Entrepreneur GPT Versions Save

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

autogpt-v0.5.0

4 months ago

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.

New Contributors 🧙🏼

agbenchmark-v0.0.10

7 months ago

v0.4.7

8 months ago

AutoGPT v0.4.7 introduces initial REST API support, powered by e2b's agent protocol SDK. It also includes improvements to prompt generation and support for our new benchmarking tool, Auto-GPT-Benchmarks.

We've also moved our documentation to Material Theme at https://docs.agpt.co. And, as usual, we've squashed a few bugs and made under-the-hood improvements.

What's Changed

New Contributors

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.6...v0.4.7

v0.4.6

9 months ago

What's Changed

Improvements ✨

Bugfixes 🐛

Re-arch 🏗️

New Contributors

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.5...v0.4.6

v0.4.5

9 months ago

This maintenance release includes under-the-hood improvements and bug fixes, such as more accurate token counts for OpenAI functions, faster CI builds, improved plugin handling, and refactoring of the Config class for better maintainability.

Release Highlights 🌟

We have released some documentation updates, including:

How to share system logs

Auto-GPT re-architecture documentation

New Contributors & Notable Catalysts 🦾

What's Changed 📜

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.4...v0.4.5

v0.4.4

9 months ago

Auto-GPT v0.4.4 is dedicated to the core re-arch tram, led by @collijk.

Release Highlights 🌟

This release is noteworthy for two reasons.

Auto-GPT-4

Firstly, it comes hot on the heels of OpenAI's GA release of GPT-4. Auto-GPT users have eagerly awaited the opportunity to unlock more power via a GPT-4 model pairing. In v0.4.4, the SMART_LLM (formerly SMART_LLM_MODEL) defaults to GPT-4 once again, and we have implemented adjustments to ensure the correct usage of SMART_LLM and FAST_LLM (formerly FAST_LLM_MODEL) throughout the code-base. The smarter option is used consistently for areas requiring state-of-the-art accuracy, such as agent command selection. At the same time, the faster LLM assists with tasks that even the speedier GPT-3.5-turbo excels at, like summarization.

Note: GPT-4 is costlier, so please review your SMART_* and FAST_* settings. You can also use --gpt3only and --gpt4only command line flags to adjust your model preferences at runtime.

Autogpt/core

The second reason, and the reason for the dedication at the beginning of these release notes, is equally exciting. The much-anticipated re-arch is now available! The team, led by @collijk, has worked tirelessly over the past few months to put the "Auto" back in Auto-GPT, nearly doubling the code available in the master branch. The autogpt/core folder contains the work from the re-arch project, which is now systematically making its way to the rest of the application, starting with the Configuration modules. Watch for improvements over the next few weeks. There is still much to do, so if you wish to assist, please check out this issue.

New Contributors & Notable Catalysts 🦾

What's Changed 📜

Besides the highlights above, this release cleans up longstanding Azure configuration rough edges, fixes plugin incompatibilities and plugs security. Read on for a detailed list of changes.

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.3...v0.4.4

v0.4.3

10 months ago

We're excited to present the 0.4.3 maintenance release of Auto-GPT! This update primarily focuses on refining the LLM command execution, extending support for OpenAI's latest models (including the powerful GPT-3 16k model), and laying the groundwork for future compatibility with OpenAI's innovative function calling feature.

Release Highlights 🌟

  • OpenAI API Key Prompt: Auto-GPT will now courteously prompt users for their OpenAI API key, if it's not already provided.
  • Summarization Enhancements: We've optimized Auto-GPT's use of the LLM context window even further, boosting the effectiveness of summarization tasks.
  • JSON Memory Reading: Support for reading memories from JSON files has been improved, resulting in enhanced task execution.
  • New "replace_in_file" Command: This nifty new feature allows Auto-GPT to modify files without loading them entirely.
  • Enhanced Token Counting: We've refined our token counting system to provide more precise cost estimates.

Deprecated Commands ❌

As part of our ongoing commitment to refining Auto-GPT, the following commands, which we determined to be either better suited as plugins or redundant, have been retired from the core application:

  • analyze_code
  • write_tests
  • improve_code
  • audio_text
  • web_playwright
  • web_requests

Progress Update on Re-Architecting 🚧

As you may recall, we recently embarked on a significant re-architecting journey to future-proof the Auto-GPT project. We're thrilled to report that elements of this massive overhaul are now being integrated back into the core application. For instance, you may notice less reliance on global state being passed around via singletons.

Stay tuned for further updates and advancements in our future releases! Head over to the discussion forums or discord to share your feedback on this release, and we appreciate your continued support.

New Contributors & Notable Catalysts 🦾

What's Changed 📜

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.2...v0.4.3

v0.4.3-alpha

10 months ago

We're excited to present the 0.4.3 maintenance release of Auto-GPT! This update primarily focuses on refining the LLM command execution, extending support for OpenAI's latest models (including the powerful GPT-3 16k model), and laying the groundwork for future compatibility with OpenAI's innovative function calling feature.

Release Highlights 🌟

  • OpenAI API Key Prompt: Auto-GPT will now courteously prompt users for their OpenAI API key, if it's not already provided.
  • Summarization Enhancements: We've optimized Auto-GPT's use of the LLM context window even further, boosting the effectiveness of summarization tasks.
  • JSON Memory Reading: Support for reading memories from JSON files has been improved, resulting in enhanced task execution.
  • New "replace_in_file" Command: This nifty new feature allows Auto-GPT to modify files without loading them entirely.
  • Enhanced Token Counting: We've refined our token counting system to provide more precise cost estimates.

Deprecated Commands ❌

As part of our ongoing commitment to refining Auto-GPT, the following commands, which we determined to be either better suited as plugins or redundant, have been retired from the core application:

  • analyze_code
  • write_tests
  • improve_code
  • audio_text
  • web_playwright
  • web_requests

Progress Update on Re-Architecting 🚧

As you may recall, we recently embarked on a significant re-architecting journey to future-proof the Auto-GPT project. We're thrilled to report that elements of this massive overhaul are now being integrated back into the core application. For instance, you may notice less reliance on global state being passed around via singletons.

Stay tuned for further updates and advancements in our future releases! Head over to the discussion forums or discord to share your feedback on this release, and we appreciate your continued support.

New Contributors & Notable Catalysts 🦾

What's Changed 📜

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.2...v0.4.3-alpha

v0.4.2

10 months ago

The 503 error has been more frequent the past hours so we added a hotfix to retry the call if this error is returned, otherwise Auto-GPT stops.

v0.4.1

10 months ago

This release focuses on improving command reliability and fixing bugs from version 0.4.0. Some internal changes have been made that pave the way for the highly anticipated 0.5.0 major release.

As usual, this release cannot have happened without Auto-GPT's ever-enthusiastic community. Hop over to the discussion boards to discuss this release and more.

This time round, we're highlighting "New Contributors" before the longer changelog details, and including testers, PR-reviewers and other active community members. We may keep this new format in future releases.

Highlights ✨

  • Directory-based plugins! - Great news! Plugins no longer have to be compressed into zip files. Simply placing a plugin in a subfolder or repository clone within the plugins directory will now allow it to be recognized and loaded.
  • Keyboard navigation! - People who are "less mouse, more keyboard" will love this.
  • JSON fixes - Several prompts and JSON problems have been resolved, leading to a more dependable selection and execution of commands.
  • More dependable search - Internet searching is now more reliable and less prone to errors thanks to Auto-GPT's improved ability to detect duckduckgo rate limits. The tool now automatically retries searches when these limits are reached.
  • Better read_file - Building on the expansion of the read_file command in version 0.4.0, further improvements have been made to Auto-GPT's reading and writing of files.
  • More reliable Python code execution - Similarly, Auto-GPT should choke less when creating or executing Python code, and now has the ability to do so within a Docker install
  • To round up the highlights, the configuration of allowed/denied shell commands has been simplified and made less confusing, and batch summarization of LLM message history should address some identified crashes caused by the summarization process.

New Contributors & Notable Catalysts

Changelog

Full Changelog: https://github.com/Significant-Gravitas/Auto-GPT/compare/v0.4.0...v0.4.1