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.
24 repositories · updated November 14, 2026
Infinity is a Rust runtime for building massively concurrent agent systems. Agents yield while tools run, then resume when events arrive, supporting both resident processes and serverless deployment such as AWS Lambda.
ActiveHealth 41/100
AgentRun is a self-hostable platform for managing agents, their revisions, and runs, built on Pi’s durable runtime. Its workflow DSL supports typed decisions and agent tasks, while the server provides a single API and interface for inspecting runs.
NewHealth 42/100
Model Harness is a ports-and-adapters agent framework for .NET 8 and .NET 10. It wraps model calls in a configurable loop with guides for context and sensors for checks, budgets, and interventions.
NewHealth 39/100
ACE helps language-agent teams build and refine reusable playbooks from task outcomes, rather than repeatedly rewriting prompts or fine-tuning models. It suits teams experimenting with offline or online adaptation for agent tasks and domain-specific reasoning.
MaintainedHealth 36/100
agent-harness is a Rust framework for calling Claude Code, OpenAI Codex, OpenCode, and compatible agents from code. It normalizes their output into one typed event stream so applications can switch agents without changing their event-handling loop.
NewHealth 38/100
Shepherd is a Python runtime for supervising agent work through durable, reversible Git-like execution traces. It retains outputs for review, replay, selection or discard, with OS-enforced permissions on macOS and Linux; Windows is unsupported.
NewHealth 41/100
AgentsKit is a TypeScript toolkit for building AI agents in JavaScript, from chat UIs to autonomous runtimes. Its lightweight core and shared contracts connect tools, memory, retrieval, and provider adapters without locking projects into one provider.
ActiveHealth 67/100
Declarative Agents uses YAML profiles and a Go runtime to define and execute tool-augmented LLM agents without encoding each workflow in a separate binary. It suits teams building configurable agent applications, but is now in maintenance mode and depends heavily on one contributor.
NewHealth 68/100
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.
ActiveHealth 39/100
Microsoft's Python toolkit uses the upstream Agent Control Specification policy runtime to govern autonomous AI agents. It adds policy enforcement, identity, audit, sandboxing, and reliability controls, with integrations for multiple agent frameworks and language SDKs.
ActiveHealth 68/100
DeepSeek-Reasonix is an open-source coding agent that reads and edits project files and runs commands on your computer. Use it in the terminal, desktop app, browser, or editor, with a built-in DeepSeek preset or another configured model.
ActiveHealth 84/100
A community-curated directory of AI agent frameworks, tools, platforms, research papers, and learning resources. Use it to explore the fast-changing agent ecosystem and compare options by category.
ActiveHealth 52/100