Awesome List of AI Agents

🔗 Follow Slava for more agentic AI resources

• 🐦 Twitter • 💼 LinkedIn • 🐙 Github

This project tracks the latest agentic AI projects and provides a list of 100+ resources, curated by Slava Kurilyak

Wait But Why

AI agents outperform LLMs

According to @andrewyng, "GPT-3.5 with an agentic workflow actually outperforms GPT-4"

Hire Me

Do you have an idea for an AI agent or are you looking for an agentic AI solution?

Schedule a discovery call with me

Disclaimer: I am the Founder/CEO at Produvia

At Produvia, we partner with $7M+ in revenue brands to develop custom AI agents

AI Agents

Here's an awesome list of AI agents:

AgentX: AgentX is an AI-powered sales assistant designed to enhance sales strategies and efficiency through advanced features like a Memory Module and Online Mode, leveraging industry best practices for smarter selling | website | twitter | newsletter
Devin by Cognition: Devin is a fully autonomous AI software engineer, revolutionizing coding with advanced reasoning and planning capabilities | announcement | website
OpenDevin: OpenDevin is an open-source initiative aimed at replicating and enhancing the autonomous AI software engineer Devin, focusing on collaboration and complex task execution in software development, emphasizing its relevance to advancing agentic AI technologies | github | github profile
Devika: Devika is an open-source AI software engineer designed to understand and execute high-level coding tasks by researching, planning, and writing code, aiming to be a competitive alternative to Cognition AI's Devin | github | demo | discord
Codel: Autonomous AI agent, inspired by Devin, designed for complex task execution with features like a secure sandboxed Docker environment, integrated browser for real-time web information, text editor, and PostgreSQL database for history tracking, highlighting its relevance to agentic AI through its ability to autonomously navigate and perform actions across terminal, browser, and editor interfaces | announcement | github | github user
GPT Pilot: GPT Pilot is an open-source AI developer tool that aims to provide a comprehensive development companion, capable of writing features, debugging, and interacting with users, presenting itself as an alternative to Devin, the world's first AI software engineer developed by Cognition Labs | github | discord
Devon (previously Gilfoyle): Devon, not Devin, aims to perfect code correction for fill-in-the-middle, bug spotting, and completion tasks, using JSON for metadata in edits, and incorporates looping until user termination in function updates | github
Hume AI: Hume AI offers empathic AI solutions with emotional intelligence through APIs for interpreting emotional expressions and generating empathic responses, aimed at enhancing human well-being and enabling developers to create AI agents with improved understanding and engagement | website | discord
AutoDev: AutoDev is an AI-powered coding assistant offering multilingual support, automatic code generation, and debugging assistance, featuring customizable prompts and specialized tools for development, testing, documentation, and the integration of custom AI agents, with a focus on experimenting and building AI agents using its UI framework | github | docs
vimGPT: vimGPT is a project that integrates GPT-4V's vision capabilities with the Vimium extension to enable web browsing and interaction through keyboard navigation and voice commands, offering innovative solutions and improvements for accessibility and efficiency | github | demo | hackernews
OpenPipe: Optimize AI agents with language models that are faster and 14x more cost-effective than OpenAI's solutions | demo
Waii: A swift and straightforward AI agent for converting natural language to SQL queries, seamlessly integrable with your application | demo
Data Questionnaire Agent: A chatbot designed to query users on data integration practices, offering advice based on responses, utilizing a modified Chainlit library for operation | github
Cosmo: Cosmo offers an all-inclusive AI agent for merchants on WhatsApp, enabling order placements, customer interaction, automatic question answering, inventory and CRM integration, with features like instant payments, customer insights, dynamic order fulfillment, and a comprehensive merchant web app for online transaction management, aimed at simplifying shopping and boosting sales by 57% | website | demo
Deepgram: Conversational AI tools designed for creating voice bots and agents, featuring realistic, low-latency voice technology | demo
Deepunit: An AI agent designed to generate unit tests for complete code coverage across your project, requiring only your repository as input | demo
GitWit: GitWit is an online tool that accelerates web app development with AI, supporting React, Tailwind, and NodeJS, boasting a 3X speed increase and over 1000 projects generated | website | discord | github profile
Harpa: Harpa is a versatile Chrome extension that integrates AI capabilities, such as summarizing content, automating workflows, and enhancing productivity, supported by GPT-4 and Claude 2, trusted by 300,000+ professionals | website
AI Assistant by Deco: Deco provides a GPT-powered, multilingual AI Sales Assistant designed to personalize and automate the shopping experience, boost sales, and increase operational efficiency for online stores | website | github profile
FinGen: FinGen is a financial analysis agent using RSC, LangChain, and Polygon finance API, emphasizing it's not financial advice and requires API keys for use | announcement | github | github user
Self Operating Computer by Otherside: Self Operating Computer (SOC) enables multimodal models to autonomously interact with a computer using human-like inputs and outputs, compatible with various models, and under ongoing development for more accurate functionalities | landing page | github |github profile
MultiOn: MultiOn utilizes AI to automate actions within web browsers, such as form filling, data retrieval, and executing web searches, mimicking human interaction but without manual input, facilitated through a Chrome extension and API for developers | website
ChatGPT by OpenAI: ChatGPT is an AI language model designed to understand and generate human-like text, facilitating conversation and assisting with various tasks | website | website org
Open Interpreter: Open Interpreter is a coding agent enabling language models to execute code locally, facilitating natural-language interaction with your computer's capabilities, overcoming limitations of hosted solutions like internet access and package restrictions, with features including interactive and programmatic chats, system message customization, and more, allowing for enhanced control and flexibility in development environments | github
AnyBiz: AnyBiz offers AI-driven sales agents that enhance sales strategies through intelligent automation, continuous learning, and hyper-personalization, operating 24/7 without breaks | website
ShortGPT by RayVentura: ShortGPT is an AI-powered framework for automating content creation, including video editing, voiceover synthesis, caption generation, and asset sourcing, with support for multiple languages and seamless integration with Google Colab and Docker for easy deployment | github | github profile
ShortX by RayVentura: ShortX is a AI-powered video automation platform for YouTube Shorts, Instagram Reels, TikTok, and Snapchat, offering customizable templates, AI services, and a subscription model with an affiliate program and user testimonials | website
GPT Engineer: GPT-Engineer is an AI-powered tool allowing users to specify software in natural language, automatically generating and executing code, with options for improvement suggestions, and fostering collaboration within the open-source community | github | github profile | [website](https://gptengineer.app
Self Operating Computer by Otherside: SOC is a framework enabling multimodal models to operate a computer using human-like inputs and outputs, with compatibility for various models such as GPT-4v, Gemini Pro Vision, and LLaVA, offering future support for additional models and featuring various modes including voice and optical character recognition | github | github profile
Personal Assistant by HyperWrite: HyperWrite offers a Personal Assistant AI agent for everyday tasks, seamlessly integrating into workflows to automate tedious tasks, optimize planning, and inform decision-making, while also providing personalized suggestions and transforming wishes into commands across various platforms | website | github profile
AutoGPT: AutoGPT provides accessible AI tools for building and using AI agents, offering a comprehensive framework including Forge for agent creation, agbenchmark for performance evaluation, a leaderboard for competition, a user-friendly UI, and CLI for seamless integration and management | github | github profile
BabyAGI: BabyAGI exemplifies an AI-powered task management system utilizing OpenAI and vector databases like Chroma or Weaviate, creating, prioritizing, and executing tasks based on previous outcomes and predefined objectives, with the main function involving an infinite loop where tasks are processed, enriched, and stored using OpenAI's NLP capabilities and Chroma/Weaviate, inspired by the Task-Driven Autonomous Agent concept | github | github profile
GPT Researcher by Tavily: GPT Researcher is an AI-powered autonomous agent designed for efficient and unbiased online research, generating detailed reports by leveraging recent advancements in AI and web scraping, with a focus on speed, reliability, and cost-effectiveness | github | github profile
GPT Newspaper by Tavily: GPT Newspaper is an autonomous agent project using AI to create personalized newspapers based on user preferences, featuring six specialized sub-agents for searching, curating, writing, designing, editing, and publishing content tailored to individual interests | github | github profile
Tavily: Tavily AI is your comprehensive research assistant, offering a platform for rapid insights with a Search API for LLMs, ensuring real-time, accurate, and bias-reduced data gathering and organization, suitable for both individual and enterprise needs | website | github profile
BrowserGPT: BrowserGPT is a project that combines OpenAI's GPT-4 and the Playwright library to control browsers via natural language, enabling code snippet generation for browser tasks | github | github profile
ChartGPT: ChartGPT offers AI-driven services like table summarization, charting, and code generation, featuring pay-as-you-go pricing, trusted by major companies, emphasizing data security, ease of use, and 24/7 customer support | website
AI Agent Assist by DialPad: Dialpad introduces Ai Agent Assist, offering real-time, Ai-powered answers to enhance customer service through deep integrations, reducing agent ramp time, and providing actionable insights with out-of-the-box productivity | landing page
Cal.ai: Cal.ai is an open-source AI scheduling assistant that manages email communications for booking, rearranging, and inquiring about meetings, leveraging a LangChain Agent Executor and MailParser for efficient scheduling without API key exposure | website | github
Bloop: Bloop is a GPT-4-based coding assistant that boosts engineer productivity by allowing natural language interactions with codebases for explanations, feature writing, error troubleshooting, and more, featuring a code-centric AI playground, fast regex search, and comprehensive code navigation tools | github
Cody: Cody, an AI coding assistant, now offers an enterprise version with enhanced security, scalability, and control for organizations, supporting various IDEs and providing AI-powered autocomplete, chat assistance, and custom command capabilities | website | github
Tabby: Tabby is a self-hosted, open-source AI coding assistant similar to GitHub Copilot, featuring a self-contained setup with no DBMS/cloud dependency, OpenAPI for easy integration, consumer-grade GPU support, and a full-feature admin UI in its latest release | github | website | docs
Continue: Continue is an open-source autopilot plugin for VS Code and JetBrains, enhancing coding with LLMs through features like task and tab autocomplete, natural language edits, file generation, and customization options, available under the Apache 2.0 license | github | website
Cursor: Cursor is an AI-enhanced programming editor focusing on code discussion, editing, and debugging, with plans for advanced features like repository healing and AI-generated documentation | github | website
Sweep: Sweep is an AI tool that automates the transformation of GitHub issues into pull requests, streamlining code improvements and bug fixes, supported by a suite of features like codebase understanding, test running, and a developer-friendly interface for installation and usage | github | website
Pieces: Pieces is an AI-powered productivity tool for developers that enhances efficiency through a unified toolchain, offering on-device workflow assistance, intelligent code snippet management, and seamless integration with development tools and plugins | website | discord
Aider: Aider is a command-line tool for AI-assisted pair programming, allowing code editing in local git repositories with GPT-3.5/GPT-4, featuring direct file edits, automatic git commits, and support for most popular programming languages | github
Imbue:: Imbue, previously known as Generally Intelligent, is developing AI systems designed for reasoning and coding, aiming to create truly personal computers that enhance human freedom, dignity, and agency, supported by a $200M funding round to advance their technology | website | twitter
VacAIgent: VacAIgent is a Streamlit-integrated, CrewAI framework-based AI application (Trip Planner Agent) that automates and enhances trip planning through a user-friendly interface, demonstrating collaborative AI agent task execution and offering an interactive web app experience for tailoring travel plans | github | code walkthrough
XAgent: XAgent is an open-source, experimental Large Language Model-driven autonomous agent designed to autonomously solve a wide range of tasks with features like autonomy, safety, extensibility, a GUI for easy interaction, and the ability to cooperate with humans | github | demo | docs | blog

AI Agents + Development Frameworks

Here's an awesome list of agentic AI development libraries or frameworks:

TaskingAI:: TaskingAI is a platform enhancing AI-native app development with Firebase-like simplicity, offering an all-in-one LLM platform with intuitive project management, BaaS-inspired workflow, and customizable integration for developing GPTs-like multi-tenant applications | github | website
AgentOS: The Agent OS is an experimental platform for creating self-evolving, autonomous AI agents capable of writing and executing their own code, designed to be a long-term environment for such agents and supports various programming languages | github
AutoAct: AutoAct is an automatic agent learning framework that synthesizes planning trajectories without large-scale data or closed-source models, using a division-of-labor strategy for task completion, demonstrating superior or comparable performance in experiments | github | website | paper | announcement
SWE-agent: This open source project introduces SWE-agent, a software engineering agent for LMs like GPT-4, enhancing bug and issue resolution in GitHub repositories with state-of-the-art performance, facilitated by a well-designed Agent-Computer Interface (ACI) and support for OpenAI and Anthropic Claude models | github | website | demo | discord
Agents by Hugging Face: Hugging Face's Transformers Agents provide three main types: HfAgent for inference with open-source models, LocalAgent for using local models and tokenizers, and OpenAiAgent for access to OpenAI's closed models, enabling code generation and other AI tasks with varying levels of customization and local or remote execution | website
Axflow: Axflow is a TypeScript framework designed for AI development, offering a modular collection of tools for building natural language applications, and it emphasizes a code-first approach to simplify the integration of LLMs into scalable solutions | website | github
AGiXT: AGiXT is an advanced AI Automation Platform designed to enhance AI instruction management and task execution across various providers, incorporating features like adaptive memory, smart instruct, and a versatile plugin system to push the boundaries of AI technology towards achieving Artificial General Intelligence (AGI) | github | website
Cognee: Cognee is an open-source framework aimed at simplifying data processing for large language models (LLMs) by creating knowledge graphs and data models, offering tools for information addition, knowledge creation, and similarity-based search | github
MemGPT: MemGPT introduces a customizable AI chatbot framework with self-editing memory and access to unlimited data, promoting perpetual, context-rich conversations | website | github
Superagent: Superagent is an open-source AI Assistant Framework & API enabling developers to integrate advanced AI agents into their applications, with support for various features like memory, streaming, and API connectivity, and backed by Y Combinator demo | github
Adala: Adala is a framework for autonomous data labeling agents, supporting Python 3.8 to 3.11, with features for customizable, intelligent data processing and integration into Python Notebooks | github
Agentive: Agentive is a platform for AI Automation Agency owners, offering tools for creating, managing, and deploying custom AI solutions, with features like model selection, tool integration, prompt crafting, versioning, and training with own data, designed to simplify AI agent delivery | website | announcement
Central by Zapier: Zapier Central is an AI workspace designed to automate tasks across 6,000+ apps with AI bots, offering capabilities like live data connection, AI automation, and interaction with data sources for businesses and individual productivity enhancements | announcement | website
Tarsier by Reworkd: Tarsier is an open-source utility library by Reworkd, aimed at enhancing web interaction for AI agents by visually tagging interactable elements, facilitating actions based on text or "screenshots" for GPT-4(V) and providing OCR utilities | github | website | demo
AgentGPT by Reworkd: AgentGPT allows users to configure and deploy autonomous AI agents, enabling them to name their own custom AI and guide it towards any desired goal through task execution and learning | github | github profile
AgentLabs: AgentLabs is an open-source, universal frontend solution for AI agents, offering an authentication portal, chat interface, analytics, and payment features to streamline the deployment of AI agents to public users | github | website | docs
Agency Swarm by VRSEN: Agency Swarm is a framework designed to automate AI agencies by creating a swarm of collaborative agents with customizable roles and functionalities, aiming to simplify the agent creation process and make automation more intuitive | github
Agents-as-a-Service (AaaS) by VRSEN: Agent-as-a-Service (AaaS) scales businesses with AI agent teams, offering custom solutions focused on automation, efficiency, and scalability | website
LangChain by Langchain AI: LangChain is a framework enabling context-aware reasoning applications with integrated libraries, templates, and developer tools | github
LangChain JS by Langchain AI: LangChain JS is a framework for developing applications powered by language models, enabling context-aware and reasoning-based applications through composable tools and off-the-shelf chains, with seamless integration with the LangChain Python package | github
LangGraph by Langchain AI: LangGraph is a library facilitating the construction of stateful, multi-actor applications with LLMs, enabling cyclic coordination across multiple computation steps, particularly suited for agent-like behaviors, while also providing streaming support, and various guides and examples for implementation and usage | github
OpenGPTs by Langchain AI: OpenGPTs is an open-source project providing customizable GPT-based experiences, offering control over language models, prompts, tools, vector databases, retrieval algorithms, and chat history databases, featuring three cognitive architectures: Assistant, RAG, and Chatbot, with support for various language models and deployment options including Docker, Cloud Run, and Kubernetes | github
LangServe by Langchain AI: LangServe facilitates the deployment of LangChain runnables and chains as a REST API, providing features like automatic schema inference, efficient endpoints, and a playground page, with plans for a hosted version for one-click deployments | github
AutoGen by Microsoft: AutoGen is a multi-agent conversation framework facilitating the development of next-gen LLM applications, highlighted by various accomplishments and offering enhanced LLM inferences, customizable agents, and comprehensive documentation | github
AutoGen Studio by Microsoft: AutoGen Studio 2.0 is Microsoft's advanced AI development tool, offering a user-friendly interface, powerful Python API, and comprehensive features for creating and controlling AI agents and workflows | website
JARVIS by Microsoft: JARVIS aims to advance artificial general intelligence (AGI) through cutting-edge research and facilitate broader community engagement | github
SuperAGI: SuperAGI is an open-source framework facilitating the development, management, and operation of useful Autonomous AI Agents with a variety of features and toolkits available, including a graphical user interface, action console, and multiple vector databases | github | github profile
ChatDev: ChatDev is a virtual software company utilizing intelligent agents to revolutionize the digital world through programming, offering a highly customizable framework and integrating innovative approaches like Experiential Co-Learning, Docker support, Git management, and Human-Agent Interaction | github | github profile
MetaGPT: MetaGPT is a multi-agent framework enabling GPT to collaborate within a software company, facilitating complex tasks by assigning different roles to GPTs | github | github profile
Haystack: Haystack is an end-to-end LLM framework facilitating the construction of applications powered by LLMs, Transformer models, vector search, and more, offering flexibility, transparency, and extensibility, with features including retrieval-augmented generation, document search, question answering, and semantic search, along with a diverse user base including companies like Airbus, Apple, and Netflix | github | github profile
crewAI by João Moura: crewAI is a cutting-edge AI framework designed for orchestrating role-playing, autonomous AI agents, enabling seamless collaboration and complex task handling | github | github profile
crewAI+ by João Moura: CrewAI+ is in beta, offering seamless API integration, business support, and early access for design partners; apply now to shape future features | website
DB-GPT: DB-GPT revolutionizes database interactions using private LLM technology, enabling streamlined AI-native data app development with multi-model management, Text2SQL optimization, and fine-tuning, facilitating enterprises and developers to create bespoke applications in the Data 3.0 era | github | github profile
DevOpsGPT: DevOpsGPT is an AI-driven software development automation solution that combines large language models with DevOps tools to convert natural language requirements into working software, enhancing development efficiency, shortening cycles, and reducing communication costs | github | github profile
E2B: E2B Sandbox offers secure cloud environments tailored for AI agents and apps, facilitating long-running sessions with various tools and can be integrated with any large language model | github | github profile
Agents by AI Waves: Agents is an open-source framework for building autonomous language agents with features including long-short term memory, tool usage, web navigation, multi-agent communication, human-agent interaction, and symbolic control, allowing customization through natural language config files and deployment in various interfaces | github | github profile
CAMEL: CAMEL (Communicative Agents for Mind Exploration of Large Language Model Society) is an open-source library designed for studying autonomous and communicative agents, facilitating research in understanding their behaviors, capabilities, and potential risks through scalable techniques and cooperative frameworks, including role-playing, with extensive documentation, examples, and datasets, while also supporting integration with open-source models as backends for diverse applications | github | github profile
Superagent: Superagent is an open-source AI assistant framework backed by Y Combinator, facilitating the integration of large language models (LLM) and generative AI into applications, supporting various use cases such as question answering, chatbots, and content generation | github | github profile
AgentVerse: AgentVerse is an Apache2-licensed Python framework for deploying multiple LLM-based agents in various applications, offering task-solving and simulation frameworks for collaborative task accomplishment and behavior observation among agents | github | github profile
GPTeam: GPTeam is a collaborative AI project utilizing GPT-4 to create multi-agent systems aimed at enhancing productivity and communication, with features including agent memory and interaction, alongside instructions for setup and integration with third-party services | github | github profile
Streamlit Agent by Langchain: This repository showcases various LangChain agents as Streamlit apps, including a basic streaming app, a memory-based conversation app, a demo replicating MRKL functionality, a minimal agent with search capability, chatbots with feedback options, document querying, database communication, and pandas DataFrame interaction, featuring LangChain and Streamlit integrations | github | github profile
OpenAGI: OpenAGI is an open-source platform integrating Large Language Models (LLMs) with domain-specific expert models for complex task-solving, fostering a paradigm where LLMs operate various external models, accompanied by a Reinforcement Learning from Task Feedback (RLTF) mechanism for self-improvement | gitbub | github profile
LoopGPT: L♾️pGPT is a modular auto-GPT framework with features such as a "Plug N Play" API, GPT 3.5 compatibility, minimal prompt overhead, human-in-the-loop capability, and full state serialization, facilitating easy installation and usage through Python code, CLI, or Docker, with the ability to add custom tools and course correction, along with saving and loading agent state, requiring Python 3.8+ and an OpenAI API Key, and optional setup for Google search support | gitbub | github profile
uAgents by Fetch AI: uAgents is a Python library by Fetch AI for creating autonomous AI agents with features like easy creation, blockchain network connectivity, and cryptographic security | gitbub | github profile
Fetch by Fetch AI: Fetch AI offers a platform for launching AI apps and services, including agent hosting, analytics, IoT gateways, and a Web3-based open network, alongside an open network for AI Agents that allows for connectivity, transactions, and the formation of dynamic marketplaces, facilitating the deployment and monetization of AI and ML models through agent technology | Product | github profile
Flowise: Flowise simplifies the creation of applications leveraging large language models (LLMs) by providing a drag-and-drop interface for customizing AI workflows, offering easy installation, Docker support, development tools, and documentation for integrating various functionalities such as authentication, streaming, and custom tools to enhance AI agents' capabilities | website | docs | github profile
Lobe Chat: Lobe Chat is an open-source UI framework for building ChatGPT/LLM-based chat applications, featuring modern design, speech synthesis, multi-modal support, extensible plugins, and free one-click deployment for various AI agents | github | website
CodeActAgent: CodeActAgent, trained on CodeActInstruct, showcases superior performance in both in-domain and out-of-domain tasks, enabling dynamic code execution and multi-turn interactions for more effective LLM agents | github
Bazed: | Bazed Agent Framework, aimed at empowering developers to build autonomous agent swarms without requiring deep Python ML knowledge, is facilitating the creation of sophisticated systems through TypeScript for enhanced autonomy and reliability github | website | discord
databerry: Chaindesk is a no-code platform for building custom LLM Agents, enabling users to quickly set up a semantic search system over personal data without technical knowledge | github
Beam: Beam AI offers a platform for Agentic Process Automation, using AI agents to automate workflows, enhancing productivity for businesses of all sizes with features like pre-trained agents, seamless integrations, and industry-specific solutions | website | twitter | linkedin | youtube
Streamship: A development platform for AI Agents offering Python SDK, cloud deployment, serverless hosting, vector search, webhooks, and media generation, with a focus on simplicity, scalability, and integration with popular models and services | website | twitter | discord | github profile
BDR Agent by Relevance: Relevance AI's flagship BDR Agent is designed to assist sales teams by researching and qualifying leads, engaging in personalized prospecting according to your playbook 24x7, and booking meetings to grow your business without increasing headcount | website | demo | twitter | github profile | linkedin
PraisonAI: Praison AI is a low-code, centralized framework leveraging AutoGen and CrewAI to simplify creating and orchestrating multi-agent systems for LLM applications, emphasizing customization and ease of human-agent interaction | github | demo | code snippet

AI Agents + No-Code Development Frameworks

Here's an awesome list of no-code agentic AI development frameworks:

Relevance: Relevance AI offers a platform for building and deploying AI workers to automate tasks, integrate with tech stacks, and manage security, aiming to enhance business efficiency without increasing headcount | website | twitter | github profile | linkedin
Vertex AI by Google: Vertex AI, enhanced by Gemini models, offers comprehensive generative AI solutions for rapid application development, data processing, custom model training with minimal ML expertise, and production deployment, aimed at accelerating innovation and reducing costs in enterprise environments | website
AI Studio by Azure: Azure AI Studio offers a platform for developing generative AI applications and custom copilots, featuring prebuilt models, training capabilities, free Azure Cosmos DB access for 90 days, and built-in security with no extra charge during preview | website
LlamaCloud by LlamaIndex: LlamaCloud by LlamaIndex streamlines AI development by enabling developers to minimize infrastructure management and parameter tuning, focusing instead on creating AI products, with features for proprietary parsing of complex documents, easy data ingestion and storage, and advanced data retrieval | website | github profile | discord | linkedin
Mendable: Mendable offers an AI chatbot solution that enables companies to build and deploy technical assistants trained on their specific documentation and resources, aiming to improve customer and employee support, with features including enterprise-grade security, continuous model training, and integration with a wide range of data sources and APIs | website | docs | twitter | github profile
Kapa: Kapa.ai is an AI-powered chatbot service for developers that automates answering technical questions by learning from technical resources, thus helping identify gaps in documentation, with features including data security, PII anonymization, and continuous updating from a range of knowledge sources | website | docs
Libraria: Libraria AI offers a platform to create, manage, and embed custom AI chatbots with natural language processing and features like call-to-actions, link carousels, and analytics for enhanced customer interactions and satisfaction, alongside free and paid plans tailored for different business needs | website | twitter

AI Agents + Evaluation Frameworks

Here's an awesome list of eval frameworks for AI agents:

LangFuse: Langfuse, an open-source LLM engineering platform, offers debugging, prompt management, metrics for LLM apps improvement, and won the #1 Golden Kitty in the AI Infra Category from Product Hunt | website | twitter | discord
AgentOps: AgentOps aims to improve AI agent development with tools for observability, evaluations, and replay analytics, offering a streamlined process for testing and debugging compliant AI agents through a user-friendly interface and comprehensive documentation | github | website | docs | discord | demo
Bananalyzer by Reworkd: Bananalyzer is a framework for evaluating AI agents on web tasks, utilizing Playwright for creating diverse datasets of website snapshots for reliable and varied web task assessments | website | github
AgentBench: AgentBench v0.2 is a benchmark designed to evaluate Large Language Models as agents across a diverse set of environments, enhancing framework usability and extending model evaluations | github

AI Agents + Observability Frameworks

Here's an awesome list of monitoring frameworks for AI agents:

LangSmith by LangChain: LangSmith provides tools for debugging, testing, evaluating, and monitoring LLM applications, integrating seamlessly with LangChain for comprehensive AI agent observability | docs | website
Traces by Weights & Biases: W&B Traces enhances AI agent observability by providing intuitive visualizations for debugging LLMs, allowing practitioners to review past results, debug errors, and gain insights into model behavior | website
Context: Context.ai is a tool for evaluating and analyzing products with LLMs, aiming to improve user experience and performance | website | docs
Helicone: Helicone is an open-source observability platform for Language Learning Models (LLMs), providing features like request logging, caching, rate limiting, cost and latency tracking, UI-based prompt iteration, and collaboration tools | website | github

AI Agents + Mobile-Friendly Frameworks

Here's an awesome list of running AI agents on mobile (on your own phone):

NavAIGuide: NavAIGuide is an extensible, mobile-friendly, multi-modal agentic framework designed to integrate with mobile and desktop apps, featuring visual task detection, advanced code selectors, action-oriented execution, and resilient error handling | github
AppAgent: AppAgent is a mobile-friendly LLM-based multimodal agent framework developed to operate smartphone apps, enabling human-like interactions for a wide range of applications without system back-end access | github | github profile

AI Agents + Local Inference

Here's an awesome list of running AI agents locally (on your own computer):

Pinokio: Pinokio is a browser that enables the installation, running, and programmable control of any application with one click, supporting any open-source repo locally, including LLM or AI agent-based projects | website | github | github profile
Ollama: Ollama is a tool for running large language models locally, offering easy setup for macOS, Windows, Linux, and Docker, along with a library of models and quickstart guides for customization and integration | github | github profile
Jan: Jan is an open-source, development-stage ChatGPT alternative that operates fully offline on diverse hardware platforms, supporting universal architectures from PCs to multi-GPU clusters | github | github profile
LM Studio: LM Studio offers a platform for running various local LLMs like LLaMa, Falcon, MPT, and others offline, featuring a Chat UI, OpenAI-compatible server, and model downloads from Hugging Face, with support for Mac, Windows, and Linux, emphasizing privacy and no data collection, free for personal use | website | github profile
FastChat: FastChat is a platform for training, serving, and evaluating large language model chatbots, featuring an open-source distributed multi-model system, API compatibility, and a dataset for LLM conversations | github | demo | discord | twitter
PrivateGPT: PrivateGPT is a secure, offline-capable AI tool for querying documents with Large Language Models, offering high-level and low-level APIs for privacy-conscious, context-aware application development | github
LocalGPT: LocalGPT is an open-source project for secure, private interactions with documents locally, featuring comprehensive model support, embeddings, API for RAG applications, and GUI options, with a focus on privacy and local data processing | github

AI Agents + Reinforcement Learning Frameworks

Here's an awesome list of AI agents applying reinforcement learning:

LlamaGym: LlamaGym simplifies the fine-tuning of LLM agents with online reinforcement learning, providing a framework to iterate and experiment across Gym environments for efficient agent prompting and hyperparameter tuning | github | github profile

AI Agents + Standardization

Here's an awesome list of protocols or standardized ways of interacting with AI agents:

Agent Protocol: The Agent Protocol establishes a unified API standard for seamless interaction and integration across diverse AI agents, promoting ecosystem growth and simplification of agent development and benchmarking | website | website org | github | github profile

AI Agents + Bitcoin

Here's an awesome list of LLMs with function calling (aka tools) which unlocks Bitcoin payments:

LangChainBitcoin by Lightning Labs: LangChainBitcoin is a toolset for enabling LangChain agents to interact with Bitcoin, the Lightning Network, and APIs requiring L402-based authentication, including features for Bitcoin transactions and API traversal with automated Lightning payments | announcement | github
Agent Tools by AIBTCDev Typescript tools for Bitcoin/Stacks blockchain interaction, utilizing Bun.js and Stacks.js, with a focus on AI integration | github | github profile | website | discord
AI Agent Crew by AIBTCDev: Langchain and CrewAI have launched AI agents equipped with Bitcoin wallets, facilitating automated operations within a blockchain environment | github | github profile | website | discord
Gated 402 API by AIBTCDev: | An API using a Stacks smart contract to control access, issuing a 200 status for access approval and a 402 with payment instructions for denial | github | github profile | website | discord

AI Agents + Hardware (Wearables)

Here's an awesome list of AI agents running on hardware or is in a form of a wearable:

01 by Open Interpreter: The "01 Project" is an open-source initiative focused on creating an ecosystem for AI devices, aiming to become the GNU/Linux in this domain, with details on its experimental status, software, hardware, and a speech-to-speech interface based on a code-interpreting language model for dynamic interactions | announcement | demo | github | website | docs
Humane: AI Pin, a wearable, multi-modal device, enhances ambient computing in the real world, offering a suite of AI digital assistants for various tasks while prioritizing user privacy for a more intuitive, human-centered experience | website

AI Agents + Safety Guardrails (Safeguarding)

Here's an awesome list of guardrail frameworks that enforce safety for AI agents:

IvyCheck: IvyCheck offers an API for real-time AI application safety checks, preventing prompt injection attacks, PII data leakage, and hallucinations in agentic AI development github | announcement | website
Guardrails by Guardrails AI: Guardrails is a Python framework for building reliable AI applications, offering Input/Output Guards to detect and mitigate risks, along with structured data generation from large language models (LLMs) | github | twitter
NeMo Guardrails by Nvidia: NeMo Guardrails is an open-source toolkit facilitating the integration of programmable guardrails, essential for steering and safeguarding AI agents' conversational outputs, into large language model-based applications | github | paper
Cadea by Flowbase: Cadea offers a secure AI platform for businesses, providing solutions against prompt injection, data breaches, and ensuring content safety through end-to-end security, access controls, and integration with major identity providers | website

AI Agents + Structured Outputs

Here's an awesome list of enforcing structured outputs from AI agents:

FuzzTypes: FuzzTypes is a Pydantic extension library providing autocorrecting annotation types, enhancing Pydantic's data conversions for AI agents by enabling powerful normalization capabilities like named entity linking to ensure structured data consists of "smart things" instead of "dumb strings" | github | website
Instructor: Instructor, a Python library, facilitates working with structured outputs from large language models (LLMs), offering features like response model specification, retry management, validation, and streaming support, primarily aimed at enhancing workflows of AI agents utilizing LLMs | github | website
Instructor Cloud: Instructor Cloud offers a platform for extracting models from text rapidly, with real-time streaming and the potential to utilize GPT-4*, encouraging engagement through contributions and adaptation of its FastAPI-based service | github | announcement
Pydantic: Pydantic is a Python library facilitating data validation through type hints, particularly useful for AI agents, offering fast validation capabilities and compatibility with various development tools | github | website
Outlines: Outlines is a robust text generation library designed for agentic AI developers, featuring support for multiple model integrations, advanced prompting with Jinja, efficient structured generation through regex, JSON schema, context-free grammars, and more, enabling the creation of predictable and structured AI agent outputs | github | website | discord
Marvin: Marvin is an open-source AI toolkit designed for developers focused on enhancing AI agent capabilities, offering tools for natural language interfaces, image and audio generation, and entity extraction, scalable and easy to integrate into existing projects | github | website
Perplexity-Inspired LLM Answer Engine: A versatile answer engine leveraging Groq, Mistral AI, Langchain.JS, Brave Search, Serper API, and OpenAI to deliver efficient and sophisticated responses with reduced hallucination through RAG for citation-backed search queries | github | github profile
Jaiqu by AgentOps: Jaiqu is an AI-powered tool for automatically transforming any JSON schema using GPT-4, featuring schema validation, fuzzy term matching, and repeatable jq query generation | github | demo | website | twitter | discord

AI Agents + Model Merges

Here's an awesome list of model merges which embed AI agents with new knowledge:

Evolutionary Model Merge by Sakana AI: Sakana AI's evolutionary model merge (EMM) combines 500,000 open-source models using evolutionary techniques to create new foundation models, achieving groundbreaking results without being explicitly optimized for specific benchmarks, marking a significant step toward AGI by empowering AI with combined knowledge akin to Retrieval Augmented Generation | announcement | github
MergeKit by Arcee AI: Arcee AI's MergeKit offers tools for merging pre-trained large language models, enabling the creation of more versatile AI agents by combining knowledge from different sources, akin to Retrieval Augmented Generation (RAG) | github

AI Agents + Tool Use (Function Calling)

Here's an awesome list of function calls (aka tools) for your AI agents:

Composio: Composio enables quick integration of 90+ tools for developers and agents, offering managed authentication, easy testing, and up-to-date APIs to simplify development and enhance functionality | demo | yet another demo | website | docs | blog | github profile
crewAI Tools by João Moura: crewAI Tools is a library that provides a framework for developing sophisticated tools to enhance crewAI agents, with methods for subclassing BaseTool, utilizing the tool decorator, and guidelines for contributing to the ecosystem | github
LangChain Tools by LangChain AI: Langchain integrates various providers like Anthropic, AWS, and OpenAI, and offers tools for components such as LLMs, chat models, and data analysis, supporting functionalities from Alpha Vantage to YouTube | website
LlamaIndex Tools by Llama Hub: LlamaHub offers a variety of tools for building data agents, with top downloads including IonicShoppingToolSpec, OpenAPIToolSpec, WikipediaToolSpec, GmailToolSpec, and GoogleCalendarToolSpec, enabling seamless integration with user-defined functions, query engines, and third-party services | website | docs
aifs by OpenInterpreter: AIFS offers a simple and efficient local semantic search capability for folders, leveraging Unstructured.IO for advanced data processing and ChromaDB for fast, similarity-based searching of embeddings | github
Vector Stores as Tools: Langchain features VectorDBQAChain, which integrates LLMs and vector databases into agent tools for enhanced question-answering capabilities by leveraging data ingested into vector stores | notebook

AI Agents + User Interface Development

Here's an awesome list of UIs (generative UIs, conversational UIs, and agentic UIs) optimized for AI agents:

AI SDK by Vercel: The Vercel AI SDK is an open-source library for creating AI-powered conversational interfaces, supporting multiple frameworks and languages, with built-in adapters for major AI services | announcement | website | github | github examples

AI Agents + Large Language Models (LLMs)

Here's an awesome list of AI agents:

Assistants API by OpenAI: The Assistants API facilitates the development of AI agents, offering tools such as Code Interpretation and Function calling for embedding advanced, intelligent functionalities within applications | API docs
Groq: Groq introduces a game-changing AI processor, emphasizing speed, efficiency, and ease of use, aimed at enhancing GenAI inference, particularly for real-time applications | API docs
Claude 3: Claude 3, Anthropic's new suite of LLMs, enhances AI agents with superior reasoning, rapid responses, and diverse cognitive capabilities without compromising user privacy | API docs

AI Agents + Custom Development

Here's an awesome list of AI agencies that specialize in custom AI agent development:

Produvia: Since 2013, Produvia Inc. has served $7M+ in revenue brands by developing custom agentic AI solutions powered by state-of-the-art function calling LLMs including but not limited to: Claude 3 Opus, GPT-4, Bard (Gemini Pro), Claude 3 Sonnet, Claude 3 Haiku, Mistral Medium, Command R, Mistral-Next, Starling-LM-7B-beta | website | twitter | linkedin

AI Agents + Prompt Engineering

Here's an awesome list of agent-friendly prompt engineering techniques:

Priompt: Priompt is a JSX-based library for designing prompts with priorities, aiming to optimize inclusion of content within token limits, inspired by React and detailed with installation instructions, examples, principles, and future considerations | github

AI Agents + LLM-Friendly Languages

Here's an awesome list of languages optimized for LLMs:

LMQL: LMQL is a Python-based programming language for large language models, allowing seamless integration of LLMs into code with advanced features like conditional logic, constraints, and multi-model support | github | website

Hire Us

Do you want to develop a custom agentic AI solution or looking launch your own AI agent?

Schedule a discovery call with Produvia

Disclaimer: Slava Kurilyak is the Founder/CEO at Produvia

At Produvia, we partner with $7M+ in revenue brands to develop custom AI agents

Show Your Support

To express your support, you can take the following actions:

Star the Repository: This helps increase its visibility.
Submit Suggestions: If you have any ideas or feedback, please open a new issue here.
Contribute Directly: You can contribute by forking this repository and then submitting your contributions through a new pull request here.

wikicrafter / awesome-ai-agents Goto Github PK

awesome-ai-agents's Introduction