Search Results for "loop"
Sort By:
Showing 41 open source projects for "loop"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
1
ralph-loop-agent
Continuous Autonomy for the AI SDK
ralph-loop-agent is an experimental autonomous agent framework from Vercel Labs that brings continuous autonomy to the AI SDK, enabling AI solutions to perform long-running, iterative tasks without manual stop/start intervention. Rather than simply answering a single request and stopping, Ralph Loop implements a loop control architecture that allows an agent to repeatedly evaluate its progress, adjust its approach, and continue working toward a defined completion criteria until tasks are fully resolved. ... -
2
Ralph
Autonomous AI agent loop that runs until all PRD items are complete
Ralph is an autonomous AI coding loop that repeatedly runs agentic development tools until every item in a product requirements document is complete. It is designed to work with Amp or Claude Code, launching a fresh AI instance on each iteration to avoid context overload. Instead of relying on one long conversation, Ralph keeps progress through git history, a structured prd.json file, and an append-only progress.txt memory file. -
3
pi-autoresearch
Autonomous experiment loop extension for pi
pi-autoresearch is an automation-oriented research assistant project that focuses on orchestrating iterative information gathering, analysis, and synthesis workflows with minimal human intervention. It is designed to simulate a continuous research loop where queries are generated, refined, and expanded based on previous outputs, enabling deeper exploration of complex topics. The system likely integrates with external data sources or APIs to retrieve information and process it into structured insights. Its architecture suggests a focus on autonomy, allowing it to run multi-step research pipelines that mimic human investigative processes. ... -
4
eve
The Framework for Building Agents
...The framework is designed to include production concerns from the start instead of leaving developers to assemble durability, sandboxing, approvals, and deployment separately. Eve supports durable execution, sandboxed compute, human-in-the-loop approvals, subagents, long-running work, and Vercel-native deployment. It also fits into agent templates and app workflows, such as Slack agents or persisted chat experiences. It is useful for developers who want to move from prototype agents to production-ready agents with clearer structure, safer execution, and cloud deployment built into the framework. -
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.
-
5
Codex Autoresearch
A codex plugin for running optimization loops inside a codebase
Codex Autoresearch is an autonomous software improvement framework that enables AI coding agents to iteratively enhance codebases without continuous human input. The system operates in a loop where the agent modifies code, evaluates results against measurable metrics, and either keeps or discards changes based on performance. It generalizes the concept of autoresearch beyond machine learning, allowing optimization of test coverage, latency, lint errors, and overall code quality. Developers define a goal and verification command, and the agent continuously runs experiments to reach the desired outcome. ... -
6
Ralph TUI
A terminal UI for orchestrating AI coding agents
ralph-tui is a terminal-first task runner that orchestrates AI agent work as a structured queue of tasks, making “agentic execution” feel more like operating a build tool than chatting in a textbox. It prioritizes a disciplined loop: select the next task, construct the right prompt and context, execute the agent, detect completion, and move forward until the workload is done. By centering everything in a TUI, it encourages repeatable workflows where you can watch progress, adjust priorities, and keep your attention on the execution pipeline rather than juggling windows and tabs. ... -
7
Museeks
A simple, clean and cross-platform music player
A simple, clean and cross-platform music player. Museeks is on its way to a big rewrite with some major UI changes, please help shape the future of the music player in the discussions section! You will not find tons of features, as its goals is not to compete with more complete and more famous music players. Museeks is currently in development. This implies some things can break after an update (database schemes changes, config...). -
8
TestSprite
AI-powered automated testing from your terminal
...It supports scripting, deterministic output, JSON results, predictable exit codes, and dry-run behavior for automation. Overall, it helps teams turn AI-generated code into a more testable, repeatable, and evidence-backed development loop. -
9
Eigent
The Open Source Cowork Desktop to Unlock Your Exceptional Productivity
...You can run Eigent fully locally for maximum privacy and data control, or choose a cloud-connected experience for quick access. The platform supports a wide range of AI models and integrates powerful tools through the Model Context Protocol (MCP). With human-in-the-loop controls and enterprise-ready features, Eigent balances automation with oversight and security. -
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.
-
10
Zypher Agent
A minimal yet powerful framework for creating AI agents
Zypher Agent is an open-source framework for building full-featured AI agents that can be embedded directly into applications, enabling reactive decision loops where the agent dynamically chooses its next actions. Unlike workflow-style orchestrators, it uses a reactive agent loop that interprets the task, reasons about next steps via LLMs, and integrates directly with extensible tools and external services. Zypher prioritizes native support for multiple model providers such as OpenAI and Anthropic Claude, while also offering a rich set of tools for file system operations, search, and terminal execution. It includes mechanisms like checkpointing to version agent decision states, concurrency protections, error handling, and operational interceptors to customize behavior after each reasoning step. ... -
11
InkOS
Autonomous novel writing CLI AI Agent
InkOS is a multi-agent creative writing system designed to automate the production of long-form narrative content such as novels through coordinated AI workflows. The system organizes multiple specialized agents that collaborate in stages, including drafting, reviewing, editing, and refining text, with optional human checkpoints to ensure quality and coherence. Its architecture reflects a pipeline approach where each agent contributes a specific function, allowing iterative improvement... -
12
AgentScript
Build AI agents that think in code
AgentScript is a TypeScript SDK for building reliable AI agents that express their plans as code, enabling stop/start workflows, tool-level state management, and enhanced observability. -
13
OpenScience
The open-source AI workbench for scientific research
OpenScience is an open-source AI workbench for scientific research. It lets users give an agent a research goal, then have it read literature, form hypotheses, write and run code, run experiments, analyze results, and write up findings. The workspace runs in the browser and includes a file tree, editor, terminal, session history, and scientific rendering for molecules, structures, genomes, and plots. It supports frontier, open-weight, and local models through bring-your-own-key provider... -
14
Gajae-Code
Gajae Code MVP
...Gajae-Code is useful for developers who want coding agents to behave less like single-prompt assistants and more like disciplined project collaborators. Its main value is giving AI coding work a clearer loop for interviews, plans, goals, execution checks, and evidence. -
15
Tone.js
A Web Audio framework for making interactive music in the browser
Tone.js is an open source Web Audio framework for creating interactive music in the browser. It has advanced scheduling capabilities, synths, effects and more. Tone.js is built to be useful and familiar to both musicians and audio programmers. It has common DAW (digital audio workstation) features for those looking to schedule events and tinker with pre-built synths and effects. There’s also a great selection of high-performance building blocks for signal-processing programmers familiar... -
16
DeepSeek-Reasonix
DeepSeek-native AI coding agent for your terminal
...The project is especially useful for developers who want an open, terminal-first coding agent optimized for DeepSeek’s cache mechanics. It also includes a prerelease desktop client for users who prefer a GUI over the same agent loop. -
17
agent-browser
Browser automation CLI for AI agents
...The project emphasizes standards and safety, defining interfaces that let agents access DOM data, interpret events, and generate actionable insights without exposing sensitive credential-level access or violating policy boundaries. Users benefit from a tighter feedback loop: agents can observe user tasks in-situ and respond with contextually relevant actions or suggested steps, like form completion, navigation shortcuts, or detailed explanations of UI elements. -
18
Radon IDE
VSCode/Cursor extension that turns your editor into an IDE
...It is designed to help developers build, run, inspect, and debug mobile applications without constantly switching between disconnected tools. The project focuses on improving the React Native development loop by bringing app controls and feedback closer to the code editor. It is especially useful for teams using Expo or React Native who want faster iteration and a more integrated workflow. The repository is mainly used for issue tracking and discussion around the Radon IDE product. Its main value is making React Native development feel more like a dedicated IDE experience inside editors developers already use. -
19
React Three Fiber
A React renderer for Three.js
...It merely expresses three.js in JSX, <mesh /> becomes new THREE.Mesh(), and that happens dynamically. There is no additional overhead. Components participate in a unified render loop outside of React. It outperforms three.js at scale due to React's scheduling abilities.Y ou need to be versed in both React and three.js before rushing into this. If you are unsure about React consult the official React docs, especially the section about hooks. -
20
AI Job Search
AI-powered job application framework built on Claude Code
AI Job Search is a Claude Code-based framework for managing job applications from profile setup to interview preparation. It helps users turn their CV, documents, and career background into a structured application profile. The workflow can search job portals, score roles by fit, rank openings, and generate tailored application materials. It also creates LaTeX-based CVs and cover letters, then runs a reviewer-style pass before presenting final outputs. Extra commands support interview prep,... -
21
Agentspan
Durable, Distributed runtime for ALL of your agents
Agentspan is a distributed runtime designed to run AI agents reliably across machines while maintaining long-lived execution states. It enables agents to persist beyond process crashes, allowing workflows to continue even after interruptions or restarts. The system is built for durability, meaning tasks can pause for extended periods, including waiting for human approval, and then resume seamlessly. It supports scaling across multiple environments, making it suitable for production-grade... -
22
TraceRoot
Find the Root Cause in Your Code's Trace
...Lightweight SDKs for Python and TypeScript enable seamless instrumentation using OpenTelemetry, with support for both self-hosted and cloud deployment. Human-in-the-loop interaction is central: developers can guide reasoning by selecting relevant spans or logs, then verify agent reasoning through traceable context. -
23
Mastra
The TypeScript AI agent framework
Mastra is a TypeScript-first framework for building AI-powered applications and agents, designed to take projects from prototype to production on a modern JavaScript/TypeScript stack. It integrates cleanly with React, Next.js, and Node-based backends, but can also run as a standalone server, giving teams flexibility in how they deploy their AI logic. At its core, Mastra provides abstractions for agents, workflows, tools, memory, retrieval, and model routing, so developers can focus on... -
24
OSMO
The developer-first platform for scaling complex Physical AI workloads
OSMO is a developer-first orchestration platform designed to scale complex physical AI workflows across heterogeneous computing environments, including cloud GPUs, simulation clusters, and edge devices. It was originally built internally at NVIDIA to support robotics and embodied AI systems, where workflows span multiple stages such as data generation, training, simulation, and hardware testing. The platform addresses what NVIDIA refers to as the “three computer problem” by unifying these... -
25
CallMe
Minimal plugin that lets Claude Code call you on the phone
...The plugin uses a local MCP server alongside a webhook tunnel (typically via ngrok) to connect with voice providers like Telnyx or Twilio for outbound calls, with prompts and responses flowing between Claude Code and the user’s voice device. Multi-turn conversations are supported, so users can respond in real time to questions the agent asks during execution, giving it a practical human-in-the-loop capability for complex workflows.