- AI Legion
- Autonomous HR Chatbot
- Cody by ajhous44
- Cody by Sourcegraph
- English Compiler
- GPT Engineer
- GPT Migrate
- GPT Pilot
- GPT Researcher
- GPT Runner
- Lemon Agent
- Local GPT
- Loop GPT
- Mini AGI
- Multiagent Debate
- Multi GPT
- Open Interpreter
- Private GPT
- React Agent
- Smol developer
- Suspicion Agent
- Teenage AGI
- “Westworld” simulation
- Ability AI
- Adept AI
- Aide by Codestory
- Airplane Autopilot
- Butternut AI
- Codium AI
- Fine Tuner
- GitHub Copilot X
- GitLab Duo
- Heights Platform
- Hex Magic
- Minion AI
- Mutable AI
- Otherside’s AI Assistant
- Proficient AI
- ThinkChain AI
- v0 by Vercel
A browser-based implementation of AutoGPT, accessible via a no-code platform
- A no-code platform
- Assigning a goal to the agent
- Witnessing its thinking process
- Formulation of an execution plan
- Taking actions accordingly
- Uses OpenAI functions
- Supports gpt-3.5-16k, pinecone and pg_vector databases
- Frontend: NextJS + Typescript
- Backend: FastAPI + Python
- DB: MySQL through docker with the option of running SQLite locally
Agents is an open-source library/framework for building autonomous language agents.
- Long-short Term Memory: Language agents in the library are equipped with both long-term memory implemented via VectorDB + Semantic Search and short-term memory (working memory) maintained and updated by an LLM.
- Tool Usage: Language agents in the library can use any external tools via function-calling and developers can add customized tools/APIs here.
- Web Navigation: Language agents in the library can use search engines to navigate the web and get useful information.
- Multi-agent Communication: In addition to single language agents, the library supports building multi-agent systems in which language agents can communicate with other language agents and the environment. Different from most existing frameworks for multi-agent systems that use pre-defined rules to control the order for agents’ action, Agents includes a controller function that dynamically decides which agent will perform the next action using an LLM by considering the previous actions, the environment, and the target of the current states. This makes multi-agent communication more flexible.
- Human-Agent interaction: In addition to letting language agents communicate with each other in an environment, our framework seamlessly supports human users to play the role of the agent by himself/herself and input his/her own actions, and interact with other language agents in the environment.
- Symbolic Control: Different from existing frameworks for language agents that only use a simple task description to control the entire multi-agent system over the whole task completion process, Agents allows users to use an SOP (Standard Operation Process) that defines subgoals/subtasks for the overall task to customize fine-grained workflows for the language agents.
A platform for agents to work together, similar in spirit to AutoGPT and Baby AGI, but written in TypeScript
- An LLM-powered autonomous agent platform
- A framework for autonomous agents who can work together to accomplish tasks
- Interaction with agents done via console direct messages
A command line tool that lets you pair your program with GPT-3.5/GPT-4, to edit code stored in your local git repository
- Aider is a command line tool that lets you pair program with GPT-3.5/GPT-4, to edit code stored in your local git repository
- You can start a new project or work with an existing repo. And you can fluidly switch back and forth between the aider chat where you ask GPT to edit the code and your own editor to make changes yourself
- Aider makes sure edits from you and GPT are committed to git with sensible commit messages. Aider is unique in that it works well with pre-existing, larger codebases
An experimental open-source attempt to make GPT-4 fully autonomous, with >140k stars on GitHub
- Chains together LLM “thoughts”, to autonomously achieve whatever goal you set
- Internet access for searches and information gathering
- Long-term and short-term memory management
- Can execute many commands such as Google Search, browse websites, write to files, and execute Python files and much more
- GPT-4 instances for text generation
- Access to popular websites and platforms
- File storage and summarization with GPT-3.5
- Extensibility with Plugins
- “A lot like BabyAGI combined with LangChain tools”
- Features added in release 0.4.0
- File reading
- Commands customization
- Enhanced testing
Crafting a sophisticated system that autonomously generates its own code based on the context of your project.
- Model: GPT 4
- Automata takes your project as a context, receives tasks, and executes the instructions seamlessly.
- Automata aims to evolve into a fully autonomous, self-programming Artificial Intelligence system.
- It’s designed for seamless integration with all available agent platforms and LLM providers.
- Utilizes the novel code search algorithm, SymbolRank, and associated tools to build superior coding intelligence.
- Modular, fully configurable design with minimal reliance on external dependencies
- Author: Owen Colegrove
AI-generated pull requests to fix issues, powered by ChatGPT
- Triggered by adding a label containing AutoPR to an issue, AutoPR will:
- Plan a fix
- Write the code
- Push a branch
- Open a pull request
A prototype enterprise application – an Autonomous HR Assistant powered by GPT-3.5.
- An agent that can answer HR related queries autonomously using the tools it has on hand.
- Powered by GPT-3.5
- Current tools assigned to the agent (with more on the way):
- Timekeeping Policy
- Employee Data
- Medium: Creating a (mostly) Autonomous HR Assistant with ChatGPT and LangChain’s Agents and Tools
- Author: Stephen Bonifacio
- Video Demo: Youtube Link
A simple framework for managing tasks using AI
- A pared-down version of the original Task-Driven Autonomous Agent
- Creates tasks based on the result of previous tasks and a predefined objective.
- The script then uses OpenAI’s NLP capabilities to create new tasks based on the objective
- Leverages OpenAI’s GPT-4, pinecone vector search, and LangChainAI framework
- Default model is OpenAI GPT3-turbo
- The system maintains a task list for managing and prioritizing tasks
- It autonomously creates new tasks based on completed results and reprioritizes the task list accordingly, showcasing the adaptability of AI-powered language models
- Paper: Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications
- Founder’s Twitter
- Twitter thread describing the system
A task management and functionality expansion on top of BabyAGI
- A more advanced version of the original BabyAGI code
- Improves upon the original framework, by introducing a more complex task management prompt, allowing for more comprehensive analysis and synthesis of information
- Designed to handle multiple functions within one task management prompt
- Built on top of the GPT-4 architecture, resulting in slower processing speeds and occasional errors
- Provides a framework that can be further built upon and improved, paving the way for more sophisticated AI applications
- One of the significant differences between BabyAGI and BabyBeeAGI is the complexity of the task management prompt
BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI
- Just 300 lines of code
- This was built as a d iteration on the original BabyAGI code in a lightweight way. Differences to BabyAGI include the following:
- Task Creation Agent runs once
- Execution Agent loops through tasks
- Task dependencies for pulling relevant results
- Two tools: search tool and text completion
- “Mini-agent” as tool
- Search tool combines search, scrape, chunking, and extraction.
- Results combined to create summary report
BabyDeerAGI is a mod of BabyAGI, at ~350 lines of code
- Parallel tasks (making it faster)
- 3.5-turbo only (GPT-4 not required)
- User input tool
- Query rewrite in web search tool
- Saves results
Newest mod of BabyDeerAGI, and the OG BabyAGI, at ~895 lines of code
- Skills class allows for creation of new skills
- ‘Dynamic task list’ example with vector search
- Beta reflection agent
- Can read, write, and review its own code
An AI agent designed to test what happens when you combine CLI and LLM, which are more traditional interfaces than GUI (created by @saten-private)
- An AI agent based on @yoheinakajima’s BabyAGI which executes shell commands
- Automatic Programming, Successfully created an app automatically just by providing feedback. The procedure can be found here.
- Automatic Environment Setup, Successfully installed a Flutter environment on Linux in a container, created the Flutter app, and launched it. The procedure can be found here.
- Aside from setting up the environment, it seems to be able to handle a bit of general tasks such as Generating text, like poems, code, scripts, musical pieces, email, and letters, translating languages
- There is a risk of breaking the environment. Please run in a virtual environment such as Docker.
- GPT-4 or higher is recommended
Most recent mod of BabyAGI with a new parallel UI panel
- A mod of BabyElfAGI, in a series of mods w the naming of BabyAGI in alphabetical order
- Self-improving task lists (FOXY method)
- By storing a final reflection at the end, and pulling the most relevant reflection to guide future runs, BabyAGI slowly generates better and better tasks lists
- Novel Chat UI w parallel tasks
- You can chat w BabyAGI! It has an experimental UI where the chat is separate from the tasks/output panel, allowing you to request multiple tasks in parallel
- The Chat UI can use a single skill quickly, or chain multiple skills together using a tasklist
- New skills
- 🎨 DALL-E skill with prompt assist
- 🎶 Music player w Deezer
- 📊 Airtable search (add your own table/base ID)
- 🔍 Startup Analyst (example of beefy function call as a skill)
- It’s own README
The BambooAI library is a user-friendly semi-autonomous AI agent designed to make data exploration and analysis more accessible to non-programmers.
- BambooAI runs in a loop (until the user decides to end it).
- Allows the mixing of different models with different capabilities, token costs, and context windows for different tasks.
- Maintains the memory of previous conversations.
- Builds the prompts dynamically utilizing relevant context from Pinecone vector DB.
- Offers a narrative or asks follow-up questions if required.
- For codified responses, the task is broken down into a list of steps and a pseudo-code algorithm is built.
- Based on the algorithm, it uses Python code for dataset analysis, modeling, or plotting.
- Debugs the code which then executes, auto-corrects if needed, and displays the output to the user.
- Ranks the final answers, and asks the user for feedback.
- Builds a vector DB knowledge-base, based on the rank and the user feedback.
An Autonomous AI Assistant designed to perform a wide range of practical tasks autonomously
- “BeeBot is currently a work in progress and should be treated as an early-stage research project. Its focus is not on production usage at this time.”
A GPT-4 powered semantic code search engine that uses an AI agent
- Powered by GPT-4 and semantic code search, precise code navigation
- Built on stack graphs and scope queries
- Fast code search and regex matching engine written in Rust
- Allows to find Code on Rust and Typescript
- Allows to stage changes
- The agent searches both your local and remote repositories with natural language, regex, and filtered queries
- Bloop can be run via app (easy to download via GitHub)
A highly capable, autonomous AI Agent with an easy to use CLI, RESTful/WebSocket API, Pre-built Docker image and a robust suite of integrated tools.
- Support for all GPT-N, Embeddings and Dall-E OpenAI Models
- Support for Azure OpenAI Services
- Easy to use SDK for integration into any application
- Powerful Code Interpreter capabilities
- Powerful data query capabilities via Postgres DB integration
- Pre-built Docker image provides safe execution environment for code generation/execution
- Support for telephony applications (via BlandAI)
- Support for stock trading (via Alpaca Markets)
- Integrates with Gmail and Google Search
- Easy to install
pip install bondai
- To start the CLI just run
- To start the RESTful/WebSocket API just run
An open-source scheduling assistant built on Cal.com.
- Cal.ai can book meetings, summarize your week, and find time with others based on natural language.
- Responds flexibly to unseen tasks eg. “move my second-last meeting to tomorrow morning”.
- Uses GPT-4 and LangChain Agent Executor under the hood.
An agent architecture for “Mind” Exploration of Large Scale Language Model Society
- CAMEL is an open-source library designed for the study of autonomous and communicative agents. 1)AI user agent: give instructions to the AI assistant with the goal of completing the task.
- AI assistant agent: follows AI user’s instructions and responds with solutions to the task
- CAMEL also has an open-source community dedicated to the study of autonomous and communicative agents
- Paper – CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
- Colab demo
- Hugging face datasets
- Authors: Guohao Li∗ Hasan Abed Al Kader Hammoud* Hani Itani* Dmitrii Khizbullin, Bernard Ghanem
A chemistry agent that performs tasks across synthesis, drug discovery, and materials design
- ChemCrow is an open-source package for the accurate solution of reasoning-intensive chemical tasks
- It integrates 13 expert-design tools to augment LLM performance in chemistry and demonstrate effectiveness in automating chemical tasks
- Built with Langchain
- The LLM is provided with a list of tool names, descriptions of their utility, and details about the expected input/output. It is then instructed to answer a user-given prompt using the tools provided when necessary. The instruction suggests the model to follow the ReAct format – Thought, Action, Action Input, Observation. One interesting observation is that while the LLM-based evaluation concluded that GPT-4 and ChemCrow perform nearly equivalently, human evaluations with experts oriented towards the completion and chemical correctness of the solutions showed that ChemCrow outperforms GPT-4 by a large margin. This indicates a potential problem with using LLM to evaluate its own performance on domains that require deep expertise. The lack of expertise may cause LLMs not to know its flaws and thus cannot judge the correctness of task results.
The purpose of Clippy is to elop code for or with the user. It can plan, write, debug, and test some projects autonomously. For harder tasks, the best way to use it is to look at its work and provide feedback to it.
An AI assistant designed to let you interactively query your codebase using natural language. By utilizing vector embeddings, chunking, and OpenAI’s language models, Cody can help you navigate through your code in an efficient and intuitive manner.
An AI code assistant from Sourcegraph that writes code and answers questions for you by reading your entire codebase and the code graph.
An open-source autopilot for software development
- An open-source autopilot for software development—bring the power of ChatGPT to VS Code
- Answer coding questions
- Edit in natural language
- Generate files from scratch
The AI-first Code Editor. Build software faster in an editor designed for pair programming with AI.
A super-easy no-code platform for creating AI chatbots trained on your own data
- One of the easiest and fastest no-code platform I have encountered
- After creating new agent, picking a model, data and other settings, they are ready to be deployed to website, Slack, Crisp, or Zapier
- Limit of agent in the free version
- Joy UI
- Streamline customer support, onboard new team members, and more
- Load data from anywhere
- No-code: User-friendly interface to manage your datastores and chat with your data
- Secured API endpoint for querying your data
- Auto sync data sources (coming soon)
- Auto generates a ChatGPT Plugin for each datastore
An AI that enables quick demo generation for LLM-based applications using just prompts
- DemoGPT leverages the power of Language Models (LLMs) to provide fast and effective demo creation for applications.
- Automates the prototyping process, making it more efficient and saving valuable time.
- Understand and process the given prompts to generate relevant applications.
- Integrated with LangChain for generating application code through iterative parsing of LangChain’s documentation with a “Tree of Transformations” (ToT) approach.
- The roadmap for DemoGPT includes constant updates and improvements based on user feedback and real-world application, working towards refining the technology and solving the hallucination problem.
- “We are planning to introduce features that will further enhance the application generation process, making it more user-friendly and efficient.”
Team of virtual developers
- “Tell your AI team what microservice you want to build, and they will do it for you. Your imagination is the limit!!
- Welcome to Dev-GPT, where we bring your ideas to life with the power of advanced artificial intelligence! Our automated development team is designed to create microservices tailored to your specific needs, making your software development process seamless and efficient. Comprised of a virtual Product Manager, Developer, and DevOps, our AI team ensures that every aspect of your project is covered, from concept to deployment.
DevOpsGPT: AI-Driven Software Development Automation Solution
Welcome to the AI Driven Software Development Automation Solution, abbreviated as DevOpsGPT. We combine LLM with DevOps tools to convert natural language requirements into working software. This innovative feature greatly improves development efficiency, shortens development cycles, and reduces communication costs, resulting in higher-quality software delivery.
POC AI based Compiler, for converting english based markdown specs, into functional code
- “We know that all great™ projects start with awesome™ detailed functional specifications. Which is typically written in English, or its many other spoken language alternatives.
- So what if, instead of writing code from functional specs, we simply compile it directly to code?
- Into a future, where we replace nearly everything, with just written text.”
A developer assistant able to make a whole nodejs project with unlimited prompts
- Provides a core prompt for building the foundation of your application
- Allows you to add unlimited sections, each of which is a prompt representing a specific part of your app
- Friday utilizes GPT-4 for AI assistance, but it has been tested and optimized with GPT-4-32k for improved speed and better results.
- It requires 2 small requests for your app’s base and 1 request per section you provide.
- Friday employs esbuild behind the scenes for every app created by it.
- Author: Amirreza Salimi
An engineering Gen AI platform engineering team member
- GeniA is able to work along side you on your production enviroment, executing tasks on your behalf in your dev & cloud environments, AWS/k8s/Argo/GitHub etc.
- Allows you to enhance the platform by integrating your own tools and APIs.
- Slack App Bot integration.
- Supports GPT-3.5 & GPT-4.
A project inspired by Auto-GPT and BabyAGI, conducting various kinds of tasks via nice UI
- A web platform inspired by AutoGPT and BabyAGI
- What it can do:
- Order your coffee at Starbucks
- Perform market analysis
- Find and negotiate a lease
- Supports GPT-3.5 & GPT-4
An AI agent that generates an entire codebase based on a prompt
- Model: GPT 4
- Specify your project, and the AI agent asks for clarification, and then constructs the entire code base
- Made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt
- You can specify the “identity” of the AI agent by editing the files in the identity folder
- Editing the identity and evolving the main prompt is currently how you make the agent remember things between projects
- Each step in steps.py will have its communication history with GPT4 stored in the logs folder, and can be rerun with scripts/rerun_edited_message_logs.py
Easily migrate your codebase from one framework or language to another
- Pick from different LLMs
- Ability to allow GPT Migration to generate and run unit tests for the new codebase
- Ability to select source and target language of the migration
- Ability to customize the agent’s workflow (setup -> migrate -> test)
- GPT Migrate team is working on adding benchmarks for the agent
An agent that codes the entire app as you oversee the code being written
- Dev tool that writes scalable apps from scratch while the developer oversees the implementation
- A research project to see how can GPT-4 be utilized to generate fully working, production-ready, apps
- The main idea is that AI can write most of the code for an app (maybe 95%) but for the rest 5%, a developer is and will be needed until we get full AGI
GPT based autonomous agent that does online comprehensive research on any given topic
- Can produce detailed, factual and unbiased research reports
- Offers customization options for focusing on relevant resources, outlines, and lessons
- Addresses issues of speed and determinism, offering a more stable performance and increased speed through parallelized agent work, as opposed to synchronous operation
- Inspired by AutoGPT and the Plan-and-Solve paper
- The main idea is to run “planner” and “execution” agents, whereas the planner generates questions to research, and the execution agents seek the most related information based on each generated research question
Conversations with your files which selected! Manage and run your AI presets!
- Conversation with your files which selected by you, no embedding, no vector database!
- It’s also a AI Prompt Storybook. You can use it to manage some AI preset with your team. It support any IDE and language developer. We provide cli to run web and VSCode extension, Jetbrains plugin is coming soon.
- Private first, all data is local.
- We support both OpenAI and Anthropic (Claude-2)
- It support support for multiple languages.
IX is a platform for building, debugging, and deploying collaborative Agents and cognitive workflows.
IX is a LangChain based agent platform that includes all the tools to build and deploy fleets of agents that collaborate to complete tasks. IX is both an editor and a runtime. The editor is a no-code graph style editor for the design of agents, chains, tools, retrieval functions, and collaborative workflows.
- Intuitive graph style no-code editor.
- Horizontally scaling agent worker fleet.
- Multi-user, multi-agent chat interface.
- Smart input auto-completes
- Supports Chroma and other vector databases for document search.
- Supports OpenAI API, Anthropic, PaLM, and LLama based models.
- The component library is easily extended.
- Powered by LangChain
Plan-Validate-Solve (PVS) Agent for accurate, reliable, and reproducible workflow automation
- A standalone supervised Plan and Solve Agent specialized on performing read and write operations on various tools like GitHub, HubSpot or Airtable (ACL 2023 Paper “Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models“)
- Separation of tasks and human-in-the-loop interactions: Lemon Agent is currently holding a Planner Agent and a Solver Agent to keep the agents focussed and increase accuracy. We are planning on adding additional agents real soon. In addition, Lemon Agent will ask for approval at relevant workflow steps to make sure the intended actions are executed.
- Unlimited configuration options: Lemon Agent gives you unlimited configuration options (see example here) when defining your workflow. For instance, you can tell Lemon Agent to ask for permission before executing a workflow step or to drop a 🧔♀️ dad joke every time the model executes a workflow step.
- UI flexibility: Build any UI on top or engage with Lemon Agent via the built-in CLI.
- [Soon] Model & framework agnostic operations: Lemon Agent is a standalone agent, but can easily be integrated into frameworks like LangChain and be used with any model.
- Bonus: Identify weak spots in your agent’s decision-making capabilities and move to a more deterministic behavior by further configuring your Lemon Agent workflows. (.html file that can be run without any additional installation)
LocalGPT is an open-source initiative that allows you to converse with your documents without compromising your privacy
- Chat with your documents on your local device using GPT models. No data leaves your device and 100% private
- With everything running locally, you can be assured that no data ever leaves your computer
- Dive into the world of secure, local document interactions with LocalGPT
A re-implementation of the popular Auto-GPT project as a proper python package, written with modularity and extensibility in mind
- Languages: Python
- Default model: GPT-3.5-turbo (also possible with GPT-4)
- Modular Auto-GPT Framework
- Plug N Play” API – Extensible and modular “Pythonic” framework, not just a command line tool
- “Easy to add new features, integrations and custom agent capabilities, all from Python code, no nasty config files!”
- “Minimal prompt overhead – Every token counts. We are continuously working on getting the best results with the least possible number of tokens.”
- “Human in the Loop – Ability to “course correct” agents who go astray via human feedback.”
- “Full state serialization – can save the complete state of an agent, including memory and the states of its tools to a file or Python object. No external databases or vector stores required (but they are still supported)!”
Mentat is the AI tool that assists you with any coding task, right from your command line.
Unlike Copilot, Mentat coordinates edits across multiple locations and files. And unlike ChatGPT, Mentat already has the context of your project – no copy and pasting required!
A multi-agent framework that, given one line requirement, returns PRD, Design, Tasks, or Repo
- MetaGPT allows to assign different roles to GPTs to form a collaborative software entity for complex tasks
- It takes a one-line requirement as input and outputs user stories / competitive analysis/requirements/data structures / APIs / documents, etc.
- Internally, MetaGPT includes product managers/architects / project managers/engineers
- It provides the entire process of a software company along with carefully orchestrated SOPs. Code = SOP(Team) is the core philosophy
- The paper about LLM-based multi-agent work pushes forward the idea of autonomous agents collaborating with each other to do more than one can on its own.
- MetaGPT incorporates efficient human workflows as a meta-programming approach into LLM-based multi-agent collaboration
A minimal general-purpose autonomous agent based on GPT-3.5 / GPT-4
- MiniAGI is a minimal general-purpose autonomous agent based on GPT-3.5 / GPT-4
- Can analyze stock prices, perform network security tests, create art, and order pizza
- MiniAGI is a simple autonomous agent compatible with GPT-3.5-Turbo and GPT-4
- It combines a robust prompt with a minimal set of tools, chain-of-thoughts, and short-term memory with summarization
- Capable of inner monologue and self-criticism
An implementation of the paper “Improving Factuality and Reasoning in Language Models through Multiagent Debate”
- The paper illustrates how we may treat different instances of the same language models as a “multiagent society”, where individual language model generate and critique the language generations of other instances of the language model
- The authors find that the final answer generated after such a procedure is both more factually accurate and solves reasoning questions more accurately
- Illustrating the quantitative difference between multiagent debate and single agent generation on different domains in reasoning and factual validity
An experimental open-source attempt to make GPT-4 fully autonomous
- An experimental multi-agent system
- Multiple “expertGPTs” collaborate to perform a task
- Each with their own short and long-term memory and the ability to communicate with each other
- Set a task and watch the experts get to work.
- 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
An open-source AGI R&D platform that enables agents for both benchmark tasks and open-ended tasks
- Powered by various language models such as GPT-4, Vicuna, LLaMA, and Flan-T5
- Supports multi-modality tool learning and task solving such as text, image, video and audio
- Supports task decomposition into both linear task-solving plans and non-linear task-solving plans
- Allows both benchmark task-solving and open-ended task-solving
- Provides easy-to-use evaluation protocols to evaluate task-solving ability
- Provide Reinforcement Learning from Task Feedback (RLTF) to allow continuously self-improving agent
An open-source interpreter that lets LLMs run code on your computer to complete tasks
- Runs locally
- Can for example summarize PDFs, visualize datasets, control your browser
- Works from a ChatGPT-like interface in your terminal.
A development toolkit designed to streamline prompt design, version management, publishing, collaboration, troubleshooting, observability and more
- “Whether you are a technical person or a stakeholder, you can use Pezzo effectively. We don’t believe that AI prompts should be designed in a developer’s code editor. Aside from the technical issues with this approach, it blocks productivity.”
- Centralized Prompt Management: Manage all AI prompts in one place for maximum visibility and efficiency.
- Streamlined Prompt Design, Publishing & Versioning: Create, edit, test and publish prompts with ease.
- Observability: Access detailed prompt execution history, stats and metrics (duration, prompt cost, completion cost, etc.) for better insights.
- Troubleshooting: Effortlessly resolve issues with your prompts. Time travel to retroactively fine-tune failed prompts and commit the fix instantly.
- Cost Transparency: Gain comprehensive cost transparency across all prompts and AI models.
- Simplified Integration: Reduce code overhead by 90% by consuming your AI prompts using the Pezzo Client, regardless of the model provider.
A tool for private interaction with documents, without a need for an internet connection
- Built with LangChain, GPT4All, LlamaCpp, Chroma and SentenceTransformers
- A test project to validate the feasibility of a fully private solution for question answering using LLMs and Vector embeddings, not production ready
Personalized AI assistant that helps with nutrition and other goals
- “Personalized AI assistant that decomposes problems, offers solutions, and lets you use Agent actions to automate your flows”
- Helps users reach a solution by decomposing their requests into categories with a set of options (cuisine -> European)
- Has a dynamic UX/UI that helps avoid prompting
- Voice input supported
- Provides users with results of their queries and automates actions around them
- Remembers your past preferences and uses them to optimize your choices
- Powered by Langchain, decomposable async prompts + vector DB + Redis cache
- App built with Flutter + Dart
- Connected to Zapier NLP
An open-source React.js Autonomous LLM Agent
- An experimental autonomous agent
- Model: GPT-4
- Purpose: Gnerate and compose React components from user stories
- Radix UI
- Shandcn UI
- OpenAI API
- The agent is taking a user story text and generating and composing multiple react components to generate the relevant screens, based on atomic design principles
- Generate React Components from user stories
- Compose React Components from existing components
- Use a local design system to generate React Components
- Use React, TailwindCSS, Typescript, Radix UI, Shandcn UI
- Built with Atomic Design Principles
- It is still experimental but very interesting results, It is completely open-sourced, looking for contributors!
🐣 Your own junior developer. Deployed in few seconds via e2b
- Human-centric, coherent whole program synthesis
- Your own junior developer
- Allows to develop, debug, and decompile
- 200 LOC, half english
- 100k context can summarize both content and codebases
- Markdown is the best prompting DSL
- Copy and paste your errors as prompts
- Copy and paste curl output as prompts
- Write CSS animation by describing what u want
- GPT4 >>> GPT3.5/Anthropic Claude for codegen
Not a single agent, but a tool that allows creating agents without coding
- Simplifies the configuration and deployment of LLM Agents to production
- “One of the core principals of SuperAgent is to build with any third-party dependencies to proprietary tech”
- It provides a range of features and functionalities to make it easier for developers to build, manage and deploy AI agents to production including features such as built in memory and document retrieval via vector dbs, powerful tools, webhooks, cron jobs etc.
- There are two main types of agents: action agents and plan-and-execute agents
- Author: Ismail Pelaseyed
- Interview: Discussing agents’ tracing, observability, and debugging with Ismail Pelaseyed, the founder of Superagent
An open-source autonomous AI framework to enable development and deployment autonomous agents
- An AI agent framework
- Open source, but infrastructure is -source
- Provision, Spawn & Deploy Autonomous AI Agents
- Extend Agent Capabilities with Tools
- Run Concurrent Agents Seamlessly
- Graphical User Interface
- Action Console
- Multiple Vector DBs
- Multi-Modal Agents
- Agent Trajectory Fine-Tuning
- Performance Telemetry
- Optimized Token Usage
- Agent Memory Storage
- Looping Detection Heuristics
- Concurrent Agents
- Resource Manager
Playing Imperfect Information Games with Theory of Mind Aware GPT-4
- The paper delves into the applicability of GPT-4’s learned knowledge for imperfect information games
A Github assistant the helps fix small bugs and implement small features
- To install, click the install button
- Then add the repository you want, make a quick ticket (e.g. writing tests)
- Prepend the ticket with “Sweep:” and let Sweep handle the rest
- Interview: Sweep founders share learnings from building an AI coding assistant
- Tricks for prompting Sweep
A BabyAGI-inspired agent that can recall infinite memory, “thinks” before making action, and doesn’t lose memory after being shutting down
- Model: GPT-4
- Language: Python
- Uses OpenAI and Pinecone to give memory to an AI agent and also allows it to “think” before making an action (outputting text)
- Also, just by shutting down the AI, it doesn’t forget its memories since it lives on Pinecone and its memory counter saves the index that it’s on
- A process that happens every time the AI is queried by the user:
- AI vectorizes the query and stores it in a Pinecone Vector Database
- AI looks inside its memory and finds memories and past queries that are relevant to the current query
- AI thinks about what action to take
- AI stores the thought from Step 3
- Based on the thought from Step 3 and relevant memories from Step 2, AI generates an output
- AI stores the current query and its answer in its Pinecone vector database memory
- Created by @sean_pixel
- Inspired by paper “Generative Agents: Interactive Simulacra of Human Behavior”
A multi-agent simulation library, with a goal to simulate and optimize systems and environments with multiple agents interacting
- Researchers from Stanford and Google created an interactive sandbox env with 25 Gen AI agents can simulate human behavior
- They walk in the park, join for coffee at a cafe, and share news with colleagues. They demonstrated surprisingly good social
- Westworld’s inspiration is drawn from Unity software and Unity ML Agents, adapted in Python
- The library is available on PyPi via pip install westworld
- Easy creation of Grid and non-grid environments
- Objects (Agents, Obstacles, Collectibles, Triggers)
- Subclassing of different objects to create custom objects
- Spawner to generate objects randomly in the environment
- Basic rigid body system for all objects
- Simple agent behaviors (pathfinding, wandering, random walk, fleeing, vision range)
- Automatic maze generation
- Layer integration to convert image to obstacle and snap it to a grid
- Sample simulations and sample agents for classic simulations
- Simulation visualization, replay and export (gif or video)
- Underlying paper – Generative Agents
- A paper simulating interactions between tens of agents
- Presenting an architecture that extends a language model to store and synthesize the agent’s experiences, enabling dynamic behavior planning in an interactive sandbox environment with generative agents
A LLM-powered embodied lifelong learning agent in Minecraft
- A LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention
- Voyager consists of three key components:
- an automatic curriculum that maximizes exploration
- Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning
A GPT agent framework for invoking APIs
- WorkGPT is an agent framework in a similar fashion to AutoGPT or LangChain. You give it a directive and an array of APIs and it will converse back and forth with the AI until its directive is complete.
- For example, a directive could be to research the web for something, to crawl a website, or to order you an Uber. We support any and all APIs that can be represented with an OpenAPI file.
- WorkGPT now has OpenAI’s new function invocation feature baked into it
- While chaining together APIs was possible before (see AutoGPT), it was slow, expensive, and error prone
- The tweet announcing this feature
- Author: Alex MacCaw
yAgents is an Agent-Builder Agent made by Yeager.ai capable of designing, coding and debugging its own tools.
- Designed to help build, prototype, and deploy AI-powered tools and agents easily and efficiently.
- Built on the LangChain framework, it allows users of any technical background to create, improve, and deploy AI agents.
- Equipped with an interactive command line interface for real-time feedback and ease of navigation.
- Features session persistent memory to ensure data preservation across multiple sessions
- Quick and easy installation via pip.
- Contributions to expand and improve yAgents are highly encouraged.
- Requires GPT-4 API access.
- Not tested for Windows systems
Swift implementation of BabyAGI
- “This is a Swift port of BabyAGI, an example of an AI-powered task management system that uses OpenAI and Pinecone APIs to create, prioritize, and execute tasks. The main idea behind this system is that it creates tasks based on the result of previous tasks and a predefined objective.”
- Author: PJ Gray
Empowering Businesses with Secure, People-Centric Autonomous AI Agents
- Empowering Businesses with Secure, People-Centric Autonomous AI Agents
- Still in early version
A ML research and product lab building general intelligence by enabling humans and computers to work together creatively
- An AI teammate for everyone
- “Adept is building an entirely new way to get things done. It takes your goals, in plain language, and turns them into actions on the software you use every day.”
- In early stage
- “We’re building a machine learning model that can interact with everything on your computer.”
The AI-powered mod of VSCode
- Still in early stage, new features coming soon
- Now available for JS/TS
- Can the codebase, identify the root cause, make the fix and auto-generate tests to evaluate whether the bug was resolved
No-code platform for building AI agents
- AilaFlow is no-code platform for building AI agents
- Use a template, adjust it using no-code editor to your needs
- Category: Productivity, Framework for building agents
Airkit is a developer-first platform for building, testing, and deploying AI Agents.
- A browser based studio for managing prompts, building tools, and testing your agents.
- Built in short-term and long-term memory management
- 1 click deployment. Embed anywhere with our Web SDK.
Airplane is a company for building internal tools, they’re building their autopilot AI assistant.
- A developer-centric approach to building internal UIs and workflows
- Turning APIs, SQL queries, and scripts into apps for the entire team
- Allows to run tasks through a no-code dashboard
- Tasks for customer support, on-call runbooks, and scheduled tasks
An AI agent specifically designed for business intelligence
- Breaks down a high level research question into a step-by-step plan, and executes it
- Diverse tools, including a full web browser
- Can access internet information without the need for an API
- “We don’t generate content using AI, as it can be unreliable. Instead, we extract relevant information from trusted sources, cluster and process it into a user-friendly format.”
- AI-powered query planner intelligently routes and executes requests, ensuring correctness and diverse source selection
- Interview: David Zhang from Aomni gives his view agents’ reliability, debugging and orchestration
“Virtual intern for developers”, generates code via PRs raised against your repository
- Create an Issue
- Approve the Implementation Plan
- Review the Pull Request
- Writing code
- Reviewing changes
- Addressing comments
- Answering questions
- BitBuilder Junior
- BitBuilder Junior is an intern-level code generation tool that lives in your GitHub repository. It follows instructions to implement unambiguous code changes by changing multiple files, writing tests for generated code, and matching the style, framework, and libraries you’re already using.
AI no-code copilot that allows users to build AI apps.
- broadn is a no-code platform that helps non-technical people build AI products in minutes. We’re faster and more flexible than traditional no-code tools through an LLM powered conversational interface and an agent architecture that automates complex backend/workflow operations
- Conversational interface
- LLM/AI model connectors (text, image models, etc)
- Create bespoke chatbots
- Render UI components
- Connect to external data via APIs
A tool for creating a fully-functioning, ready-to-launch website in 20 seconds
- No coding required thanks to user-friendly interface
- Full SEO optimization
- Picture Upload: Users can conveniently upload and regenerate their own pictures for unlimited customization of their profiles
- Profile Customization: Users have the flexibility to customize their profiles by hiding sections, adding social media links, and sharing contact details, allowing them to showcase their unique personality and brand
- Instant Preview: Users can instantly visualize their profile changes through a conveniently placed preview button, ensuring a quick assessment of the desired appearance
- 30% Faster Speed: The app achieves an impressive 30% increase in website generation speed, providing users with a fast and efficient website building experience.
AI-powered interactive code integrity dev tool enabling developers to ship software faster and with fewer bugs
- Generating meaningful tests for busy devs
- Exploring and analyzing your code, docstrings, comments, and by interacting with you
- Non-trivial tests (and trivial, too!) suggested right inside your IDE
- Generates tests
- Covers edge cases
- Best practice, readability code suggestions
- Gives you the code explanation
- It is free
Career Copilot and AI Agent for Software Developers
- Comprehensive job search
- Accurate job recommendations based on your skills, experience, and preferences
- AI-powered auto-applications
Web based version of AutoGPT/babyAGI
- Friendly UI for building AI agents
- Author: Sully Omarr
- Interview: About deployment, evaluation, and testing of agents with Sully Omar, the CEO of Cognosys AI
AI-powered design tools for everything from copywriting to generating unique icons from text, recently acquired by Figma
- Magic Copy writes, edits, and rewrites Figma text layers so you can design with real copy
- Generating images in Figma while designing
- Magic Rename intelligently names your layers so you can spend more time designing
- Magician works right inside your favorite design tool (e.g., Figma)
- Possible to get all the latest AI design advancements + future spells in one convenient plugin
Dot, the data bot – a virtual assistant that help with analytics
- Dot allows to chat with your Data Warehouse (e.g. Snowflake, BigQuery, RedShift, Postgres …) or Semantic Layer (e.g. Looker, dbt, dotML).
- Answer most business questions instantly 24/7, so data teams can focus on deep work, not on answering easy questions about dashboards
- Category: Research, Business intelligence, Data analysis
A fully autonomous software engineer
- in alpha
- encode works with you and your team to get work done
- demo: https://encode.software/demo
Working on autonomous coding Droids for building software end-to-end
- In aplha stage
- It’s not supposed to be just another coding copilots like GitHub Copilot or Codeium, but autonomous agents capable of autonomously building software from end to end
Build Software with AI Agents. Leverage AI to the maximum and x10 your dev velocity.
- Deploy, manage, and run AI agents that serve as your virtual teammates.
- Built for teams, with organizational memory and collaboration in mind.
- Privacy oriented, we don’t store your code, everything runs locally.
- Multiagent platform: Build your own custom agents.
Platform for no-code building of AI agents
- With Fine-Tuner, you can build sophisticated, tailored AI agents at scale without any need for technical skills or coding. Just bring your data and ideas, and we’ll provide the toolset you need to transform them into powerful AI solutions, capable of handling vast amounts of data and users. Take advantage of our scalable platform to meet your growing needs with ease and efficiency
- Connecting Your Chatbot to Your App
- FineTuner.ai is a no-code AI platform that enables users to create and deploy custom AI agents and components without any coding. With an intuitive UI/UX and rapid API deployment, FineTuner.ai simplifies AI development, allowing users to focus on their unique use cases and ideas.
4.1. Access the API tab for an overview of the required tokens and parameters to connect your chatbot to your app using REST API endpoints.
- The Fine-Tuner REST API provides API endpoints for Fine-Tuner data types that allow to interact with your AI models remotely by sending and receiving JSON
- Authentication to the Fine-Tuner API is performed via HTTP Bearer Authentication
- Front end: Bubble
A platform for creating LLM-powered apps like AI agents
- Building and managing LLM powered applications
- A cloud-based platform-as-a-service that allows developers to build smart agents that couple LLMs with back-end logic to interface to data, systems, and tools
An AI executive assistant that automates communication busywork.
- Works across all your communication and work tools: emails, social media DMs, calendar, Notion, etc.
- Adapted to your work habits.
- Ask your assistant to:
- Craft messages
- Summarize, extract tasks and information
AI-powered software developer
- AI pair programmer
- Chat and terminal interfaces
- Support for pull requests
- Early adoption of OpenAI’s GPT-4
A suite of AI capabilities for every step of the software development lifecycle
- A suite of AI-powered capabilities for #DevSecOps workflows
- A toolbox of features integrated into the DevSecOps Platform to help teams across the entire software development environment become more efficient
- Examples of what GitLab Duo can do:
- Planning refinement
- Security risk resolution
- CI/CD pipeline health
- Analytics charting.
A tool automating code generation, in beta version, created for full-stack developers
- GitWit uses a GPT-based agent to generate code and git to track changes made to files
- GitWit ties together large language models and modern developer tools
- It can spawn and modify codebases using just a single prompt
- GitWit is primarily aimed at full-stack developers, and is particularly loved by those with a learning mindset—such as those learning a new stack or technology
- It is in early beta and may require some experimentation with the prompts you enter
- You are offered to choose from code bases:
- React + NextJS
- Python using pip
- An AngularJS using npm.
- Custom stack
A first of it’s kind multimodal content creation agent
- Category: General purpose, Productivity, Generating apps
A beta version of a tool for fixing technical gap automatically, putting code migrations and dependency upgrades on autopilot
- Grit uses machine learning and static analysis to auto-generate pull requests for cleaning up technical debt
- Users can declare how they want their code to be structured and let Grit rewrite it for them
Your AI Coach and and AI Copilot for course creators, community builders, and coaches. Built into an all-in-one course creation and community software.
- Heights AI Chat can make edits to your digital products, answer support questions, and provide advice on growing your business.
- Heights AI Coach is your personal autonomous coach, helping you accomplish your unique goals
- Your AI coach will ask you questions and analyze the products you create to provide you with new tasks and recommendations every week.
- Information you share with your AI Coach will never be shared with another creator’s AI Coach.
- Any information submitted will never be used for AI language model training data.
Hex AI-powered tools for humans doing amazing things with data
- “A suite of powerful AI features meant to augment data people”
- Hex can explain and document your code
- Hex Magic features know about database schemas, past operations, and the project’s execution graph, so they can make deeper, more insightful recommendations
You can see more – and sign up for the waitlist – over here.
Personal assistant for life: to keep you on top of your calendar, tasks and information
- Personal assistant for life: to keep you on top of your calendar, tasks and information
- Currently in a beta version
Julius AI allows data processing, analysis, and visualization
- Chat-powered data analytics and AI agents, all in a notebook interface
- Allows to answer any question about users’ data with a single prompt
- An intelligent data analyst tool that interprets, analyzes, and visualizes complex data in an intuitive, user-friendly manner
- “Jupyter Notebooks on steroids”
Web Scraping on Autopilot with AI
- Using LLMs to generate web scrapers and data processing steps on the fly that adapt to website changes.
- No coding or browser extension is required.
- The autonomous crawling agent efficiently locates the desired information on websites.
- Adaptability to website changes makes it maintenance-free
- Transforms data from multiple sources into the same structure
- Handles all clicking and scrolling automatically
- Handles proxies
- Powerful integrations
An AI assistant that can help with daily tasks, e.g., calendar management, email drafting, and contract sending
- Lindy is still in a beta version
- Lindy triages your email
- It learns from your inbox and automatically surfaces the highest-priority emails for you
- Automatic conflict handling
- Daily briefing
- Contract management
- Meeting note taking
- Author: Flo Crivello
Made by creator of GitHub Copilot, so far in a waitlist stage
AI personal agent, holding the record for the first AI flight booking, food order (a burger) & workplace cert
- The agent runs and controls the local Google Chrome, which allows it to interact with the world/services/web apps, just like people interact with the world/services/web apps using Google Chrome
- The agent itself probably also runs locally and currently, it needs the local Google Chrome to function
- Our understanding from the demo video is that they use local code and a custom plugin in ChatGPT to control a web browser (e.g., Google Chrome). This setup enables MultiOn to perform tasks like ordering plane tickets as if a human were interacting with the browser directly
- Use cases
- A lot of cool real use cases, e.g., -Sending an email fully autonomously -Posting a tweet -Sending a tweet reply to a specific person with a specific message -Sending a Facebook message to a friend -Searching for vacation rentals and check pricing for an upcoming trip -Searching for a wedding venue and starting the wedding planning process -Scheduling a car wash
- After introducing the GPT function calling, MultiOn can call itself recursively to spawn more sub-agents
- Instead of calling multiple functions or APIs you just need one Universal Function that can interact with all services and have it call itself to accomplish more complex tasks in parallel
AI Accelerated Software Development
- AI Autocomplete
- Production Quality Code with One Click
- Prompt driven development
- Test Generation (coming soon)
Still in an early stage, with waitlist for early access
“Build your team of AI agents that work for you. Early access now live. Join waitlist.”
An AI browsing assistant for everyday tasks, can operate a web browser to complete nearly any task
- AI agent that can use a web browser like a human
- “Just describe what you want it to do, and it will automatically operate Chrome to achieve your task.”
- Examples of use cases: Booking flights, ordering food, researching complex topics, managing your email
- Designed to handle tasks from booking flights to conducting in-depth research, and everything in between.
- Examples of usage:
- Organize Gmail inbox
- Booking a flight
- Ordering online
- Finding hire candidates
Personal programming and research assistant
- Phind is an AI search engine and pair programmer
Interaction APIs and SDKs that allow developers to build, deploy and operate conversational AI agents in their apps
- An end-to-end solution, with which it takes 3 minutes not weeks to get a user-facing agent up and running in your app (currently 3 SDKs including React)
- Powerful tools built into the admin dashboard and Admin API including analytics, monitoring, rate-limiting, content moderation, etc.
- minimizes or eliminates the need for custom backend infrastructure so you can focus on implementing the business logic
- Technology-agnostic solution that supports multiple LLM providers (currently 7 models from OpenAI and Anthropic) allowing you to easily switch between models with 1 click
- Ready-to-use, highly customizable and beautiful UI components rendering complex interaction trees with support for advanced features like streaming
Questflow is a marketplace for autonomous AI workers with no-code.
- Questflow is a marketplace designed for SMBs to connect with autonomous AI workers.
- Our platform enables digital workers to discover and deploy AI agents for seamless workflow automation.
- With a no-code editor, we empower digital knowledge providers to create, distribute, and monetize AI workers.
- Similar to Upwork, Questflow offers a marketplace where users can utilize AI agents to accomplish tasks across various digital workspaces.
- Creators have the opportunity to transform their specialized knowledge into AI agents, expanding their reach and generating revenue.
A digital AI assistant, an AI-powered workspace integrating notes, tasks, and tools
- Generating content
- Brainstorming ideas
- Grammer check
Automated migrations and upgrades for every codebase
- Perform major version upgrades on any number of applications, of any size
- Upgrade frameworks such as Next.js 12 to 13, libraries such as MUI 4 to 5, or languages such as Python 2 to 3
- Target users: enterprise codebases
AutoGPT agents with plugins
- “Delegate your tasks to autonomous AI agents. Transform your daily work with revolutionary and intuitive AI tools powered by GPT4”
- Access APIs like Zapier, Wolfram, etc.
- Open links
- Manipulate files
- Search web
Add an AI copilot to your product’s data dashboard with just a few lines of code.
- Get set up in minutes with the Superluminal React component, or use the API directly for custom solutions.
- Writes Python code to answer questions and perform tasks, similar to ChatGPT + CodeInterpreter.
- Fully managed compute infrastructure for the secure execution of generated code.
- Customize the look and feel to fit your product.
- Full support for graphs, pivots and filters in addition to textual answers.
- Enable your customers to extract more value from the data already on their dashboard with meaningful answers to high-level questions.
TalktoData AI allows advanced data discovery, cleaing, analysis, and visualization
- AI Data Analyst that works with your CSV, Excel, Goolge Sheets and SQL Databases
- AI Agent for all the data analytics needs
- Allows users to generate beautiful visualizations, followup question and refine requirements
- “ChatGPT for Data Analysis”
- A Data Analyst the never sleeps and always available(A chat away)
A financial AI agent platform using your own knowledge base
- ThinkChain provides a large and growing set of advanced AI agents, e.g.
- Discover agent – can access search and your Knowledge base for informed answers
- Chain of Thought agent – breaks questions into parts to be addressed independently
- Analyst agent – creates realtime financial analysis, from DCF to LBO and everything in between
- Auto Agent – can create an entire workflow from scratch
- Currently in an early access version
v0 is a generative user interface system by Vercel Labs powered by AI. It generates copy-and-paste friendly React code based on Shadcn UI and Tailwind CSS.
- Currently in waitlist stage
- v0 generates custom components on the fly that you can copy and paste into your existing codebase
- Built on NextJS App Router
- AI by the Vercel
Wispy is a web-browsing AI assistant that can summarize content, compose content, explain things or create quizzes for topics you are learning
- Wispy is stil in Beta version
- With Wispy, you can effortlessly transform web content to perfectly suit your unique needs, all without leaving the comfort of your browser
- Chat-based AI like Llama and GPT-4 are not the only ways to incorporate AI into your life
- With Wispy, go beyond chatbots with a browser-native AI companion that makes your browsing more delightful, productive, and streamlined!
Join Guidady AI Mail List
Subscribe to our mailing list and get interesting stuff and updates to your email inbox.