSON blocks in responses.
    • Fixed boolean value decoding issues in extract_dict_from_response.

  • Error Handling

    • Added error handling for loading non-existing agents.
    • Fixed handling of action_history related exceptions in CLI and Server modes.
    • Implemented self-correction mechanism for invalid LLM responses by appending error messages to the prompt.

  • Artifact & File Handling

    • Fixed handling of artifact modifications by setting agent_created attribute instead of registering a new Artifact.
    • Fixed read_file command in GCS and S3 workspaces.

  • Dependency Updates & Security Fixes

    • Updated aiohttp and fastapi dependencies to mitigate vulnerabilities.
    • Fixed Content-Type Header ReDoS vulnerabilities in python-multipart.

  • TTY Mode Enhancements

    • Fixed finish command behavior in TTY mode.
    • Agent now properly raises AgentTerminated exception to exit the loop.

  • Miscellaneous Fixes

    • Fixed summarize_text and QueryLanguageModel abilities to handle OpenAI API changes.
    • Improved representation of optional command parameters in prompts.
    • Fixed GCS workspace binary file upload.
    • Moved auto-gpt-plugin-template to regular dependencies to fix missing module error.

Chores & Refactoring 🧹

  • Updated agbenchmark and autogpt-forge dependencies across the project.
  • Upgraded OpenAI library to v1 and refactored code to accommodate API changes.
  • Improved logging by capturing errors raised during action execution.
  • Cleaned up unused imports and fixed linting issues across the codebase.
  • Sped up test_gcs_file_workspace by changing the fixture scope.

Pull Requests

Note: most of the changes mentioned above were made through direct commits. See also the full changelog.

  • [Documentation Update] Updating Using and Creating Abilities to use Action Annotations by @himsmittal in #6653
  • AGBenchmark: Codebase clean-up by @Pwuts in #6650
  • fix: cast port to int by @orarbel in #6643
  • Add documentation on how to use Agent Protocol in .env.template by @ntindle in #6569
  • feat(benchmark): JungleGym WebArena by @Pwuts in #6691
  • fix No modules named 'forge.sdk.abilities' and 'forge.sdk' #6537 #5810 by @kfern in #6571
  • feat(agent/web): Add browser extensions to deal with cookie walls and ads by @Pwuts in #6778
  • fix(forge): no module named 'sdk' by @MKdir98 in #6822
  • Adding support to allow for sending a message with the enter key by @zedatrix in #6378
  • Fixed revising constraints and best practices by @ThunderDrag in #6777
  • Set subprocess.PIPE on stdin and stderr and just let pytest run the currentt file when running main() by @aorwall in #5868
  • Update execute_code.py by @ehtec in #6903
  • fix(agent/execute_code): Disable code execution commands when Docker is unavailable by @kcze in #6888
  • OPEN-133: Fix trying to load non-existing agent by @kcze in #6938
  • Fixing support for AzureOpenAI by @edwardsp in #6927
  • OPEN-165: Improvement - check for duplicate command by @kcze in #6937
  • chore: Change agbenchmark to directory dependency in autogpt and forge by @Pwuts in #6946
  • Create Security Policy by @joycebrum in #6900
  • feat(agent): Abstract file storage access by @kcze in #6931
  • fix(autogpt): Fix GCS and S3 root path issue by @kcze in #7010
  • feat(autogpt/forge): Send exception details in agent protocol endpoints by @kcze in #7005
  • fix(agent): Handle action_history-related exceptions gracefully by @kcze in #6990
  • fix(autogpt/cli): Loop until non-empty task is provided by the user by @kcze in #6995
  • docs: Redirect AutoGPT users from Forge tutorial with warning by @ntindle in #7014
  • docs: replace polyfill.io by @SukkaW in #6952
  • feat(autogpt/cli): Check if port is available before running server by @kcze in #6996
  • feat(autogpt/cli): Display info if code execution is enabled by @kcze in #6997
  • feat(agent): Implement more tolerant json_loads function by @kcze in #7016
  • ci(agent): Matrix CI tests across Linux, macOS and Windows by @Pwuts in #7029
  • feat(agent): Handle OpenAI API key exceptions gracefully by @kcze in #6992
  • test(agent): Fix VCRpy request filter for cross-platform use by @Pwuts in #7040
  • ci(agent): Add macOS ARM64 to AutoGPT Python CI matrix by @Pwuts in #7041
  • security(agent): Replace unsafe pyyaml loader with SafeLoader by @matheudev in #7035
  • fix(agent): Fix check when loading an existing agent by @kcze in #7026
  • fix(agent, forge): Conform web_search.py to duckduckgo_search v5 by @kcze in #7045
  • fix(agent, forge): Conform web_search.py to duckduckgo_search v5 by @kcze in #7046
  • fix(agent): Make save_state behave like save as by @kcze in #7025
  • refactor(agent): Refactor & improve create_chat_completion by @Pwuts in #7082

New Contributors

Read more

Contributors

aorwall, orarbel, and 13 other contributors
Assets 2
Loading

AutoGPT v0.5.0

14 Dec 15:17
@Pwuts Pwuts
autogpt-v0.5.0
af3ebdf
Compare
Choose a tag to compare
AutoGPT v0.5.0

First some important notes w.r.t. using the application:

  • run.sh has been renamed to autogpt.sh
  • The project has been restructured. The AutoGPT Agent is now located in autogpts/autogpt.
  • The application no longer uses a single workspace for all tasks. Instead, every task that you run the agent on creates a new workspace folder. See the usage guide for more information.

New features ✨

  • Agent Protocol 🔌
    Our agent now works with the Agent Protocol, a REST API that allows creating tasks and executing the agent's step-by-step process. This allows integration with other applications, and we also use it to connect to the agent through the UI.
  • UI 💻
    With the aforementioned Agent Protocol integration comes the benefit of using our own open-source Agent UI. Easily create, use, and chat with multiple agents from one interface.
    When starting the application through the project's new CLI, it runs with the new frontend by default, with benchmarking capabilities. Running autogpt.sh serve in the subproject folder (autogpts/autogpt) will also serve the new frontend, but without benchmarking functionality.
    Running the application the "old-fashioned" way, with the terminal interface (let's call it TTY mode), is still possible with autogpt.sh run.
  • Resuming agents 🔄️
    In TTY mode, the application will now save the agent's state when quitting, and allows resuming where you left off at a later time!
  • GCS and S3 workspace backends 📦
    To further support running the application as part of a larger system, Google Cloud Storage and S3 workspace backends were added. Configuration options for this can be found in .env.template.
  • Documentation Rewrite 📖
    The documentation has been restructured and mostly rewritten to clarify and simplify the instructions, and also to accommodate the other subprojects that are now in the repo.
  • New Project CLI 🔧
    The project has a new CLI to provide easier usage of all of the components that are now in the repo: different agents, frontend and benchmark. More info can be found here.
  • Docker dev build 🐳
    In addition to the regular Docker release images (latest, v0.5.0 in this case), we now also publish a latest-dev image that always contains the latest working build from master. This allows you to try out the latest bleeding edge version, but be aware that these builds may contain bugs!

Architecture changes & improvements 👷🏼

  • PromptStrategy
    To make it easier to harness the power of LLMs and use them to fulfil tasks within the application, we adopted the PromptStrategy class from autogpt.core (AKA re-arch) to encapsulate prompt generation and response parsing throughout the application.

  • Config modularization
    To reduce the complexity of the application's config structure, parts of the monolithic Config have been moved into smaller, tightly scoped config objects. Also, the logic for building the configuration from environment variables was decentralized to make it all a lot more maintainable.
    This is mostly made possible by the autogpt.core.configuration module, which was also expanded with a few new features for it. Most notably, the new from_env attribute on the UserConfigurable field decorator and corresponding logic in SystemConfiguration.from_env() and related functions.

  • Monorepo
    As mentioned, the repo has been restructured to accommodate the AutoGPT Agent, Forge, AGBenchmark and the new Frontend.

    • AutoGPT Agent has been moved to autogpts/autogpt
    • Forge now lives in autogpts/forge, and the project's new CLI makes it easy to create new Forge-based agents.
    • AGBenchmark -> benchmark
    • Frontend -> frontend

    See also the README.

Pull Requests

Note: most of the changes mentioned above were made through direct commits. See also the full changelog.

  • Sync release into master by @lc0rp in #5118
  • Add files via upload by @ntindle in #5130
  • Fix speak mode with elevenlabs falling into error by @dannaward in #5127
  • Agent loop v2: Planning & Task Management (part 2) by @Pwuts in #5077
  • fix(docker): add gcc installation in order to build psutil by @alexsoyes in #5059
  • Fix elevenLabs config error by @dannaward in #5131
  • Update init.py to support image_gen commands by @dmoham1476 in #5137
  • Fixed stream elements speech function by @NeonN3mesis in #5146
  • Restructure Repo by @merwanehamadi in #5160
  • Refactor/remove abstract singleton as voice base parent by @collijk in #4931
  • Add support for args to execute_python_file by @MauroDruwel in #3972
  • read me update for monorepo by @SilenNaihin in #5199
  • Change agbenchmark folder by @merwanehamadi in #5203
  • Integrate benchmark and autogpt by @merwanehamadi in #5208
  • Migrate AutoGPT agent to poetry by @Pwuts in #5219
  • Adding Space After Colon in Console Input Prompt by @WilliamEspegren in #5211
  • AutoGPT: use config and LLM provider from core by @Pwuts in #5286
  • Rename Auto-GPT to AutoGPT by @merwanehamadi in #5301
  • AutoGPT: Move all the Agent's prompt generation code into a PromptStrategy by @Pwuts in #5363
  • Fixed stacking prompt instructions by @NeonN3mesis in #5520
  • AutoGPT: Implement Agent Protocol by @Pwuts in #5612
  • Fix typo in exceptions.py by @eltociear in #5813
  • docs: fix typos in markdown files by @shresthasurav in #5871
  • feat: Add support for new models and features from OpenAI's November 6 update by @Pwuts in #6147
  • Improve the accuracy of the extract_dict_from_response method's JSON extraction. by @HawkClaws in #5458
  • Allow port numbers to be used in local host names. e.g. localhost:8888. by @aaron13100 in #5318
  • Streamline documentation for getting started by @Pwuts in #6335
  • Fix docker build. Changing agbenchmark dependency as git reference instead of folder reference. by @warnyul in #6274
  • refactor(agent/config): Modularize Config and revive Azure support by @Pwuts in #6497
  • feat(agent/workspace): Add GCS and S3 FileWorkspace providers by @Pwuts in #6485
  • Add dependencies required to use PostgreSQL by @ntindle in #6558
  • Updating duckduckgo-search version to v4.0.0 to unbreak web_search command by @zedatrix in #6557 d820239

New Contributors 🧙🏼

Contributors

zedatrix, warnyul, and 16 other contributors
Assets 2
Loading