Open Source AI Agents - Page 5
Sort By:
-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
BISHENG
BISHENG is an open LLM devops platform for next generation apps
BISHENG is an open LLM application DevOps platform, focusing on enterprise scenarios. It has been used by a large number of industry-leading organizations and Fortune 500 companies. "Bi Sheng" was the inventor of movable type printing, which played a vital role in promoting the transmission of human knowledge. We hope that BISHENG can also provide strong support for the widespread implementation of intelligent applications. Everyone is welcome to participate. -
2
Claude Autoresearch
Claude Autoresearch Skill, autonomous goal-directed iteration
Claude Autoresearch is an autonomous research assistant system that automates the process of exploring, collecting, and synthesizing information across multiple iterations. It is designed to mimic human research behavior by generating queries, evaluating results, and refining its approach based on previous findings. The system likely integrates with external data sources, allowing it to gather information from diverse inputs and organize it into structured outputs. Its iterative loop enables deeper exploration of topics over time, making it particularly useful for complex or open-ended research questions. The architecture emphasizes autonomy, reducing the need for constant user input while still producing meaningful insights. It may also include summarization and reporting capabilities to present findings in a digestible format. Overall, autoresearch represents a step toward self-directed knowledge discovery systems that continuously improve their outputs through iteration. -
3
Cua
Open-source infrastructure for Computer-Use Agents. Sandboxes
Cua is an open-source command-line utility and workflow orchestrator designed to help developers define, compose, and run common tasks with a unified interface, promoting consistency and reuse across projects. It introduces a declarative syntax for specifying build scripts, automation pipelines, environment setups, and project-specific commands so contributors don’t need to memorize disparate scripts or tooling across languages and ecosystems. Cua can also manage task dependencies, handle cross-platform invocations, and simplify complex workflows into simple aliases or compound commands that are easy to share in teams. By centralizing shared commands in a structured, documented config, it helps reduce errors, accelerates onboarding of new contributors, and keeps task definitions versioned with the codebase. The CLI is typically lightweight, easy to install, and designed to integrate with existing toolchains and shells without friction. -
4
GenericAgent
Self-evolving autonomous agent framework
The GenericAgent project is a flexible framework for building autonomous AI agents that can operate across diverse tasks and environments. It is designed around modularity, allowing developers to define agents with interchangeable components such as tools, memory systems, and reasoning strategies. The architecture emphasizes generality, enabling the same agent framework to be adapted for different domains including coding, research, and task automation. It integrates with modern language models to provide planning, execution, and iterative reasoning capabilities, making it suitable for complex workflows. The project also focuses on extensibility, allowing developers to plug in custom tools or APIs and tailor agent behavior to specific use cases. By abstracting common agent patterns, it reduces the overhead of building agent systems from scratch. Overall, GenericAgent provides a foundation for scalable and reusable AI agent development. -
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
5
Hermes Agent Orange Book
From Beginner to Master · Orange Book Series
Hermes Agent Orange Book is a structured knowledge resource and guide for building and understanding Hermes-style autonomous agents. It compiles principles, workflows, and patterns used in agent-based systems into an organized format. The project focuses on explaining how agents manage memory, tools, and iterative reasoning processes. It serves as both a reference and a learning resource for developers working with autonomous AI systems. The content emphasizes practical implementation strategies rather than abstract theory. It is particularly useful for those building or studying agent architectures. Overall, it provides a comprehensive overview of agent design and operation. -
6
HybridClaw
The enterprise operating layer for open agents
HybridClaw is an emerging open-source framework focused on enabling hybrid AI agent systems that combine local execution, tool integration, and multi-agent orchestration into a cohesive development environment. It is designed to work alongside modern agent ecosystems such as OpenClaw, Claude Code, and similar agentic coding tools, providing a flexible infrastructure for managing agent behaviors, workflows, and capabilities. The project emphasizes modularity, allowing developers to define and compose “skills” or capabilities that agents can invoke dynamically, enabling more adaptive and context-aware automation. HybridClaw aims to bridge the gap between isolated AI tools and fully orchestrated agent systems by enabling communication, coordination, and shared context across multiple agents or processes. It is particularly relevant in scenarios where developers want to build complex autonomous systems that interact with codebases. -
7
Langroid
Harness LLMs with Multi-Agent Programming
Given the remarkable abilities of recent Large Language Models (LLMs), there is an unprecedented opportunity to build intelligent applications powered by this transformative technology. The top question for any enterprise is: how best to harness the power of LLMs for complex applications? For technical and practical reasons, building LLM-powered applications is not as simple as throwing a task at an LLM system and expecting it to do it. Effectively leveraging LLMs at scale requires a principled programming framework. In particular, there is often a need to maintain multiple LLM conversations, each instructed in different ways, and "responsible" for different aspects of a task. -
8
Leon
Leon is your open-source personal assistant
Leon is an open-source personal AI assistant platform that lets users run a conversational agent locally or on their own servers, providing an alternative to cloud-hosted assistants with a focus on privacy, extensibility, and modular components. It’s designed to process natural language queries and perform tasks such as information retrieval, task automation, scheduling, and custom workflows defined by the user. The architecture emphasizes modularity: you can plug in different language models, intent recognizers, or action handlers to tailor Leon for specific domains like productivity, home automation, or developer tooling. Because it runs independently of third-party cloud services, Leon gives users full control over their data and system behavior, which is especially important for privacy-conscious users and organizations. -
9
Letta
Letta (formerly MemGPT) is a framework for creating LLM services
Letta is an AI-powered task automation framework designed to handle workflow automation, natural language commands, and AI-driven decision-making. -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
10
Letta Code
The memory-first coding agent
Letta Code is a memory-first CLI coding agent built on the Letta platform that offers developers a persistent AI assistant capable of learning and improving over time rather than resetting state each session, giving agents a sense of continuity and context across coding tasks. Unlike traditional session-based coding tools, Letta Code attaches a long-lived agent to a working directory so that the agent accumulates memory about a project’s structure, preferences, and history, effectively acting as a collaborative partner rather than a stateless helper. Users can initialize and connect the agent to various models, including popular large language models, and issue commands, refactor code, or ask context-aware questions directly in the terminal, with memory retained across multiple interactions. -
11
Mike
OSS AI Legal Platform
Mike is a software project that appears to focus on automation or tooling, likely designed to streamline workflows related to development, deployment, or data processing. It may function as a command-line utility or lightweight framework that integrates with existing systems to improve efficiency. The project emphasizes simplicity and clarity, providing focused functionality without unnecessary overhead. Its design likely supports extensibility, allowing users to adapt it to specific use cases or integrate it into larger pipelines. The repository may include scripts, utilities, or abstractions that reduce repetitive tasks and improve productivity. Overall, mike represents a pragmatic approach to solving targeted technical problems through concise tooling. -
12
PentestAgent
AI agent framework for black-box security testing
PentestAgent is an open-source autonomous security testing platform designed to help organizations identify vulnerabilities and assess security posture by simulating real-world attack scenarios without manual intervention. It brings a modular and automated approach to penetration testing by orchestrating a suite of tools and scripts that can emulate common exploitation techniques, reconnaissance workflows, and post-exploitation activities across targets. Users configure rules, policies, and environments, and the agent continuously probes for weaknesses, prioritizes findings, and generates contextual reports that help both technical and non-technical stakeholders understand risk exposure. Because it supports a range of plug-ins and external security tools, pentestagent can be adapted for web applications, network infrastructure, API surfaces, and even cloud environments, making it flexible for diverse security programs. -
13
Semantic Kernel
Integrate cutting-edge LLM technology quickly and easily into your app
Semantic Kernel is an open-source SDK that lets you easily combine AI services like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C# and Python. By doing so, you can create AI apps that combine the best of both worlds. To help developers build their own Copilot experiences on top of AI plugins, we have released Semantic Kernel, a lightweight open-source SDK that allows you to orchestrate AI plugins. With Semantic Kernel, you can leverage the same AI orchestration patterns that power Microsoft 365 Copilot and Bing in your own apps, while still leveraging your existing development skills and investments. -
14
Skills For Real Engineers
Skills for Real Engineers. Straight from my .claude directory
Skills For Real Engineers is a curated collection of modular AI “skills” designed to improve how developers interact with coding agents by enforcing structured engineering workflows. Each skill is a small, focused instruction set that guides an AI through tasks such as planning, refactoring, testing, or architectural analysis. Instead of relying on vague prompts, the system encodes repeatable processes that ensure consistent and higher-quality outputs. The repository includes tools for converting conversations into product requirements, breaking plans into actionable issues, and stress-testing ideas through structured questioning. It emphasizes disciplined thinking before coding, encouraging developers to fully explore design decisions. Skills can be installed individually and integrated into agent environments, making them highly composable. Overall, the project transforms AI from a reactive assistant into a process-driven engineering collaborator. -
15
Sophia
TypeScript AI platform with AI chat, Autonomous agents
Sophia is an AI-based fraud detection framework designed to identify and mitigate fraudulent activities in digital transactions and advertising. -
16
Joget
AI Powered Open Source Platform to Easily Build Enterprise Web Apps
Joget offers an open-source, AI-powered platform that converges no-code/low-code development with AI to rapidly build and customize enterprise applications at scale. By combining AI with visual app builders—not raw code—Joget makes app generation faster, safer, and more accessible for everyone. With Generative AI and Agentic AI capabilities, Joget Intelligence enables organizations to automate and enhance processes while maintaining oversight and compliance. Unlike typical AI code generation, Joget's visual-first approach ensures applications are maintainable and governed within collaborative human workflows. As an Application and Integration Fabric, Joget connects legacy and modern systems seamlessly. Its extensible, open-source core and plugin architecture offer unmatched flexibility, and its White Label solution allows OEMs and digital solution providers to fully rebrand the platform. Trusted by startups, global enterprises, and government agencies across the globe. -
17
AIPex
AI browser automation assistant, no migration and privacy first
AIPex is an AI-augmented development toolkit and workflow platform that aims to accelerate software productivity by integrating intelligent assistants, code generation tools, and customizable automation patterns directly into developer workflows. Rather than treating AI as a separate helper, AIPex embeds AI capabilities into common tasks like scaffolding components, generating tests, analyzing code quality, and performing refactors, allowing developers to stay in flow while benefiting from model-assisted insights. It supports modular plugin architecture so teams can extend or customize how assistants behave based on project conventions, code standards, or tooling preferences. AIPex also includes orchestration pipelines that let teams define multi-step AI-driven transformations — for example, generating code then running validation, producing documentation, and opening change requests — all within a unified pattern. -
18
Academic Research Skills for Claude Code
Academic Research Skills for Claude Code
Academic Research Skills is a structured learning repository aimed at improving users’ ability to conduct rigorous academic research, particularly in technical and scientific domains. It compiles methodologies, frameworks, and best practices for literature review, critical analysis, and research writing. The project is designed as a self-guided resource, helping learners understand how to evaluate sources, synthesize information, and develop strong arguments. It likely integrates examples, templates, and conceptual explanations to bridge the gap between theory and practical research execution. The repository emphasizes skill-building rather than automation, making it especially useful for students and early-career researchers. Its overall goal is to enhance research literacy and reproducibility in academic workflows. -
19
Agentic Data Scientist
An end-to-end Data Scientist
Agentic Data Scientist is an experimental AI-driven research framework that orchestrates data science workflows through autonomous agents that can reason, plan, and execute complex analytics tasks. Unlike traditional scripted pipelines, this project lets AI agents break down high-level research goals into sub-tasks such as data acquisition, cleaning, modeling, evaluation, and reporting, with minimal human direction. Each agent is designed to independently call functions, interact with data sources, and adapt to uncertainties during processing, enabling iterative refinement of models without manual coordination. The framework supports interoperability with existing data tools and libraries, letting the agents leverage libraries like pandas, scikit-learn, and visualization frameworks to perform real computations rather than mock demonstrations. -
20
AutoGPT-Next-Web
Assemble, configure, and deploy autonomous AI Agents in your browser
One-Click to deploy well-designed AutoGPT-Next-Web web UI on Vercel. -
21
Ax
Build LLM powered Agents and "Agentic workflows"
Build intelligent agents quickly — inspired by the power of "Agentic workflows" and the Stanford DSPy paper. Seamlessly integrates with multiple LLMs and VectorDBs to build RAG pipelines or collaborative agents that can solve complex problems. Advanced features streaming validation, multi-modal DSPy, etc. We've renamed from "llmclient" to "ax" to highlight our focus on powering agentic workflows. We agree with many experts like "Andrew Ng" that agentic workflows are the key to unlocking the true power of large language models and what can be achieved with in-context learning. Also, we are big fans of the Stanford DSPy paper, and this library is the result of all of this coming together to build a powerful framework for you to build with. -
22
Burr
Build applications that make decisions. Chatbots, agents, simulations
Burr makes it easy to develop applications that make decisions (chatbots, agents, simulations, etc...) from simple python building blocks. Burr works well for any application that uses LLMs and can integrate with any of your favorite frameworks. Burr includes a UI that can track/monitor/trace your system in real-time, along with pluggable persisters (e.g. for memory) to save & load application state. -
23
CAMEL AI
Finding the Scaling Law of Agents. A multi-agent framework
The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their "cognitive" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. -
24
ChatArena
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments
ChatArena is a library that provides multi-agent language game environments and facilitates research about autonomous LLM agents and their social interactions. -
25
ChemCrow
Chemcrow
ChemCrow is an AI-powered framework designed to assist in chemical research and discovery. It integrates AI models with chemical knowledge bases to provide intelligent recommendations for synthesis planning, reaction prediction, and material discovery. This tool helps automate and accelerate research in computational chemistry and drug development.
