Open Source AI Agents
AI agents are software systems that use models to interpret goals, decide what to do, and take actions through tools, services, or applications. They can break larger tasks into steps, retrieve information, interact with databases, and adapt their actions based on results. Agent technology helps automate workflows that are difficult to handle with a single prompt or a fixed sequence of rules, while allowing people to review or guide important decisions.
Open source options include agent frameworks, workflow orchestrators, tool integrations, memory and retrieval components, and interfaces for building or operating agents. When choosing one, consider project maturity, license, maintenance activity, model and tool compatibility, deployment requirements, and how it handles permissions, errors, and evaluation. These tools are useful to developers, researchers, and organizations exploring task automation or building assistants tailored to their needs.
65 repositories · updated October 3, 2026
Agent Anvil: CI-First Evaluation Harness for Tool-Using AI Agents
Agent Anvil is a robust, CI-first evaluation harness designed for AI agents that utilize tools. It meticulously runs scenario suites, captures detailed traces of agent behavior, and provides semantic grading to identify issues. The platform excels at clustering failures and suggesting concrete fixes for prompts, tools, and guardrails, ensuring agents behave safely and effectively.
Pydantic AI Harness: Enhancing Your AI Agents with Robust Capabilities
Pydantic AI Harness is the official capability and harness library for Pydantic AI, designed to extend agents for complex, long-running tasks. It provides a modular system of "capabilities" for functionalities like file system interaction, web research, memory, and sub-agent delegation. This library enables developers to build sophisticated and durable AI agents with ease.
Memoh: An Open-Source Multi-Agent Platform with Dedicated AI Workspaces
Memoh is an innovative open-source multi-agent platform designed to provide each AI agent with its own dedicated cloud computer. This includes a filesystem, desktop, browser, network, and persistent long-term memory, ensuring agents remain online 24/7. Users can integrate their own API keys or host existing AI models, fostering a versatile and always-on environment for AI development and deployment.
Graphon: A Python Graph Execution Engine for Agentic AI Workflows
Graphon is an innovative Python-based graph execution engine designed for building agentic AI workflows. It provides a robust framework for orchestrating complex AI tasks, featuring event-driven execution, graph validation, and shared runtime state. This evolving repository already includes a functional engine, built-in nodes, and end-to-end examples for developers.
text-to-cad: AI Agent Skills for CAD, CAE, and CAM Workflows
text-to-cad is a comprehensive Python library developed by earthtojake, providing a rich set of agent skills for Computer-Aided Design (CAD), Computer-Aided Engineering (CAE), and Computer-Aided Manufacturing (CAM). It enables AI agents to generate, inspect, source, slice, and manage CAD and robot-description artifacts, streamlining complex engineering processes.
uta: A CLI Agent Orchestrator for Parallel AI Task Management
uta is a command-line interface (CLI) agent orchestrator designed to decompose complex goals into parallel subtasks. It can dispatch these tasks to various agent CLIs like Claude Code or Gemini CLI, record every step of the process, and synthesize the final results. This tool enhances agent capabilities by enabling parallelism and cross-provider task execution.
Open Code Review: AI-Powered Code Review Tool from Alibaba
Open Code Review is an AI-powered command-line interface tool for code review, battle-tested at Alibaba's scale. It leverages a hybrid architecture, combining deterministic engineering with an LLM agent, to provide secure, fast, and efficient code analysis. This tool generates precise, line-level comments and supports a multi-language ruleset, ensuring high-quality code reviews.
oh-my-hermes: Enhance Hermes Agent with Advanced AI Workflow and Memory
oh-my-hermes is an all-in-one plugin designed to significantly enhance the Hermes Agent. It provides advanced coding intelligence, a robust long-term memory system, and optimized workflow packages, transforming standard Hermes requests into structured, actionable tasks with clear operational layers.
ASC: A Super Fast Android Decompiler for Mobile Reverse Engineering
ASC is an innovative and exceptionally fast Android decompiler front-end, specifically designed for mobile researchers and agents. It redefines traditional decompilation by directly querying compiled artifacts, offering on-demand code extraction and analysis without heavy preprocessing. This approach results in significantly reduced memory usage and lightning-fast performance, even on large APKs.
Awesome-Self-Evolving-Agents: A Curated List for AI Agent Research
Awesome-Self-Evolving-Agents is a comprehensive GitHub repository offering a curated collection of resources on self-evolving agents. It includes a systematic survey, research papers, benchmarks, and open-source projects, providing valuable insights into this rapidly advancing field of AI. This repository serves as an essential guide for researchers and developers exploring model-centric, environment-centric, and co-evolutionary approaches.
open-slide: An AI-Native Slide Framework for React Presentations
open-slide is a powerful slide framework built for AI agents, enabling users to create presentations by describing them in natural language. Coding agents then generate the React components, while open-slide handles the canvas, scaling, navigation, and presentation modes. This allows agents to focus entirely on content, streamlining the creation of polished, agent-driven decks.
best-skills: Daily-Updated Rankings for Top Agent Skills
The LinklyAI/best-skills repository offers daily-updated rankings of the top 100 agent skills. It aggregates data on installs, growth, and social buzz from various platforms like skills.sh, ClawHub, Tencent SkillHub, GitHub, and X. This open-data project provides a comprehensive, cross-ecosystem view of agent skill performance, making it an invaluable resource for developers and researchers.