Open-Source AI Agent Frameworks

Activepieces is a self-hosted automation platform for teams that want AI agents and app workflows on their own servers. It runs with Docker or Kubernetes, alongside a managed cloud offering. Self-hosting controls where the app runs; connections to Anthropic, OpenAI, AWS Bedrock or Google Gemini still send model requests to those providers using your credentials.

Browser Use is an AI browser agent for developers automating tasks across websites. It can work through pages and forms to complete jobs such as booking an appointment.

Superpowers adds a development workflow to AI coding assistants. It's for developers who want to approve a design before implementation and have the agent work through a plan with testing and review.

Pi is a terminal coding agent for developers who want an assistant they can adapt to their projects. Its small core supports custom workflows through extensions and shareable packages.

DSH AgentTeams coordinates AI agents inside DeepSeek Harness for coding, research and review tasks. A lead agent assigns work to specialists and combines their results, while you can review the proposed team before execution.

DocsGPT helps teams search company documents and build AI assistants that answer from those materials. It can run inside your network with local models, including an air-gapped deployment where documents and questions stay within that network.

data-to-paper is an open-source Python framework for researchers who want AI agents to work through a dataset and draft a scientific paper whose numerical claims they can check. Its defining feature is traceability: readers can click a value in the manuscript and follow it back to the specific analysis code that produced it.

VoltAgent is a TypeScript AI agent framework for developers building assistants and automated workflows with local models through Ollama. Its VoltOps console can be self-hosted or used as a cloud service. Model execution depends on the provider: Ollama supports local inference, while OpenAI, Anthropic and Google connections send requests to those remote services.

Haystack is a Python framework for developers building AI agents, document search and applications that answer questions using their own data. Its pipelines give teams control over the information a model receives and the steps that produce an answer.

CrewAI is a Python framework for developers automating work with teams of AI agents. It combines agents that make decisions with explicit workflow logic, so a process can include both autonomous work and predictable steps.

npcpy is a Python library for developers and researchers building AI agents and applications with language models. It supports local LLM backends as well as cloud providers, so projects can choose where model requests run.

claudectl manages multiple Claude Code sessions for developers who need to track parallel work and intervene when an agent gets stuck. Its terminal dashboard brings session activity, approvals and spending into one view.

DB-GPT is a self-hosted AI data assistant for teams analyzing business data and developers building data applications. It connects plain-language questions to database queries and code-based analysis.

AI Legion is a self-hosted framework for developers who want several AI agents to work together on tasks. The program runs on your own machine through Node.js, while OpenAI's cloud models handle the language processing. It's open source under MIT.

Inkeep Agents is an AI agent builder for teams creating chat assistants and automated workflows. It supports collaboration between people who prefer a visual editor and developers who work in code.

LangChain is an open-source framework for developers building AI agents and LLM applications, including apps that run models locally through Ollama. Its Python ChatOllama integration connects to open-weight models such as gpt-oss. You write the application in code, while Ollama handles local inference.

GenericAgent runs tasks on your computer using cloud models to decide what to do. It's for people who want an AI agent to work across websites, files and desktop apps, then save successful workflows for reuse. Model calls require API keys and an internet connection, with requests going to the selected provider. It supports Claude, Gemini, Kimi and MiniMax.

Exo Agent Framework is for developers building long-running AI agents that can revise their own code, tools and prompts. It preserves agent identity and history as their behavior changes across runs.

OpenHarness is a Python framework for developers and researchers building AI agents that can act on files, use tools and retain work across sessions. It includes ohmo, a personal agent that handles coding tasks through Feishu, Slack, Telegram or Discord.

AstrBot is an AI chatbot platform for personal assistants, customer support bots and team automation inside messaging apps. You can host it on your own computer or server and choose a local or cloud model backend.

Google ADK is an AI agent framework for developers building applications that carry out multi-step tasks. Agents can run on your own infrastructure and use locally running models through adapters, or connect to hosted providers such as Gemini.

Ouroboros is a locally installed workflow engine for developers who want to define requirements and check an AI coding agent's output. It runs through a terminal CLI, a Claude Code plugin or an MCP server. Your chosen coding runtime supplies the agent and model access. When used with Claude through Claude Code's standard cloud connection, model requests go to that external service.

LazyLLM is a Python framework for developers building applications with multiple AI agents. It brings application workflows, model training and evaluation together so teams can refine a prototype using task-specific data.

Plano is a self-hosted AI gateway for developers building applications with multiple agents. It handles shared routing, orchestration and monitoring outside the agents, so developers don't need to build those functions into each one.

MS Agent is an open source Python agent framework with a self-hosted web server for working on local projects. It's for developers building research assistants and coding workflows that continue across sessions. Code execution and project file work run locally; the default model integration uses ModelScope's API and requires an API key and internet access.

Ringer coordinates parallel AI coding agents on your machine. It's for developers who want to divide implementation work among workers and judge the results with executable checks.

XAgent is an experimental self-hosted AI agent for multi-step coding, research and data-analysis tasks. It plans subtasks, revises plans as work progresses and dispatches actions to agents. A command-line interface and browser UI let you guide a run or provide missing information.

Rivet AgentOS is a runtime for developers building applications where AI agents need a working environment for code and tools. It runs inside an existing backend process, with WebAssembly isolation instead of a separate virtual machine for each agent.

Pi Subagents is an extension for developers who want to divide coding work among specialized AI agents in pi. Agents run in separate sessions, so you can assign distinct roles and follow their progress individually.

Nexent is a self-hosted AI agent platform for people and teams who want to build agents by describing tasks in plain language. It generates executable agents without requiring code or a visual workflow editor.

Oh My Subagents coordinates Codex and Claude agent teams for developers and researchers handling coding, investigations or independent code review. It saves delegated work and progress so teams can resume interrupted tasks.

tRPC Agent Go is an open-source framework for developers building agent services with local automation in Go. It can execute skill scripts in an isolated workspace and includes deployable HTTP servers for agent interfaces. The documented OpenAI and DeepSeek workflows require a provider API key, so running the service yourself doesn't make those model calls local.

Multi-Agent Shogun runs and coordinates separate AI coding assistants on your computer or a Linux server. It's for developers dividing implementation and research across parallel tasks. Coordination happens locally, but Claude Code’s standard cloud connection sends prompts and model outputs over the network to their model provider; other agents use their chosen CLI's model access and authentication.

AgentFlow is a Python framework for developers coordinating coding agents across tasks that depend on one another. It runs Codex, Claude, Kimi, and Pi agents in workflows that can split work and bring the results back together.

MaxKB is an AI agent platform for organizations building support bots, internal knowledge assistants and business automation. It combines answers based on company documents with workflows that can act through connected tools.

OpenAI Agents SDK is a Python framework for developers building tool-using agents with local models or cloud APIs. It supports gpt-oss through Ollama, with LM Studio also documented as a local model option. OpenAI models use the remote Responses API by default and require an API key, even when the agent runtime and workspace run on your machine.