Search Results for "agents"
Sort By:
Showing 254 open source projects for "agents"
View related business solutions-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Gas Town
Gas Town - multi-agent workspace manager
Gas Town is a sophisticated multi-agent workspace manager designed to orchestrate and coordinate numerous Claude Code agents working on diverse tasks within a shared development environment. It tackles the common challenge where individual AI agents lose context on restart by persisting work state using git-backed hooks, enabling reliable and resumable multi-agent workflows that scale comfortably beyond just a handful of concurrent agents. The system introduces concepts like The Mayor (the primary coordinator agent), Rigs (project containers), Crew Members (developer workspaces), and Polecats (ephemeral worker agents), organizing work into structured convoys and beads that can be tracked through command-line interfaces. ... -
2
OpenFang
Open-source Agent Operating System
OpenFang is an open-source agent operating system designed to orchestrate autonomous AI agents and workflows in a structured, production-oriented environment. Written primarily in Rust, the project focuses on building a high-performance runtime where multiple specialized agents can collaborate to complete complex computational or development tasks. It aims to move beyond simple chat-based agents by providing infrastructure for persistent agent memory, task coordination, and scalable execution. ... -
3
AnySearch Skill
Unified real-time search engine skill for AI agents
AnySearch Skill is a real-time search engine skill for AI agents. It gives agents a structured way to search the web, run vertical searches, perform parallel batch searches, and extract full-page content. The project is packaged as a skill rather than a standalone search application, so it is meant to be installed into compatible AI-agent environments. It supports multiple domain-specific search categories, making it useful when general web search is too broad. -
4
CodexMonitor
An app to monitor the (Codex) situation
CodexMonitor is a desktop application built with Tauri that provides a robust orchestration and management interface for Codex agents on macOS (and optionally Linux/Windows). It offers developers a unified workspace dashboard with features like project workspaces, thread management, and agent orchestration, letting users spawn and track multiple Codex agent sessions across local repositories. The interface complements direct interactions with the agents by integrating things like file trees, prompt libraries, reasoning logs, and CLI session panels, making it easier to manage long-running dialogues and context switches without leaving the app. ... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
AgentGuard
AgentGuard is a firewall for AI agents
...This makes it particularly valuable in environments where agents operate autonomously and may enter unintended loops or inefficient workflows. The tool integrates directly into existing applications with minimal changes, often requiring only a few lines of code to activate protection. It also supports advanced configurations such as distributed tracking through Redis and webhook notifications for real-time monitoring. -
6
Agent Auth Protocol
Standard and implementation for AI agent authentication
Agent Auth Protocol is a specification-oriented project within the Better Auth ecosystem that defines a structured protocol for authentication between applications and autonomous agents. It is designed to standardize how AI agents and services securely authenticate, communicate, and manage identity within modern software systems. Built alongside the broader Better Auth framework, it integrates with a comprehensive authentication system that supports features like OAuth, multi-factor authentication, and session management. ... -
7
OpenClaw Opik Observability Plugin
Official plugin for OpenClaw that exports agent traces to Opik
OpenClaw Opik Observability Plugin is an open-source plugin designed to add observability and monitoring capabilities to OpenClaw autonomous AI agents by exporting operational traces to the Opik observability platform. The project integrates directly with OpenClaw’s plugin architecture so that developers can capture detailed runtime information about how their agents behave while executing tasks. Each time an AI agent performs an action—such as calling a large language model, invoking a tool, accessing memory, or delegating to a sub-agent—the plugin records the full interaction and sends it to Opik for analysis and visualization. ... -
8
Pearcleaner
A free, source-available and fair-code licensed mac app cleaner
Pearcleaner is a small, native macOS utility that helps you fully remove applications by finding and deleting the leftover files they scatter across your system. After you drag an app into Pearcleaner (or select it from a list), it scans common Library locations for related caches, logs, preferences, containers, launch agents, and support files. Results are presented with clear paths and sizes so you can deselect anything you want to keep before sending items to the Trash. The tool favors safety: it avoids critical system areas, uses a conservative matching strategy, and relies on the Trash so you can restore items if you change your mind. Power users appreciate the transparency—no opaque “cleanup magic,” just an auditable list of what will be removed. ... -
9
NetBird
Connect your devices into a secure WireGuard-based overlay network
...Every machine in the network runs NetBird Agent (or Client) that manages WireGuard. Every agent connects to Management Service that holds network state, manages peer IPs, and distributes network updates to agents (peers). NetBird agent uses WebRTC ICE implemented in pion/ice library to discover connection candidates when establishing a peer-to-peer connection between machines. -
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.
-
10
Mobile Next
Model Context Protocol Server for Mobile Automation and Scraping
...It is built to integrate seamlessly with modern AI agents, enabling multi-step workflows such as automated testing, form filling, and user journey simulation. -
11
PatchMon
Linux Patch Monitoring Automation Platform
...It centralizes patch status information from many hosts into a single dashboard where users can view inventories of outdated packages, track repositories per host, and organize machines into logical groups for easier oversight. Agents installed on each server make outbound-only connections to the PatchMon server, improving security by avoiding open inbound ports, while the server side provides role-based access control, user management, and a REST API for integrations. PatchMon also supports a customizable dashboard, detailed per-host metrics, and one-line installers for quick self-hosted deployment, making it suitable for both small clusters and larger fleets. -
12
parseable
Parseable is a log analytics system written in Rust
Parseable is a log analytics platform, built for the modern, cloud native era. Parseable uses a index-free mechanism to organize and query data allowing low latency, and high throughput ingestion and query. -
13
Mole
🐹 Deep clean and optimize your Mac.
...From the command line, you can scan and remove large caches, logs, temporary files, browser remnants, and other junk that quietly accumulates over time. Mole’s smart uninstall mode walks the filesystem to remove not just an application bundle, but also associated caches, preferences, launch agents, logs, and other leftovers in more than twenty locations. It also includes optimization routines that rebuild caches, reset network services, trim swap files, and refresh indexes to keep the system feeling responsive. An interactive disk analyzer view helps you navigate directories with the keyboard to find space hogs, while status commands surface live CPU, memory, disk, and network metrics. -
14
Grafana Pyroscope
Continuous Profiling Platform. Debug performance issues
Find and debug your most painful performance issues across code, infrastructure and CI/CD pipelines. Let you tag your data on the dimensions important for your organization. Allows you to store large volumes of high cardinality profiling data cheaply and efficiently. FlameQL enables custom queries to select and aggregate profiles quickly and efficiently for easy analysis. Analyze application performance profiles using our suite of profiling tools. Understand usage of CPU and memory resources... -
15
APM Server
APM Server
...Errors are grouped based primarily on the stack trace, so you can identify new errors as they appear and keep an eye on how many times specific errors happen. Metrics are another vital source of information when debugging production systems. Elastic APM agents automatically pick up basic host-level metrics and agent-specific metrics, like JVM metrics in the Java Agent, and Go runtime metrics in the Go Agent. -
16
Netmaker
Netmaker makes networks with WireGuard
Unify your devices with an ultra-powerful overlay network. Netmaker is better, faster, and more secure. Netmaker automates a secure superhighway between devices, clouds, virtual machines, and servers using WireGuard. It blows past any NAT’s, firewalls, or subnets that stand between them. Devices are scattered across data centers, offices, clouds, clusters, and more. Distinct networks separate them, each with different management rules. Connecting machines across environments means setting up... -
17
gdown
Google Drive public file downloader when curl/wget fails
...Google Docs, Sheets, and Slides can be exported to formats such as DOCX, XLSX, PPTX, PDF, and CSV. Interrupted transfers can resume, while optional controls limit speed, route traffic through a proxy, adjust certificates, or change cookies and user agents. The tool also downloads regular HTTP and HTTPS URLs and can stream data to standard output. It is available as both a command-line program and a Python package. -
18
Helicone
Open source LLM-Observability Platform for Developers
Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. -
19
C# SNMP Library
C# SNMP Library (#SNMP) - Open source SNMP implementation for C#
...It helps developers add Simple Network Management Protocol functionality without building the protocol layer from scratch. The project supports SNMP v1, v2c, and v3, making it useful for a wide range of network management scenarios. It can be used to build both SNMP managers and agents. Its asynchronous operations help applications stay responsive while handling network communication. The library is also designed to be extensible, so teams can adapt it to specialized monitoring, discovery, and device management needs. -
20
Performance Co-Pilot (PCP)
Performance Co-Pilot
Performance Co-Pilot (PCP) provides a framework and services to support system-level performance monitoring and management. It presents a unifying abstraction for all of the performance data in a system, and many tools for interrogating, retrieving and processing that data. PCP is a feature-rich, mature, extensible, cross-platform toolkit supporting both live and retrospective analysis. The distributed PCP architecture makes it especially useful for those seeking centralized monitoring of... -
21
LAMDA
Android reverse engineering & automation framework
...It replaces a large number of manual operations with a programmed interface. It is not a single-function framework. To give you a general idea of its usefulness: Do you install various agents, plug-ins, or point-and-click settings on your phone to complete your work? Do you want to operate a mobile phone thousands of miles away in a different place? Do you have the need to programmatically control your phone? Are you still paying for expensive IP switching , remote ADB debugging , RPA automation and even logcat logs from some cloud mobile phone manufacturers? ... -
22
OPAL
Policy and data administration, distribution, and real-time updates
...It works with policy engines such as OPA and Cedar so applications can make decisions using current policy and data without constantly rebuilding custom sync logic. The project aggregates policy and data from external sources, watches for changes, and distributes updates to connected policy agents. It is built for cloud-native and microservice environments where authorization rules change frequently and need to propagate quickly. OPAL separates policy decision-making from policy distribution, which helps teams build more maintainable and consistent permission systems. It is especially useful for engineering teams implementing fine-grained authorization, relationship-based access control, feature access rules, and multi-service policy governance. -
23
Apache SkyWalking Java Agent
The Java agent for Apache SkyWalking
SkyWalking-Java: The Java Agent for Apache SkyWalking, which provides native tracing/metrics/logging abilities for Java projects. SkyWalking: an APM(application performance monitor) system, specially designed for microservices, cloud-native and container-based (Docker and Kubernetes) architectures. -
24
apm-agent-java
Elastic APM Java Agent
Elastic APM Java Agent. Using the -javaagent option is the most common way to set up Java agents on a JVM. -
25
ThreatMapper
Open source cloud native security observability platform
Thousands of companies trust Deepfence to secure their most critical cloud workloads and applications with a unified platform. Experience rapid threat detection and remediation, while significantly reducing non-critical security alerts by 90%. Deepfence ThreatMapper hunts for threats in your production platforms, and ranks these threats based on their risk of exploit. It uncovers vulnerable software components, exposed secrets, and deviations from good security practices. ThreatMapper uses a...
