Open-Source AI Agent Frameworks

DSPy is a Python framework for developers building language model applications with local backends such as Ollama on a laptop or SGLang on a GPU server. It connects application code to those model servers, which handle inference on your hardware. It also supports cloud providers, so where model requests go depends on the backend you choose.

Adala is a Python framework for AI engineers and data scientists who want to run data-labeling and evaluation workflows in their own process. It works with local pandas DataFrames and ground-truth examples, but the documented OpenAI and OpenRouter configurations send task inputs to cloud models. Those connections need internet access and an API key.

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.

Loop.js is an AI agent framework for developers who want repeated attempts at a task with a separate check of the result. You define the goal and completion criteria, and the engine coordinates work until the verifier accepts it or a stopping condition ends the run.

MCP Agent is a Python framework for developers building AI agents that use tools through Model Context Protocol (MCP). It handles connections to MCP servers and provides reusable workflows for coordinating agents across a task.

Hypha is a TypeScript AI agent framework for developers building applications that need controlled tool use and recoverable work. It separates an agent's planning and tool choices from the execution layer that decides which actions may proceed.

Instrukt is a terminal app for developers who want to build and test AI agents on their own machine or server. It can index local code and documents, but its chat models run through OpenAI's API, which requires an API key and internet access. It doesn't provide local chat inference.

Project Orchestrator coordinates AI coding agents for developers working across tasks or related repositories. It gives agents a shared record of code, plans and decisions so each task can draw on earlier work.

AG2 is an open-source Python framework for developers building cooperating AI agents on their own machines or servers. Its Ollama integration lets agents use a local LLM; it also supports OpenAI, Anthropic and Gemini APIs, which send model requests to those providers. It runs on macOS, Windows and Linux under the Apache 2.0 license.

RubyLLM is an AI framework for Ruby and Rails developers building chat and agent features into their applications. Its shared API lets you switch between local and hosted models without writing a separate integration for each provider.

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.

BAML is a programming language for developers building AI agents, with a documented Ollama client for models running locally and tracing that runs on your machine. The OllamaClient integration is documented for the canary toolchain. The standard OpenAI connection sends model requests to OpenAI; installing BAML locally does not make that connection offline.

Octogent is a local web dashboard for developers coordinating several Claude Code sessions on one codebase. Its UI and API run on your machine, where it stores job context and transcripts. The supported workflow requires Claude Code. With its standard cloud connection, prompts and model outputs go to a remote provider; Octogent hosts the dashboard and task coordination.

Sim is an AI agent workspace for teams building automations and managing their use across an organization. It brings workflow creation, shared data and run monitoring into one place. You can self-host the workspace, but chat uses a Sim-managed service and requires sign-in to obtain a Chat API key.

Reef is self-hosted infrastructure for developers who want AI agents to learn from their interactions. It connects live requests and feedback to changes in model weights or the prompts, rules, and skills that guide an agent.

Agent Service Toolkit is a Python template for developers building their own AI agent services. It brings together agent logic, an API and a browser chat interface so you don't have to build each part from scratch.

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.

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.

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.

UFO³ is a self-hosted AI agent framework for developers and researchers automating tasks across Windows, Linux and Android devices. Its Galaxy coordinator splits a request into connected tasks, assigns them to suitable devices and tracks work that depends on results from another machine. The Python project is open source under the MIT license.

Archestra Community Edition is a self-hosted AI platform for teams managing access to company tools and models. It gives coding assistants, internal agents, and staff chat a shared place to enforce policies and track activity.

Bionic GPT is a self-hosted AI agent platform for internal teams building workflows around company knowledge and business systems. It supports tasks that involve several steps, tools and files while retaining context across the work.

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.

Pydantic DeepAgents is a terminal coding assistant and Python framework for developers who want to use or build their own AI agents. Both share a Pydantic AI foundation for carrying out tasks across files and tools.

Agent Squad is a framework for developers building assistants that divide work among specialized AI agents. It handles agent selection and conversation context so users can switch topics without starting a separate chat.

Pi Messenger connects Pi coding agent sessions working in separate terminals on the same project. It's for developers who want agents to divide work, share progress and avoid conflicting edits.

LangChainGo is a Go implementation of LangChain for developers adding language models to their own applications. It provides reusable components for connecting models to documents, tools, and conversation history.

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.

Omnigent coordinates AI agents for developers and teams who want to combine coding assistants, control their access, and supervise work in shared sessions. It runs locally or on a self-hosted server, with remote cloud sandboxes as another option.

Hexabot is an AI workflow automation platform for teams building customer service assistants and business automations. It links customer conversations to actions while letting teams keep workflow data on their own infrastructure.

Vercel AI SDK is a free TypeScript library for developers building apps and agents that use local models through Ollama or LM Studio. It runs within your application; those backends run the models. Its default model route uses Vercel AI Gateway, which sends requests to a cloud service, while the documented local integrations connect to your own model server.

OpenPipe ART is a Python framework for developers who want to train multi-step AI agents on the tasks their applications actually perform. It uses reinforcement learning through GRPO (Group Relative Policy Optimization) to improve model behavior based on experience and task rewards. It's open source under Apache 2.0.

swarmux is a command-line task runner for developers coordinating coding agents in tmux. Each task gets its own session and git worktree, so you can supervise separate jobs while keeping access to their terminals.

Blades is an AI agent framework for Go developers building conversational applications and automated workflows. It lets developers combine model connections, application tools and conversation memory within their own software.