Self-Determining AI Agents is a Python-based framework designed to simplify the creation of autonomous AI agents. It features a customizable planning loop where agents generate tasks, plan strategies, and execute actions using integrated tools. The framework includes persistent memory modules for context retention, a flexible task scheduling system, and hooks for custom tool integrations such as web APIs or database queries. Developers define agent goals via configuration files or code, and the library handles the iterative decision-making process. It supports logging, performance monitoring, and can be extended with new planning algorithms. Ideal for research, automating workflows, and prototyping intelligent multi-agent systems.

Whiz is designed to provide a robust foundation for developing intelligent agents that can perform complex conversational and task-oriented workflows. Using Whiz, developers define "tools"—Python functions or external APIs—that the agent can invoke when processing user queries. A built-in memory module captures and retrieves conversation context, enabling coherent multi-turn interactions. A dynamic planning engine decomposes goals into actionable steps, while a flexible interface allows injecting custom policies, tool registries, and memory backends. Whiz supports embedding-based semantic search to fetch relevant documents, logging for auditability, and asynchronous execution for scaling. Fully open-source, Whiz can be deployed anywhere Python runs, enabling rapid prototyping of customer support bots, data analysis assistants, or specialized domain agents with minimal boilerplate.

AgenticAppBuilder accelerates AI agent development by providing a one-command CLI to scaffold production-ready applications. It sets up language model configurations, memory backends, tool integrations, and a user interface, enabling developers to focus on custom agent logic. The modular architecture supports extensible toolchains, seamless API key management, and deployment scripts for local or cloud environments, reducing boilerplate and speeding prototyping.

Agent Forge provides a modular architecture for defining, executing, and coordinating AI agents. It offers built-in task orchestration APIs to sequence and parallelize operations, memory modules for long-term context retention, and a plugin system to integrate external services (e.g., LLMs, databases, third-party APIs). Developers can rapidly prototype, test, and deploy agents in production, weaving together complex workflows without managing low-level infrastructure.

AgentScript is an AI agent framework that lets users visually compose workflows, integrate external APIs, and configure autonomous agents. With built-in debugging, monitoring dashboards, and version control, teams can quickly prototype, test, and deploy agents to handle tasks like data analysis, customer support, and process automation. Agents can be scheduled, triggered by events, or run continuously, and you can extend them via custom code or third-party plugins.

Agentic AI Systems is a centralized resource on GitHub listing and describing a wide array of open-source agentic AI frameworks and tools. It organizes entries by capabilities, languages, and supported tools, offering direct links to source code, documentation, and quickstart examples. Developers can quickly identify and compare agent platforms, explore sample implementations, and integrate chosen frameworks into their own projects. The repository is regularly updated to include new projects, version changes, and community contributions, making it a go-to index for autonomous AI systems research and prototyping.

Azure AI Agent SDK is a comprehensive framework that enables developers to create intelligent, autonomous agents capable of executing complex tasks. It provides a modular architecture including planners, executors, and memory components that work together to assess user intents, plan actions, invoke external APIs or custom tools, and store state persistently. The SDK supports integration with various LLMs, enabling context-aware conversations and decision-making. With built-in telemetry and Azure service connectors, agents can handle error recovery, scale across cloud environments, and maintain secure interactions. Rapid prototyping is facilitated through CLI templates and prebuilt skills, allowing teams to deploy digital workers that automate workflows, enhance customer support, or perform data analysis independently.

Agents from Scratch TS is an open-source TypeScript framework that demonstrates how to build AI agents from the ground up using LangChain. It includes sample code for defining and registering external tools, managing conversational memory, routing user inputs to the right agent, and chaining multiple LLM calls. Developers can use it to understand best practices, customize agent behaviors, and integrate new capabilities such as web search, data retrieval, or custom plugins to automate tasks or build interactive assistants.

FAgent offers a modular architecture for constructing AI agents, including environment abstractions, policy interfaces, and tool connectors. It supports integration with popular LLM services, implements memory management for context retention, and provides an observability layer for logging and monitoring agent actions. Developers can define custom tools and actions, orchestrate multi-step workflows, and run simulation-based evaluations. FAgent also includes plugins for data collection, performance metrics, and automated testing, making it suitable for research, prototyping, and production deployments of autonomous agents in various domains.

The Gemini Agent Cookbook is a curated open-source toolkit offering a variety of hands-on examples for constructing intelligent agents powered by Google’s Gemini language models. It includes sample code for orchestrating multi-step reasoning chains, dynamically invoking external APIs, integrating toolkits for data retrieval, and managing conversation flows. The cookbook demonstrates best practices for error handling, context management, and prompt engineering, supporting use cases like autonomous chatbots, task automation, and decision support systems. It guides developers through building custom agents that can interpret user requests, fetch real-time data, perform computations, and generate formatted outputs. By following these recipes, engineers can accelerate agent prototyping and deploy robust AI-driven applications in diverse domains.

Gignite.ai is a versatile, prompt-based AI tool designed to turn software concepts into functional MVPs quickly and effortlessly. It empowers non-developers to build, customize, and deploy software projects without writing a single line of code. Users can translate their ideas into actionable prototypes by simply providing feature descriptions and prompts. This innovative tool significantly reduces the time and cost associated with traditional software development, making it accessible to a wider audience.

GPT-CodeApp provides an intuitive GUI where users type natural language descriptions (e.g., “build a React login form”) and instantly receive ready-to-use code snippets or project scaffolding. It supports major languages like JavaScript, Python, Java, C#, and more. Users can customize prompts, browse history, and export generated files. Built with Electron and React, it runs cross-platform without requiring an IDE plugin. GPT-CodeApp helps accelerate development, reduce boilerplate, and learn new frameworks by example.

GridWorldEnvs offers a comprehensive suite of grid-world environments to support the design, testing, and benchmarking of reinforcement learning and multi-agent systems. Users can easily configure grid dimensions, agent start positions, goal locations, obstacles, reward structures, and action spaces. The library includes ready-to-use templates such as classic grid navigation, obstacle avoidance, and cooperative tasks, while also allowing custom scenario definitions via JSON or Python classes. Seamless integration with the OpenAI Gym API means that standard RL algorithms can be applied directly. Additionally, GridWorldEnvs supports single-agent and multi-agent experiments, logging, and visualization utilities for tracking agent performance.

Microsoft AutoGen is designed to facilitate the end-to-end development of autonomous AI agents by providing modular components for memory management, task planning, tool integration, and communication. Developers can define custom tools with structured schemas and connect to major LLM providers such as OpenAI and Azure OpenAI. The framework supports both single-agent and multi-agent orchestration, enabling collaborative workflows where agents coordinate to complete complex tasks. Its plug-and-play architecture allows easy extension with new memory stores, planning strategies, and communication protocols. By abstracting the low-level integration details, AutoGen accelerates prototyping and deployment of AI-driven applications across domains like customer support, data analysis, and process automation.

Python Coding Agent is an open-source command-line tool that uses GPT models to generate Python code based on text prompts, execute that code locally, and catch runtime errors. It provides instant feedback, allowing users to iteratively refine code, automate repetitive scripting tasks, prototype data analysis pipelines, and debug functions. By combining natural language understanding with real-time code execution, it bridges the gap between idea and implementation, speeding up development and learning.

The AgentForce Custom Client Sample provides a codebase leveraging JavaScript/TypeScript and Salesforce APIs to authenticate against a Salesforce org, manage AgentForce chat sessions, send and receive messages, and customize user interface components. It showcases event subscription, custom business logic integration, and styling via Lightning Web Components. Developers can use this template to scaffold AI conversational agents, tailor message flows, integrate external systems, and extend the framework to meet unique organizational workflows and branding requirements.

AgentSpeak is an open-source Java-based implementation of the AgentSpeak(L) programming language, designed to facilitate the creation and management of BDI (Belief-Desire-Intention) autonomous agents. It features a runtime environment that parses AgentSpeak(L) code, maintains agents’ belief bases, triggers events, and selects and executes plans based on current beliefs and goals. The interpreter supports concurrent agent execution, dynamic plan updates, and customizable semantics. With a modular architecture, programmers can extend core components such as plan selection and belief revision. AgentSpeak enables developers in academia and industry to prototype, simulate, and deploy intelligent agents in simulations, IoT systems, and multi-agent scenarios.

This starter project provides a ready-to-use FastAPI application preconfigured for AI agent development. It uses Pydantic for request/response validation, environment-based configuration for OpenAI API keys, and modular endpoint scaffolding. Built-in features include Swagger UI docs, CORS handling, and structured logging, enabling teams to rapidly prototype and deploy AI-driven endpoints without boilerplate overhead. Developers simply define Pydantic models and agent functions to get a production-ready API server.