Search Results for "loop-aes" - Page 2
Sort By:
Showing 73 open source projects for "loop-aes"
View related business solutions-
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.
-
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.
-
1
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. It is highly configurable through a centralized configuration system, allowing experimentation with different architectural parameters such as loop depth, attention type. -
2
GPT PILOT
The first real AI developer
GPT PILOT is an open-source AI developer assistant designed to build full applications by collaborating with a human developer throughout the software lifecycle. Unlike simple autocomplete tools, it aims to function as a true AI engineer that can generate features, set up environments, debug code, and request feedback when necessary. The system works by asking clarifying questions, producing product requirements, and then implementing the application step by step while the user supervises.... -
3
AG-UI
The Agent-User Interaction Protocol
AG-UI is an open, lightweight protocol for connecting AI agents to user-facing applications through a standardized event-based interface. It is designed to make agent behavior visible, interactive, and controllable inside real-time front-end experiences. Instead of treating an AI agent as a black-box chat endpoint, AG-UI defines structured events for messages, tool calls, state changes, lifecycle updates, and user interactions. This makes it easier for developers to build agent-powered apps... -
4
VulnClaw
Based on AI Agent + MCP toolchain + penetration Skill orchestration
...The project can guide information gathering, vulnerability discovery, validation, and report generation while keeping the workflow organized through sessions and tools. Its newer architecture uses a goal-driven solving engine instead of a fixed-round loop, helping the agent stop when the goal is reached, the search space is exhausted, or a safety budget is met. It also includes evidence checks designed to reduce hallucinated conclusions by requiring real tool output before accepting key findings. VulnClaw is intended for authorized testing, CTFs, security education, and controlled red-team environments. -
$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.
-
5
AutoAgent AI
Autonomous harness engineering
...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 configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. It runs inside Docker for safe execution and reproducibility. This approach shifts agent development from manual design to automated optimization. ... -
6
Claude Agent SDK for Python
Python SDK for Claude Agent
...The SDK wraps the core functionality of Claude Code and exposes high-level asynchronous and synchronous interfaces to query prompts, manage sessions, and orchestrate tool use — so you can build agents that understand code, make edits, run bash commands, interact with files, and handle workflows without writing low-level agent loop logic yourself. It ships with a bundled Claude Code CLI for convenience, though you can also point it to a custom installation, and supports defining custom tools and hooks directly in Python, which become callable by the agent during execution. -
7
The Fable Method
How Claude Fable 5 worked, distilled into skills
The Fable Method is a structured workflow for improving how AI agents reason, act, verify, and report. It converts observed problem-solving habits into explicit steps that different language models can follow. The core process classifies the request, defines completion criteria, gathers primary evidence, chooses one recommendation, makes the smallest correct change, and verifies the result. Four included skills cover planning, execution, judging completed work, and generating domain-specific... -
8
Ditto
The simplest self-building coding agent
Ditto is a simple self-building coding agent that generates multi-file Flask applications from natural language descriptions. Users describe the app they want, and the system attempts to plan and create routes, templates, static assets, and supporting files. It uses an LLM loop with basic tools to automate part of the coding process. The project is intentionally lightweight and experimental, making it easier to understand than larger agentic coding platforms. Its modular structure separates generated Flask components into cleaner directories for routes, templates, and static files. It is best suited for prototyping, learning, and exploring how natural-language app generation can work in a small local project. -
9
autoresearch-mlx
Apple Silicon (MLX) port of Karpathy's autoresearch
autoresearch-mlx is an Apple Silicon–optimized implementation of the autoresearch framework that enables autonomous AI research loops to run natively on MLX without requiring PyTorch or CUDA dependencies. It maintains the core autoresearch structure, where an AI agent iteratively edits a training script, executes experiments under a fixed time budget, and evaluates results based on a defined metric such as validation bits per byte. The system is tailored for Apple hardware, leveraging... -
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.
-
10
Portia SDK Python
Portia Labs Python SDK for building agentic workflows
portia‑sdk‑python is an open-source Python SDK by Portia Labs for creating reliable, stateful, authenticated multi-agent AI workflows. It supports tool-backed agents capable of real-world interactions—like web browsing, API access, and human-in-the-loop clarifications—while maintaining transparency and auditability through structured plans and execution hooks. Designed for production environments, the SDK integrates with local or cloud LLMs (e.g. OpenAI, Anthropic, Mistral, Gemini) and supports extensive tool registries, session handling, and memory management. -
11
bbox-visualizer
Make drawing and labeling bounding boxes easy as cake
...There are optional functions that can draw multiple bounding boxes and/or write multiple labels on the same image, but it is advisable to use the above functions in a loop in order to have full control over your visualizations. -
12
Agentex
Open source codebase for Scale Agentex
AgentEX is an open framework from Scale for building, running, and evaluating agentic workflows, with an emphasis on reproducibility and measurable outcomes rather than ad-hoc demos. It treats an “agent” as a composition of a policy (the LLM), tools, memory, and an execution runtime so you can test the whole loop, not just prompting. The repo focuses on structured experiments: standardized tasks, canonical tool interfaces, and logs that make it possible to compare models, prompts, and tool sets fairly. It also includes evaluation harnesses that capture success criteria and partial credit, plus traces you can inspect to understand where reasoning or tool use failed. ... -
13
Google Antigravity SDK
Python library for building agents that leverages Google Antigravity
Google Antigravity SDK for Python is a Python library for building AI agents powered by Antigravity and Gemini. It provides a secure, scalable, and stateful infrastructure layer so developers can focus on agent behavior instead of manually implementing the full agent loop. The SDK includes a high-level Agent class for quick setup, as well as lower-level conversation and connection abstractions for more controlled workflows. It supports streaming responses, stateful sessions, custom Python tools, MCP server integration, hooks, policies, and event-driven triggers. The package relies on a compiled runtime binary distributed through platform-specific PyPI wheels, so installation from PyPI is required for normal use. ... -
14
Cheat on Content
Workflow that turns every post into a calibrated experiment
...Rather than generating posts for the creator, it focuses on sharpening judgment and helping users understand why certain content performs better. The project is built around the loop of score, predict, publish, retro, and improve. It is aimed at creators, marketers, and operators who want to build a repeatable system for learning from every published piece. Its value is strongest for people who already create consistently but need a better way to extract insight from their output. -
15
The AI Scientist-v2
Workshop-Level Automated Scientific Discovery via Agentic Tree Search
AI-Scientist-v2 is an advanced autonomous research system designed to perform end-to-end scientific discovery using large language models and agent-based orchestration. The platform is capable of generating original research ideas, designing and executing experiments, analyzing and visualizing results, and producing full academic papers without direct human intervention. It introduces a generalized framework that removes reliance on predefined templates, enabling broader applicability across... -
16
Pydantic Logfire
Python observability platform for tracing apps, metrics, and logs
Pydantic Logfire is an observability platform designed to help developers monitor, analyze, and understand the behavior of their applications in real time. It is built by the team behind Pydantic and follows a philosophy of combining powerful capabilities with ease of use, making it accessible to entire engineering teams. Pydantic Logfire provides deep visibility into application performance by capturing traces, metrics, and logs through an OpenTelemetry-based architecture. It is... -
17
PySpur
Visual tool for building, testing, and deploying AI agent workflows
PySpur is a visual development environment designed to help AI engineers build, test, and iterate on agent-based workflows more efficiently. It provides a structured playground where users can define test cases, construct agents either through Python code or a graphical interface, and continuously refine their behavior. It addresses common challenges in AI agent development such as prompt tuning difficulties and lack of visibility into workflow execution. By offering a visual representation... -
18
plexe
Build a machine learning model from a prompt
...The project supports both a Python library and a managed cloud option, meeting teams wherever they prefer to run workloads. The overall goal is to compress the path from idea to usable model while keeping humans in the loop for review and adjustment. -
19
Agentic RAG for Dummies
A modular Agentic RAG built with LangGraph
...The project explains the principles behind agentic retrieval pipelines where language models can dynamically decide when to retrieve information, analyze results, and plan further actions. Instead of relying on static retrieval pipelines, the system shows how agents can orchestrate retrieval, reasoning, and tool usage in a more flexible decision loop. The repository provides practical examples and tutorials that guide developers through building agentic RAG systems using modern AI frameworks. These examples illustrate how agents can access knowledge bases, retrieve documents, analyze them, and refine their queries during multi-step reasoning processes. The repository focuses on simplifying complex architectural concepts so that beginners can understand how agentic retrieval systems are constructed. -
20
MolmoWeb
Open multimodal web agent built by Ai2
MolmoWeb is an open-source multimodal web agent designed to autonomously navigate and interact with web browsers using vision-language models, representing a significant step toward fully agentic AI systems that can operate in real-world digital environments. The system takes natural language instructions and translates them into sequences of browser actions such as clicking, typing, scrolling, and navigating, effectively performing tasks on behalf of the user. Unlike traditional automation... -
21
MLE-bench
AI multi-agent framework for automating data-driven R&D workflows
RD-Agent is an open source AI framework designed to automate research and development workflows in data-driven domains. It uses large language models and multiple collaborating agents to simulate the typical cycle of research, experimentation, and improvement that human data scientists follow. It separates the process into two core phases: a research stage that proposes hypotheses and ideas, and a development stage that implements and evaluates them through code execution and experiments. By... -
22
Deep Search Agent
Implement a concise and clear Deep Search Agent from 0
Deep Search Agent is an experimental demonstration project that showcases an autonomous AI agent designed to perform multi-step research and information gathering tasks. The repository illustrates how large language models can be orchestrated with tools and planning logic to execute complex search workflows rather than single-prompt responses. It typically combines reasoning, retrieval, and iterative refinement so the agent can break down questions, gather evidence, and synthesize structured... -
23
Sandstorm
One API call, pull Claude agent, completely sandboxed
Sandstorm is an open-source project that wraps a powerful Claude-based AI agent within a completely sandboxed, ephemeral API service designed to make agentic AI workflows easy to deploy and scale without infrastructure complexity. The core idea is to provide “one API call” access to a robust Claude agent loop that runs inside a secure sandbox, so you can upload files, connect tools, and run long-running tasks — all managed behind a simple REST-style interface that disappears when the work is done. This approach lowers the friction of building autonomous agents by removing the need to provision servers, orchestrate distributed agents, or manage persistent tooling; agents can be spun up in parallel without manual setup and shut down when complete. ... -
24
Unstract
No-code LLM Platform to launch APIs and ETL Pipelines
Unstract is a powerful open-source, no-code platform built to automate the extraction and structuring of unstructured documents using large language models and flexible workflows, enabling developers and data teams to turn messy files into organized JSON content without complex coding. It integrates a visual Prompt Studio environment where users can iteratively design extraction schemas, compare outputs from different models, and monitor costs and accuracy side by side, making it easier to... -
25
Dash Data Agent
Self-learning data agent that grounds its answers in layers of content
Dash is a self-learning data agent built by the Agno AI community that generates grounded answers to English queries over structured data by synthesizing SQL and reasoning based on six layers of context, improving automatically with each run. It sidesteps common limitations of simple text-to-SQL agents by incorporating multiple context layers — including schema structure, human annotations, known query patterns, institutional knowledge from docs, machine-discovered error patterns, and live...
