Search Results for "agent" - Page 2
Sort By:
Showing 280 open source projects for "agent"
View related business solutions-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
OpenAI Agents JS
A lightweight, powerful framework for multi-agent workflows
...The SDK is provider-agnostic, meaning while it’s deeply compatible with OpenAI’s APIs, you can also adapt it to use other backends or extension layers. At its core, it introduces primitives like Agents, Tools, Guardrails, and Handoffs, letting you define structured multi-agent systems in a modular way. The repo includes examples showing how to build agents that call local functions, chain between agents, validate input/output, stream responses, and interact in real time (e.g. voice agents via WebRTC). It also has tracing and debugging support so you can introspect how agents executed their workflows. Because it aligns closely with the Python Agents SDK, it aims for cross-language parity so that JS/TS devs can adopt similar agent architectures. -
2
skills
The open agent skills tool - npx skills
...The CLI supports pulling skills from common git sources, including GitHub shorthand, full URLs, direct paths inside repos, GitLab URLs, generic git remotes, and even local folders. It is designed to work across a wide range of agents and editors, so one skill package can be installed into multiple agent-specific directories without rewriting anything for each environment. It also supports both interactive and automation-friendly flows, including non-interactive installs for CI and bulk installs for all skills, which makes it usable for teams that want consistent agent capability across machines. -
3
Agents.jl
Agent-based modeling framework in Julia
Agents.jl is a pure Julia framework for agent-based modeling (ABM): a computational simulation methodology where autonomous agents react to their environment (including other agents) given a predefined set of rules. The simplicity of Agents.jl is due to the intuitive space-agnostic modeling approach we have implemented: agent actions are specified using generically named functions (such as "move agent" or "find nearby agents") that do not depend on the actual space the agents exist in, nor on the properties of the agents themselves. ... -
4
Everything Claude Code
Complete Claude Code configuration collection
...The repository curates reproducible templates that demonstrate how Claude Code agents can participate in end-to-end developer journeys such as building new features, adhering to coding standards, generating documentation, and automating refactor patterns. It also includes example orchestrations that showcase multi-step agent workflows, letting developers see how to compose small, discrete agent capabilities into productive, cohesive sequences. Because it is designed to be modular, individuals and teams can pull in only the skills they need, combine them with custom logic, or share their own extensions with the community. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
Antigravity Awesome Skills
The Ultimate Collection of 700+ Agentic Skills for Claude Code
Antigravity Awesome Skills is a playful yet practical repository that curates a set of clever, expressive, and sometimes whimsical AI agent skill templates designed to help users bootstrap agent behavior quickly. Rather than focusing on production-grade systems, it provides creative and high-impact skills that demonstrate how agents can be used to automate tasks, generate content, assist with daily operations, or integrate into larger workflows with minimal configuration. ... -
6
BotSharp
AI Multi-Agent Framework in .NET
Conversation as a platform (CaaP) is the future, so it's perfect that we're already offering the whole toolkits to our .NET developers using the BotSharp AI BOT Platform Builder to build a CaaP. It opens up as much learning power as possible for your own robots and precisely control every step of the AI processing pipeline. BotSharp is an open source machine learning framework for AI Bot platform builder. This project involves natural language understanding, computer vision and audio... -
7
Google Workspace CLI
Command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, etc.
...The CLI supports multiple authentication methods, including OAuth login, service accounts, and environment-based credentials for automated environments. With built-in agent skills and automation features, it enables developers and AI systems to manage and automate Google Workspace workflows efficiently. -
8
Quickemu
Quickly create and run optimized Windows, macOS and Linux
Quickly create and run optimized Windows, macOS, and Linux virtual machines. Quickemu is a wrapper for the excellent QEMU that automatically "does the right thing" when creating virtual machines. No requirement for exhaustive configuration options. You decide what operating system you want to run and Quickemu takes care of the rest. The original objective of the project was to enable quick testing of Linux distributions where the virtual machines and their configuration can be stored... -
9
DeviceDetector
The Universal Device Detection library will parse any User Agent
Device Detector is a PHP library for parsing user-agent strings to detect devices, operating systems, and browsers, widely used in analytics and tracking. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
TradingAgents
Chinese Financial Trading Framework Based on Multi-Agent LLM
TradingAgents-CN is a Chinese-enhanced, multi-agent LLM framework aimed at building financial analysis and trading-oriented workflows, with an emphasis on collaboration between specialized agents rather than a single monolithic prompt. It organizes market-related tasks into roles and stages so different agents can contribute research, reasoning, aggregation, and decision support in a structured pipeline. -
11
JMX Exporter
A process for exposing JMX Beans via HTTP for Prometheus consumption
JMX to Prometheus exporter: a collector that can configurable scrape and expose mBeans of a JMX target. This exporter is intended to be run as a Java Agent, exposing a HTTP server and serving metrics of the local JVM. It can be also run as a standalone HTTP server and scrape remote JMX targets, but this has various disadvantages, such as being harder to configure and being unable to expose process metrics (e.g., memory and CPU usage). Running the exporter as a Java agent is strongly encouraged. -
12
k-skill
Skill collection for Koreans - SRT, KTX, KakaoTalk, Hangul
...The system provides a standardized structure for skills, enabling consistency across different workflows and improving interoperability between tools. It is designed to integrate with modern AI agent ecosystems, allowing developers to extend functionality without rewriting core logic. The project emphasizes simplicity and modularity, making it easier to manage large collections of skills in complex environments. It also supports extensibility, enabling users to define custom skills tailored to their needs. Overall, k-skill serves as a foundational layer for building structured and scalable AI agent capabilities. -
13
Stakpak
Ship your code, on autopilot. An open source agent
Stakpak is an open-source autonomous DevOps agent designed to run continuously on a machine, managing infrastructure, deployments, and operational tasks with minimal human intervention. It acts as a persistent system-level assistant that monitors applications, executes DevOps workflows, and only alerts humans when necessary, effectively automating routine operational responsibilities. -
14
OpenShell
OpenShell is the safe, private runtime for autonomous AI agents.
...By combining container isolation, policy enforcement, and agent orchestration, OpenShell offers a secure infrastructure for developing and operating AI agents. -
15
PydanticAI
Agent Framework / shim to use Pydantic with LLMs
When I first found FastAPI, I got it immediately. I was excited to find something so innovative and ergonomic built on Pydantic. Virtually every Agent Framework and LLM library in Python uses Pydantic, but when we began to use LLMs in Pydantic Logfire, I couldn't find anything that gave me the same feeling. PydanticAI is a Python Agent Framework designed to make it less painful to build production-grade applications with Generative AI. Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor, and many more). -
16
Conftest
Write tests against structured configuration data
...For instance, you could write tests for your Kubernetes configurations, Tekton pipeline definitions, Terraform code, Serverless configs, or any other structured data. Conftest relies on the Rego language from Open Policy Agent for writing policies. If you're unsure what exactly a policy is, or unfamiliar with the Rego policy language, the Policy Language documentation provided by the Open Policy Agent documentation site is a great resource to read. -
17
Holochain
The current, performant & industrial strength version of Holochain
Holochain is a post-blockchain framework for building agent-centric, distributed applications. Instead of using global consensus, Holochain enables each agent (user) to maintain their own local state while validating actions with a shared set of rules. This allows for scalable, secure, and resilient apps where data is owned and controlled by users. Ideal for social apps, cooperatives, and data sovereignty platforms, Holochain focuses on enabling collaboration without central servers or miners. ... -
18
WindTerm
A professional cross-platform SSH/Sftp/Shell/Telnet/Serial terminal
A Quicker and better SSH/Telnet/Serial/Shell/Sftp client for DevOps. WindTerm is a partial open source project, and the source will be gradually opened. Open source code includes, but is not limited to, the classes that can be used independently, such as functional, algorithms, GUI widgets, etc., as well as functional libraries, such as networks, protocols, etc., as well as all types that require open source according to the license. SSH v2, Telnet, Raw TCP, Serial, Shell protocols were... -
19
FlowLens MCP
Open-source MCP server that gives your coding agent
...It works together with a companion browser extension: when a user reproduces a bug or a complicated UI interaction, the extension captures a rich session log, including screen/video recording, network traffic, console logs, DOM events, storage changes, and more, and exports it. The MCP server then loads this captured “flow” and exposes it to the AI agent via the Model Context Protocol (MCP), letting the agent examine, search, filter, and reason about the session just as a human developer would, without needing the agent to re-run the flow or rely on minimal reproduction data (logs, screenshots). -
20
jvm-mon
Console-based JVM monitoring tool
Console-based JVM monitoring - when you just want to SSH into a server and see what’s going on. jvm-top lets you monitor your JVM server applications from the terminal. -
21
Telegraf
The plugin-driven server agent for collecting and reporting metrics
Telegraf is an agent for collecting, processing, aggregating, and writing metrics. Design goals are to have a minimal memory footprint with a plugin system so that developers in the community can easily add support for collecting metrics. Telegraf is plugin-driven and has the concept of 4 distinct plugin types. Input Plugins collect metrics from the system, services, or 3rd party APIs. -
22
OpenAI Codex CLI
Lightweight coding agent that runs in your terminal
OpenAI Codex CLI is a lightweight, open-source coding assistant that runs directly in your terminal, designed to bring ChatGPT-level reasoning to your code workflows. It allows developers to interactively query, edit, and generate code within their repositories, all while maintaining version control. The CLI can scaffold new files, run code in sandboxed environments, install dependencies, and commit changes automatically, streamlining chat-driven development. It supports various approval... -
23
zeroshot CLI
Your autonomous engineering team in a CLI. Point Zeroshot at an issue
zeroshot CLI is an autonomous engineering agent orchestration CLI that lets developers point it at a software task or issue and have it plan, implement, validate, and iterate on code changes without direct manual intervention. It orchestrates a multi-agent workflow where separate roles such as planner, implementer, and independent validators collaborate in isolated environments, looping until the code meets acceptance criteria or produces reproducible failures. -
24
Trellis AI
All-in-one AI framework & toolkit for Claude Code & Cursor
Trellis is an advanced workflow and agent orchestration framework designed for building, managing, and scaling intelligent applications that coordinate numerous autonomous components. At its core, Trellis lets developers define units of work — called tasks or agents — and compose them into rich workflows that can operate with concurrency, conditional logic, and dynamic branching, all without sacrificing readability or control. -
25
Motia
Multi-Language Backend Framework that unifies APIs
Motia is a large-scale, multi-language backend framework designed to unify and simplify core backend concerns — from APIs and background jobs to distributed workflows, streams, and advanced AI agent integration — through a single coherent primitive with built-in observability and state management. It provides a unified development philosophy that seamlessly bridges different backend patterns (queues, event streams, scheduled jobs) while offering integrated tools for telemetry, logging, metrics, and tracing to help teams maintain high visibility into production workloads. ...
