Search Results for "protocol test harness"
Sort By:
Showing 271 open source projects for "protocol test harness"
View related business solutions-
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.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
Harness
Harness Open Source is an end-to-end developer platform
Harness is a CI/CD platform (available as SaaS/On-prem) that automates build, test, and deployment workflows. It offers pipeline-as-code YAML definitions, AI-optimized builds, policy-driven governance, multi-environment deployment templates (canary, blue/green), and integrated security scanning. -
2
Browser Harness
Self-healing browser harness that enables LLMs to complete any task
Browser Harness is a self-healing browser control system built to give language models direct and flexible access to a real Chrome browser through the Chrome DevTools Protocol. Its main philosophy is minimalism: instead of imposing a rigid framework, it exposes a very thin bridge so the agent can perform browser tasks with almost no abstraction in the way. -
3
Defending Code Reference Harness
Skills for threat modeling, scanning, triage, patching, etc.
Defending Code Reference Harness is a reference implementation for autonomous vulnerability discovery and remediation with Claude. It is designed for security teams that want a structured way to test, triage, and patch software issues with agent support. The project includes skills for threat modeling, scanning, triage, patching, and customizable autonomous analysis workflows. -
4
Universal Commerce Protocol
Specification and documentation for the Universal Commerce Protocol
...UCP also supports reference implementations and samples so teams can validate behaviors, build clients, and test interoperability in realistic scenarios. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
Reef
Continual learning infra for self-improving agents
...Reef also supports test-time learning scenarios where measurable task outcomes can drive iterative improvement. -
6
Harvey LAB
A benchmark built to evaluate and improve agent capabilities
Harvey LAB is an open-source benchmark for evaluating how effectively AI agents perform realistic legal work. It combines a dataset of legal assignments with an execution harness that runs agents against those tasks. Each benchmark task includes instructions, working documents, and rubrics that define successful completion. The environment is designed to test practical legal workflows rather than isolated question-answering ability. Evaluation tools score agent outputs and support reports and comparative experiment runs. ... -
7
Agentic Commerce Protocol (ACP)
Interaction model for connecting buyers to complete purchases
ACP is an open, draft specification for letting buyers, their AI agents, and businesses complete purchases through a standardized interaction model. It’s maintained by OpenAI and Stripe and licensed under Apache-2.0, with the goal of being easy to adopt alongside a merchant’s existing commerce stack rather than replacing it. The repository organizes the spec as human-readable RFCs plus machine-readable OpenAPI and JSON Schema definitions, along with worked examples and a changelog so... -
8
AutoAgent AI
Autonomous harness engineering
AutoAgent is an experimental AI framework focused on autonomous agent engineering, where a meta-agent iteratively improves another agent’s architecture without direct human intervention. Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s... -
9
Ante
Ghost in your shell. Ante is a self-contained agent harness
...Skills, MCP integrations, persistent memory, resumable sessions, and public benchmark evaluation extend it into a lightweight general-purpose agent harness. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
BOINC
Open-source software for volunteer computing and grid computing
BOINC (Berkeley Open Infrastructure for Network Computing) is an open-source platform that enables distributed computing using volunteered computer resources. It allows researchers to harness massive amounts of processing power from public participants for scientific projects such as climate research, disease modeling, and astrophysics. BOINC supports cross-platform deployment and is backed by a large, active community. -
11
ASSERT
Requirement-driven evaluation harness for AI agents and LLM
ASSERT is a requirement-driven evaluation harness for AI agents and LLM applications. It turns natural-language specifications, policies, product requirements, and launch criteria into structured tests that can be reviewed, executed, scored, and improved. The pipeline derives behavior categories, generates single-turn and multi-turn test cases, runs them against a target system, and uses an LLM judge to score conversations against the stated policies. -
12
Rust Latam
Learn to write Rust procedural macros
..., #[sorted], #[bitfield]. The README indicates the focus is on learning: parsing token streams, generating code, handling generics, attribute arguments, etc. It has test harness and workflow guidance. Because procedural macros are quite subtle in Rust, this workshop is a strong resource for anyone wanting to go from beginner to intermediate/advanced macro writing. -
13
Grok Build
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive
Grok Build is a terminal-based AI coding agent that operates through a full-screen text interface. It can inspect repositories, edit files, run shell commands, search the web, and coordinate longer development tasks. Users can work interactively, invoke it headlessly in scripts or CI, or connect it to editors through the Agent Client Protocol. The Rust codebase includes separate components for the interface, agent runtime, tools, workspace control, configuration, and sandboxing. It also... -
14
XcodeBuildMCP
A Model Context Protocol (MCP) server
XcodeBuildMCP is a Model Context Protocol server that exposes Xcode operations as typed tools and resources so AI assistants can build, test, and debug iOS apps programmatically. It’s organized with a modern plugin architecture and workflow-scoped tool directories, covering common developer actions across projects, schemes, targets, simulators, real devices, and Swift packages. -
15
MQTT X
Powerful cross-platform MQTT 5.0 desktop, CLI, and WebSocket client
MQTT X is a cross-platform MQTT 5.0 client tool open sourced by EMQ, which can run on macOS, Linux and Windows, and supports formatting MQTT payload. MQTT X simplifies test operation with the help of a familiar, chat-like interface. It’s easy and quick to create multiple, simultaneous online MQTT client connections, and can test the connection, publishing, and subscription functions of MQTT/TCP, MQTT/TLS, MQTT/WebSocket as well as other MQTT protocol features. MQTT stands for MQ Telemetry Transport. ... -
16
WebdriverIO
Next-gen browser and mobile automation test framework for Node.js
Adding helper functions, or more complicated sets and combinations of existing commands is simple and really useful. WebdriverIO can be run on the WebDriver Protocol for true cross-browser testing as well as Chrome DevTools Protocol for Chromium based automation using Puppeteer. The huge variety of community plugins allows you to easily integrate and extend your setup to fulfill your requirements. WebdriverIO allows you to automate any application written with modern web frameworks such as... -
17
spp
A simple and powerful proxy
Supported protocol: TCP, UDP, RUDP (Reliable UDP), RICMP (Reliable ICMP), RHTTP (Reliable HTTP), KCP, Quic. Support type: forward proxy, reverse agent, SOCKS5 forward agent, SOCKS5 reverse agent. Agreement and type can be freely combined. External agent agreement and internal forwarding protocols can freely combine. Support Shadowsocks plug-in, spp-shadowsocks-plugin, spp-shadowsocks-plugin-android. -
18
OctoMind MCP
An MCP server for octomind tools, resources and prompts
The Octomind MCP Server is designed to integrate Octomind's end-to-end testing tools and resources into local development environments. It enables AI-powered interfaces to create, execute, and manage e2e tests, enhancing the testing workflow. -
19
InterceptSuite
A TLS MITM proxy for Non-HTTP traffic, with support for TLS upgrades
...It goes beyond HTTP‑focused tools like Burp Suite and ZAP by providing universal TLS interception—including STARTTLS and non‑HTTP protocols—offering deep visibility and control for security testing and debugging. InterceptSuite bridges this gap by providing a universal TLS interception engine that works with any protocol, giving security researchers the tools they need to analyze, understand, and test encrypted communications effectively. With Python extension support, users can add custom protocol dissection capabilities tailored to their specific needs. -
20
tapjs
Test Anything Protocol tools for node
Workspace for node-tap development. The API is simple but powerful. t.test() and a few assertions are all you really need. Everything is statically typed, so your editor can tell you what's available. Remember less, just write some tests. An easily extensible TAP test framework, with outstanding TypeScript support, a CLI, plenty of assertion methods, snapshots, object/method spies, module mocking, file system fixtures, lifecycle hooks, test filtering, comprehensive code coverage analysis,... -
21
Sippts
Set of tools to audit SIP based VoIP Systems
Sippts is a set of tools to audit VoIP servers and devices using SIP protocol. Sippts is programmed in Python and it allows us to check the security of a VoIP server using SIP protocol. You can freely use, modify and distribute. If modified, please put a reference to this site. Most security tools can be used for illegal purposes, but the purpose of this tool is to check the security of your own servers and not to use to do bad things. I am not responsible for the misuse of this tool. Sippts... -
22
iperf3
iperf3: A TCP, UDP, and SCTP network bandwidth measurement tool
...It supports TCP, UDP, and SCTP testing, making it useful for a wide range of network troubleshooting and benchmarking scenarios. The tool reports throughput, bitrate, packet loss, and other measurement details for each test. iperf3 was redesigned from the original iperf with a smaller codebase, a cleaner architecture, and library functionality that can be used by other programs. It includes features such as zero-copy mode, optional JSON output, protocol tuning, buffer tuning, and timing controls. Overall, it is a trusted utility for network engineers, research networks, developers, and administrators who need reliable active bandwidth testing. -
23
Etaoin
Pure Clojure Webdriver protocol implementation
A pure Clojure implementation of the Webdriver protocol, named after Etaoin Shrdlu, a typing machine that came to life after a mysterious note was produced on it. Use the Etaoin library to automate a browser, test your frontend behavior, simulate human actions or whatever you want. Currently supports Chrome, Firefox, Safari, and Edge. Can either connect to a remote WebDriver process or have Etaoin launch one for you. -
24
Testinfra
Testinfra test your infrastructures
With Testinfra you can write unit tests in Python to test the actual state of your servers configured by management tools like Salt, Ansible, Puppet, Chef and so on. Testinfra aims to be a Serverspec equivalent in python and is written as a plugin to the powerful Pytest test engine. By default Testinfra launches tests on the local machines, but you can also test remotes systems using paramiko. -
25
WalletConnect v2.x.x
WalletConnect Monorepo
Open protocol for connecting Wallets to Dapps. The communications protocol for web3, WalletConnect brings the ecosystem together by enabling wallets and apps to securely connect and interact. With WalletConnect, you can connect your wallet with hundreds of apps, opening the doors to a new world of web3 experiences. Uniswap. Swap, earn, and build on the leading decentralized crypto trading protocol. Foundation. Create, collect and sell NFTs.Install nodejs and npm. Install python3 and ensure...
