AI agents and frameworks

This repository serves as a comprehensive collection of resources, templates, and starter code for building artificial intelligence applications. It provides a centralized hub for developers to access practical implementations of common workflows, including retrieval-augmented generation pipelines and autonomous agent loops, alongside educational materials designed to support rapid prototyping and experimentation. The project distinguishes itself by offering a dual focus on technical implementation and critical analysis. It provides a library of lightweight, single-file agents and tutorials for complex tasks like multi-source retrieval, memory management, and tool integration via standardized protocols. Simultaneously, it includes an analytical framework for identifying and evaluating the linguistic patterns, structural templates, and stylistic markers characteristic of machine-generated text. Beyond these core offerings, the repository covers a broad capability surface that includes guidance on model fine-tuning, voice-processing integration, and strategies for optimizing agent reasoning and token consumption. It also features conceptual resources regarding the evolving role of product management in agent-driven environments and best practices for mitigating performance issues in autonomous systems. The repository is structured as a curated list with a navigation index, providing quick-start instructions for initializing and running template agents within a local development environment.

OpenChat is a conversational AI agent builder and customer service automation platform that uses large language models to power customer support chatbots across multiple channels. It provides tools for defining AI agent behavior, training on custom knowledge, managing actions, and controlling autopilot responses per channel. The platform enables deploying AI agents on web, phone, email, SMS, and WhatsApp, with a unified inbox for managing conversations across all channels. It includes CRM synchronization, automated workflows, contact segmentation, and analytics for tracking customer satisfaction and recurring issues. Key capabilities include automatic PII redaction, OpenAPI-based action execution, and a dual-purpose knowledge base that simultaneously serves a public help center and trains the AI. Organizations can manage team roles, configure office hours, and integrate with tools like Zapier for event-driven automation. The system also supports phone system integration via SIP, outbound call initiation, and AI-powered email management with custom domains and opt-out handling.

OpenHands is an autonomous agent framework designed for software engineering workflows. It provides a modular platform for orchestrating AI agents that reason, plan, and execute tasks within isolated, containerized development environments. By integrating with standard version control and development tools, the system enables agents to autonomously navigate codebases, implement features, and resolve issues through iterative reasoning and tool execution. The platform distinguishes itself through a model-agnostic orchestrator that connects diverse language models to a unified tool registry. It supports complex, multi-agent collaboration via hierarchical task delegation, allowing parent agents to spawn and manage independent sub-agents for parallelized workflows. Security is managed through configurable action approval policies and real-time risk evaluation, ensuring that autonomous operations remain within defined safety boundaries. The system covers a broad capability surface including persistent conversation state management, automated code review, and web research automation. It features an event-driven architecture that serializes interactions into immutable logs, facilitating observability and time-travel debugging. Developers can extend agent functionality through custom skill definitions, plugin packages, and integration with external services via standardized protocols. The project provides a command-line interface for managing agent sessions, remote server deployments, and containerized workspace lifecycles. It is designed for extensibility, allowing users to configure agent behavior through structured objects, markdown-based definitions, and environment-specific settings.

Dapr is a distributed application runtime that provides a sidecar-based infrastructure layer for building resilient microservices and event-driven applications. By utilizing a sidecar proxy pattern, it abstracts complex infrastructure tasks into standardized, network-accessible APIs, allowing developers to focus on application logic while the runtime handles service discovery, state management, and secure communication. The platform distinguishes itself through a pluggable component architecture and language-agnostic design, enabling services written in any programming language to interact with infrastructure building blocks via standard HTTP or gRPC protocols. It provides specialized support for stateful workflow orchestration and agentic AI development, ensuring that long-running processes and intelligent agents maintain state and reliability across service restarts. Furthermore, it enforces security through automatic mutual TLS authentication for all network traffic. Beyond its core orchestration capabilities, the runtime offers comprehensive observability features, including automated distributed tracing, system metrics collection, and log management. These tools provide visibility into complex service architectures without requiring manual instrumentation of the primary application code. The project includes extensive documentation, language-specific software development kits, and interactive learning resources to assist in the development and operation of distributed systems.

This project provides a standardized framework for extending the functional range of artificial intelligence agents through a registry of modular, declarative instructions. It enables agentic workflow automation by allowing developers to define task-specific behaviors and operational constraints that guide how agents interact with external tools and execute multi-step processes. The system distinguishes itself through a directory-based discovery model and a plugin-registry architecture that facilitates the distribution of specialized workflows. By utilizing a schema-driven specification that relies on structured metadata headers within markdown files, the framework ensures that agent capabilities remain portable and consistent across different execution environments. The repository serves as an instructional knowledge base, offering a collection of reusable skill sets that cover domains ranging from technical development to enterprise communication. Users can create custom skills by following a template-based approach, which allows for the integration of new capabilities into existing AI-powered development tools and platforms.

This is an open-source framework for building stateful, durable AI agents that run on Cloudflare Workers. It provides a runtime for long-lived agents that maintain a persistent identity, local SQL storage, and real-time connections, utilizing a lifecycle where agents hibernate when idle and wake on demand. The project distinguishes itself through its multi-channel orchestration, allowing a single agent to be deployed across voice, email, and chat interfaces with unified state. It implements the Model Context Protocol for standardized tool and data exchange and includes a dedicated framework for monetizing agent tools via the x402 micropayment protocol. The system covers a broad range of capabilities, including browser automation for web page inspection, event-driven durable workflows with human-in-the-loop approvals, and bidirectional WebSocket communication for real-time state synchronization. It also features a secure TypeScript sandbox for executing generated code and distributed tracing for monitoring agent performance.

LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing for explicit node-to-node routing and state management. Furthermore, it includes a human-in-the-loop control layer that enables developers to pause execution at defined breakpoints, allowing for manual inspection, modification, and approval of agent actions during runtime. Beyond its core orchestration capabilities, the framework supports a tiered memory architecture that separates short-term conversation context from long-term persistent data. It also provides comprehensive observability tools for tracing and monitoring execution flows, alongside security features for managing authentication and fine-grained access control. The platform is supported by extensive documentation and standardized interfaces for models, embeddings, and data sources to facilitate the development of production-grade agentic systems.

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate complex multi-agent workflows through hierarchical delegation. By supporting both local and remote execution environments, it enables developers to build stateful agents that can be managed programmatically via API or integrated into existing automation pipelines. The system includes a robust set of administrative and security features, such as human-in-the-loop approval for tool execution, multi-tenant identity management, and automated performance evaluation suites. These tools allow for the creation of reproducible agent blueprints, version-controlled deployments, and detailed observability into agent reasoning and memory integrity. The project is distributed as a Python-based framework, providing official SDKs and a command-line interface to facilitate integration into development workflows and production environments.

This project is a community-driven knowledgebase and registry for AI agent configurations. It serves as a centralized repository for system prompts, environment settings, and integration strategies designed to standardize the behavior of various AI-assisted development tools. By capturing these configurations in a structured format, the project enables developers to maintain consistent AI agent performance across different workstations and environments. The repository distinguishes itself through a hierarchical, version-controlled architecture that treats prompt engineering patterns as portable code. It decouples tool-specific settings from proprietary platforms, allowing for the auditability and reproducibility of agent behaviors. This approach facilitates the discovery of specialized configuration strategies by organizing disparate tool requirements into a searchable, human-readable directory tree. The project covers a broad spectrum of AI coding assistants and agent-based tools, providing a comprehensive index of setup requirements and operational configurations. It leverages distributed version control to aggregate best practices, ensuring that prompt schemas remain accessible and up-to-date as development environments evolve. The documentation is maintained in plain-text formats to ensure compatibility and ease of use across diverse technical workflows.

Cipher is an AI agent orchestration framework and LLM context memory layer. It provides a collaborative AI knowledge base and a context synchronization service that allows AI agents and CLI tools to maintain a persistent, structured memory of project decisions and codebase patterns across different sessions and machines. The system distinguishes itself through a version-controlled context model, using branches and commits to track how project knowledge evolves. It features a hierarchical knowledge store where information is organized as markdown files and can be synchronized between local environments and a remote cloud host. The platform covers a broad range of capabilities including AI memory governance with role-based access control, multi-tenant space isolation, and an agent-skill plugin architecture. It also includes tools for project knowledge curation, memory topic discovery, and a skill marketplace to extend agent capabilities. User identity and team coordination are managed via browser-based OAuth authentication, team membership management, and a dedicated billing portal for subscription plans.

GPT Researcher is an autonomous agent framework designed to automate the process of gathering, synthesizing, and documenting information from diverse web and local sources. It functions as a research-oriented execution environment that orchestrates specialized agents to perform complex, multi-branch research tasks, transforming raw data into structured, factual, and cited reports. The project distinguishes itself through a graph-based orchestration layer that manages state transitions and information flow between specialized agents. It employs recursive tree-search execution to explore complex topics by branching into sub-queries, while a modular tool-calling interface allows for the integration of external search engines, databases, and specialized data retrieval servers. This architecture enables the system to perform deep, concurrent research while maintaining real-time progress tracking through non-blocking callback mechanisms. Beyond its core research capabilities, the framework supports hybrid knowledge synthesis by normalizing web-scraped content and local file formats into a unified context. It provides extensive tooling for report customization, including prompt-driven synthesis and the automatic generation of inline visual illustrations. The system is designed for integration into broader software ecosystems, offering asynchronous endpoints and containerized deployment options to facilitate its use within custom web applications or messaging platforms.

Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated code meets production standards. The system covers a broad range of engineering capabilities, including technical specification automation, multi-axis code reviews, and test-driven development. It also provides frameworks for context management, security auditing, and the orchestration of parallel agent tasks to synthesize findings into consolidated reports. These skills are implemented as standardized instructions and commands that can be loaded into an agent via auto-discovery or explicit installation.

Goose is an extensible agentic AI platform designed for autonomous task orchestration and developer-centric assistance. It provides a workflow engine that manages complex, multi-step objectives by delegating tasks to specialized subagents, all while maintaining stateful session continuity. The system is built to integrate directly into terminal and coding environments, allowing for automated file manipulation and context-aware interaction. The platform distinguishes itself through a secure, sandboxed runtime environment that enforces granular permission controls and policy-driven guardrails. By utilizing a standardized protocol-based architecture, it allows users to connect external tools, services, and third-party models as modular extensions. This framework supports the creation of reproducible automation recipes, which can be configured, shared, and executed to standardize recurring workflows across different projects. Beyond its core orchestration capabilities, the system includes comprehensive developer tooling for session management, interaction logging, and terminal-based interfaces. It supports advanced automation tasks, including browser-based testing and external service integration, through a flexible extension lifecycle that allows for dynamic toolset adjustments during active sessions.

The AWS Cloud Development Kit is an infrastructure-as-code framework that enables developers to define and provision cloud resources using familiar programming languages. By utilizing construct-based synthesis, it translates high-level, object-oriented code into declarative templates, allowing for the automated management of complex cloud environments through a centralized, code-driven control plane. The framework distinguishes itself through its ability to model infrastructure as a dependency-aware resource graph, ensuring that components are provisioned and updated in the correct order. It employs a language-agnostic intermediate representation to synthesize these definitions into platform-specific configurations, while supporting aspect-oriented policy injection to apply security and compliance rules across infrastructure definitions during the synthesis phase. Beyond core provisioning, the project provides a modular component registry for distributing and reusing pre-configured infrastructure building blocks. It supports multi-account orchestration, allowing for the deployment of consistent resource sets across different regions and accounts from a single template, and includes capabilities for detecting infrastructure drift to ensure deployed environments remain aligned with their defined state. The project is distributed as a software development kit, providing programmatic interfaces to manage the full lifecycle of cloud resources and integrate infrastructure definitions directly into application codebases.

This project serves as a centralized directory and interoperability hub for the Model Context Protocol, providing a curated collection of standardized service connectors that bridge artificial intelligence models with external software, databases, and APIs. It facilitates the integration of AI agents with diverse ecosystems by offering a registry of machine-readable interface definitions that enable dynamic tool discovery and structured context injection. The directory distinguishes itself by focusing on the protocol-based interoperability required for autonomous AI agents to interact with heterogeneous remote services. It emphasizes a decoupled request-response pattern and a bidirectional capability handshake, ensuring that AI hosts and servers can negotiate operational constraints and supported features before any tool invocation occurs. This architecture supports stateless service implementations, allowing for independent scaling and deployment of tools across various environments. The collection covers a broad functional range, including integrations for business productivity, data science, infrastructure management, and developer utilities. These connectors enable AI agents to perform tasks such as secure database querying, code execution, desktop automation, and persistent memory management. The repository acts as a community-driven resource for developers seeking to extend the operational range of their AI agents through modular, plug-and-play service integrations.

This project provides a comprehensive framework for building, training, and managing autonomous agents. It enables the construction of systems that utilize language models to plan, manage memory, and execute multi-step tasks through iterative reasoning loops and tool-based actions. The framework distinguishes itself by offering specialized capabilities for interacting with graphical user interfaces and legacy software, allowing agents to perceive visual elements and perform actions like a human user. It supports complex, cross-application workflows through graph-based orchestration and provides robust mechanisms for skill evolution, where agents can iteratively refine or generate new operational capabilities based on execution feedback. Beyond core development, the project includes an extensive suite of tools for model training and optimization, including multi-stage fine-tuning, reinforcement learning, and multimodal alignment. It also features integrated observability tools for monitoring agent execution, managing persistent context, and ensuring security through sandboxed environments and risk-aware execution controls. The repository serves as both a functional development framework and an educational resource, offering structured guides and methodologies for implementing intelligent agent systems.

Semantic Kernel is an artificial intelligence orchestration framework designed to integrate large language models with existing codebases. It functions as an agentic workflow engine, providing a standardized interface that connects generative models to traditional application logic, data sources, and external tools to automate complex, multi-step business tasks. The platform distinguishes itself through a modular plugin architecture and a planner-based reasoning engine that decomposes high-level goals into executable sequences of functions. By utilizing a connector-based abstraction layer, it decouples core orchestration logic from specific model providers and vector databases, allowing for consistent retrieval and execution across diverse infrastructure. The framework includes a middleware-based request pipeline for managing cross-cutting concerns such as telemetry and safety filtering, alongside a prompt template engine for dynamic context injection. These components support the development of scalable, enterprise-ready systems that maintain security and compliance while coordinating multiple language models and specialized tools.

Agent Skills is a framework for bundling executable scripts and metadata to extend the capabilities and tool-use of language model agents. It provides a standardized directory structure for packaging specialized workflows, technical instructions, and portable agent capabilities for distribution across different AI platforms. The project features a tool optimization suite used to refine skill triggers and evaluate the reliability of agent-activated capabilities. It includes a context-aware knowledge manager that organizes technical references into a hierarchy, loading them on demand to reduce token consumption. The system covers agentic workflow standardization, AI tool evaluation, and dynamic context management. It also implements operational constraint specifications and execution guardrails to ensure agents operate within safe boundaries using approved toolsets.

Flowise is a low-code platform designed for building and deploying complex language model workflows through a visual, node-based interface. It functions as an orchestrator for autonomous multi-agent systems, allowing users to construct conversational pipelines by connecting language models, memory stores, and external tools on a drag-and-drop canvas. The platform distinguishes itself through its support for sophisticated agentic patterns, including supervisor-worker delegation and iterative reasoning strategies. Users can design directed acyclic graphs to manage conditional branching, state persistence, and complex task distribution. It also provides a robust framework for retrieval-augmented generation, enabling the creation of self-correcting systems that can index document data and validate information autonomously. Beyond its visual design capabilities, the project serves as a comprehensive backend for AI applications. It includes a secure credential management layer for third-party API keys, role-based access controls, and a RESTful API that allows for programmatic management of chat sessions, workflows, and assistant configurations. The application is designed for flexible deployment, supporting containerized environments for consistent operation across local and cloud infrastructure. Detailed documentation and tutorials are available to guide users through the lifecycle of building, testing, and scaling production-ready AI agents.

Lark CLI is a terminal-based tool designed for automating tasks and managing resources across the Lark and Feishu productivity ecosystem. It functions as a cloud workspace automator and REST API client, providing a command line interface to programmatically manage organizational documents, calendars, emails, and tasks. The project distinguishes itself through an AI agent skill framework that allows for the integration and deployment of both bundled and custom skills. It features an identity-aware execution context that enables switching between user and bot identities, and employs a sidecar-based credential isolation model to prevent token leakage during API requests. The tool covers a wide range of business productivity capabilities, including the orchestration of multidimensional tables, spreadsheets, and wiki nodes. It provides utilities for messaging management, calendar scheduling, and the processing of HR workflows such as attendance tracking and approval instances. Additionally, it includes developer tools for API schema inspection, paginated request automation, and multi-format data serialization. The CLI manages the full OAuth authentication lifecycle, including interactive login and access scope verification.