e4d84dad0a
This commit incorporates significant enhancements to the SkillTreeViewModel, introducing the ability to track current benchmark runs and submit results to the leaderboard. A new list, `currentBenchmarkRuns`, is introduced to store each benchmark run object during a specific benchmark session. This list is reset to an empty state when initiating a new benchmark. Changes made: - Introduced `currentBenchmarkRuns` to track ongoing benchmark runs, ensuring real-time data availability. - Enhanced `runBenchmark` method to populate `currentBenchmarkRuns` with benchmark run objects as the benchmark progresses. - Implemented `submitToLeaderboard` method, accepting parameters `teamName`, `repoUrl`, and `agentGitCommitSha`, and updating each run object with this information. All runs share a common UUID generated at the beginning of the submission process. These enhancements ensure that benchmark run data is readily available and organized, facilitating a streamlined process for submitting well-structured data to the leaderboard. It fosters a more interactive and informative user experience, offering insights into each benchmark run's progress and outcomes.
🌟 AutoGPT: the heart of the open-source agent ecosystem
AutoGPT is your go-to toolkit for supercharging agents. With its modular and extensible framework, you're empowered to focus on:
- 🏗️ Building - Lay the foundation for something amazing.
- 🧪 Testing - Fine-tune your agent to perfection.
- 👀 Viewing - See your progress come to life.
Be part of the revolution! AutoGPT stays at the forefront of AI innovation, featuring the codebase for the reigning champion in the Open-Source ecosystem.
We're hosting a Hackathon!
Click the banner above for details and registration!
🥇 Current Best Agent: AutoGPT
Among our currently benchmarked agents, AutoGPT scores the best. This will change after the hackathon - the top-performing generalist agent will earn the esteemed position as the primary AutoGPT 🎊
📈 To enter, submit your benchmark run through the UI.
🌟 Quickstart
-
To build your own agent and to be eligible for the hackathon, follow the quickstart guide here. This will guide you through the process of creating your own agent and using the benchmark and user interface.
-
To activate the best agent follow the guide here.
Want to build your own groundbreaking agent using AutoGPT? 🛠️ There are three major components to focus on:
🏗️ the Forge
Forge your future! The forge is your innovation lab. All the boilerplate code is already handled, letting you channel all your creativity into building a revolutionary agent. It's more than a starting point, it's a launchpad for your ideas. All tutorials are located here.
🎯 the Benchmark
Test to impress! The benchmark offers a stringent testing environment. Our framework allows for autonomous, objective performance evaluations, ensuring your agents are primed for real-world action.
🎮 the UI
Take Control! The frontend is your personal command center. It gives you a user-friendly interface to control and monitor your agents, making it easier to bring your ideas to life.
🔄 Agent Protocol
🔌 Standardize to Maximize! To maintain a uniform standard and ensure seamless compatibility, AutoGPT employs the agent protocol from the AI Engineer Foundation. This standardizes the communication pathways from your agent to the frontend and benchmark.
🤔 Questions? Problems? Suggestions?
Get help - Discord 💬
To report a bug or request a feature, create a GitHub Issue. Please ensure someone else hasn’t created an issue for the same topic.