Open Source Agent Frameworks
Agent frameworks provide building blocks for creating software agents that use language models to interpret requests, call tools, maintain state, and perform multi-step tasks. They help developers manage the coordination, memory, and execution logic that would otherwise need to be assembled from scratch, while making agent behavior easier to test and adapt. Some frameworks focus on individual agents, while others support workflows involving multiple agents or external services.
Open source options range from lightweight libraries and orchestration runtimes to visual builders, self-hosted platforms, and tools for testing or governing agent behavior. When choosing one, consider project maturity, license, maintenance activity, supported model and tool integrations, deployment requirements, and the complexity of its abstractions. These frameworks are useful to developers and teams prototyping agent applications, building production workflows, or seeking greater control over how AI systems run and connect to other software.
28 repositories · updated October 5, 2026
agent-harness: Use Coding Agents from Rust Applications
A Rust framework that gives multiple coding agents a shared interface and typed event stream. Use it to embed agent runs in applications without writing separate output parsers for each provider or CLI.
shepherd: Supervise Agents with Reversible Execution Traces
Shepherd records agent work as inspectable, reversible execution traces and keeps changes as proposals for review. It is aimed at developers building systems that supervise, replay, or manage the work of other agents.
pydantic-ai-harness: Add Capabilities for Long-Running AI Agents
A Python capability library that extends Pydantic AI agents with tools and support for coding, research, memory, delegation, and context management. This repository is no longer updated; development continues in the Pydantic AI repository.
harnessrouter: Unify Agent Harnesses Behind One API
HarnessRouter is a self-hosted Python service that exposes multiple agent harnesses through a unified, OpenAI Responses-compatible API. It suits teams building agent features that want shared session, streaming, file, and cancellation handling across harnesses.
agentskit: Build AI Agents in JavaScript
AgentsKit is a TypeScript toolkit for building JavaScript AI agents from composable packages for model adapters, runtime, tools, memory, retrieval, and user interfaces. It suits developers who need more than a chat SDK and want to keep provider and component choices flexible.
aport-agent-guardrails: Authorize AI Agent Actions Before Execution
APort adds policy checks before supported AI agent tools run, helping teams limit prompt-injection risks and unauthorized actions. It provides runtime integrations and GitHub repository checks, with local or hosted verification options.
adl-cli: Scaffold A2A Agent Servers from YAML
adl-cli turns YAML Agent Definition Language files into project scaffolding for A2A servers. It is aimed at developers who want consistent agent projects across Go, Rust, or TypeScript, with optional enterprise, development, and deployment setup.
declarative-agents: Define Tool-Augmented Agents in YAML
Declarative Agents is a Go runtime that interprets YAML profiles to run tool-augmented LLM agents. It suits teams that want to change agent workflows through configuration rather than rebuilding the runtime.
best-of-Agent-Harnesses: Compare AI Agent Harnesses
A curated, regularly rescored catalog of 167 AI agent harnesses and related tools. Compare projects by capabilities and use its guides, templates, playbooks, or machine-readable data to choose a fit for your agent workflow.
agent.cpp: Build Local AI Agents in C++
agent.cpp is a C++ library for building agents that run small language models locally through llama.cpp. It provides an agent loop, tools, callbacks, and support for GGUF models, grammar constraints, and LoRA adapters.
adk-rust: Build AI Agents with Rust
ADK-Rust is a modular framework for building and deploying asynchronous AI agents in Rust. It supports multiple model providers, tools, workflows, memory, and real-time voice, with composable crates for projects ranging from prototypes to production services.
agent-governance-toolkit: Govern Autonomous AI Agent Actions
Microsoft’s Agent Governance Toolkit adds policy checks, identity, audit logging, sandboxing, and reliability controls around autonomous agents. It suits teams integrating agent frameworks that need application-level enforcement and evidence of tool-call decisions.