GolemCore Bot
Agent frameworksGolemCore Bot is an agent platform for AI-native teams, with channel-connected agents, skills, plugins, MCP servers, memory, and execution tracing.
Choose the foundations for an agent application: model integrations, orchestration and the developer tools around them. Your team's language, workflow complexity and operating environment are useful starting points.
GolemCore Bot is an agent platform for AI-native teams, with channel-connected agents, skills, plugins, MCP servers, memory, and execution tracing.
Google's Agent Development Kit for building agent tools, workflows and evaluation pipelines.
A provider-agnostic personal AI agent that runs in terminals from laptops and remote servers, with local tools for coding and general knowledge work.
An Electron desktop app for installing, running, monitoring, and updating HagiCode Server, with local resource monitoring and agent executor selection.
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
A model-agnostic runtime for production AI agent teams, with dynamic worker colonies, shared task state, and human oversight.
A TypeScript SDK implementing Hashgraph Online Consensus Standards, with Registry Broker clients for agent discovery and chat.
Julep builds durable, composable AI agents as workflows that can resume after failures, retry safely, and expose step-by-step execution.
A Kubernetes operator for deploying and managing AI agent runtimes, with bounded self-healing that keeps LLMs out of the cluster's workload write path.
An autonomous multi-agent coding orchestrator that runs coding agents through work cycles with independent verification.
LangChain is a framework enabling context-aware reasoning applications with integrated libraries, templates, and developer tools
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
Build stateful agent workflows with explicit control over steps, persistence and human review.
LangGraph.js is a TypeScript and JavaScript library enabling the development of stateful, multi-actor applications with LLMs, featuring capabilities to construct cyclic coordination across multiple computation steps for complex agent-like behaviors, with support for conditional edges and cycles, not limited to DAGs, and extensive documentation with examples on implementation
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
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
LoopGPT 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
A TypeScript framework for building AI agents and applications.
Turn a shortlist of agent frameworks into a practical decision using task boundaries, recovery tests, integration needs and maintenance costs.
Read the guideSeparate task state, user preferences and source documents, then choose storage, retrieval and deletion rules for each type of information.
Read the guide