Projects sharing features with Vision Agent

AdalFlow is an autonomous AI agent framework and LLM application library designed for building modular workflows. It serves as a model-agnostic interface and RAG pipeline orchestrator, allowing users to develop ReAct agents that utilize iterative reasoning and external tool execution to solve complex tasks. The project distinguishes itself through a prompt optimization system that uses textual gradient descent to automatically refine prompt templates and few-shot examples. It treats model feedback as a differentiable signal, enabling a form of LLM backpropagation to iteratively improve output

LiteLLM is a unified gateway and proxy server designed to centralize access to over one hundred language model providers. It provides a standardized API interface that abstracts vendor-specific schemas, allowing developers to interact with diverse models through a single, consistent format. By acting as a central traffic management layer, it enables organizations to route, secure, and govern model interactions across multiple deployments. The platform distinguishes itself through its policy-driven architecture, which uses configuration-based routing to manage traffic distribution, load balanc

This project is a containerized development stack and application framework for building retrieval-augmented generation systems. It provides a dockerized AI sandbox that integrates local model runtimes, knowledge graphs, and vector stores to enable the creation of contextual chatbots. The stack is distinguished by its graph-based vector store, which combines structured knowledge graphs with vector indices for both semantic and structural data retrieval. It allows for local model hosting with CPU or GPU acceleration, enabling generative tasks without reliance on external cloud APIs. The frame

CodeGen is a trained large language model and program synthesis model designed to generate functional source code. It utilizes a neural network architecture to synthesize executable code from natural language descriptions or partial code snippets. The model enables automated program synthesis and AI-assisted coding by predicting and filling in missing sections of code within a program. It transforms natural language descriptions into functional programming logic to automate the creation of boilerplate and logic.

Integuru is a system of AI-driven agents and frameworks designed to document undocumented APIs and convert network traffic into automation scripts. It functions as a headless API automation framework that replaces browser-based tools with direct HTTP requests to increase throughput and reliability. The project features an LLM-based reverse engineering agent that analyzes network traffic to discover internal APIs and a natural language integration engine that transforms text descriptions of workflows into sequences of valid API calls. It includes tools for extracting request and response forma

This project is a collection of architectural templates and design patterns for building autonomous AI agents. It provides a framework for transitioning from simple prompt-response loops to goal-oriented systems that utilize structural patterns to increase autonomy and improve the reliability of complex task completion. The framework focuses on reasoning orchestration, specifically through the implementation of reflection and self-correction cycles. It enables the coordination of specialized agents via task delegation and state sharing to solve complex problems. The architectural surface cov

Code Llama is a large language model based on Llama 2 trained specifically for programming tasks and software development. It provides specialized model types optimized for general code generation, instruction following, and context-aware infilling. The project includes an instruction-tuned programming model for executing technical tasks via natural language prompts and a code infilling model that predicts missing sections based on surrounding source context. A large context code model is also provided to analyze extensive blocks of source code for improved coherence. The system covers capab

Granite Code Models is a family of transformer-based foundational models designed for software engineering and logical reasoning tasks. These models are trained on high-quality programming datasets to interpret natural language prompts and generate functional source code, explain complex logic, repair code defects, and produce technical documentation. The project distinguishes itself through specialized training methodologies that align model behavior with complex programming instructions and mathematical problem-solving. By utilizing chain-of-thought reasoning and instruction-tuned parameter

Qwen2.5-Coder is a code-centric large language model designed to generate, complete, and analyze source code. It serves as a polyglot programming model capable of producing functional code across hundreds of different programming languages. The model is optimized for reasoning over extensive software repositories, utilizing a context window that supports up to one million tokens. It also functions as an agentic coding framework, executing multi-step workflows and browser tasks through specialized function call formats. Its capabilities include large-scale codebase analysis, intelligent parti

AI-Scientist is an autonomous research pipeline and framework for scientific discovery. It employs large language model agents to manage the full lifecycle of a scientific project, from initial hypothesis generation to the production of formal academic papers. The system operates through a repeating research loop that integrates automated experimental execution, data analysis, and literature novelty verification. It queries external academic databases to validate the originality of ideas and retrieve citations, then translates experimental findings into LaTeX manuscripts. To refine these outp

DevOpsGPT is an LLM-driven DevOps automation platform and AI software development agent. It transforms natural language requirements into functional code and automated deployments by coordinating codebase analysis, code generation, and delivery pipelines. The system features an automated code generation engine and a task-based decomposition engine that analyze project structures to produce context-aware code extensions. It utilizes a pluggable model integration system to connect with private or professional language model deployments for domain-specific development tasks. The platform manage

This project is an AI software engineering tool and framework for building autonomous coding agents. It provides a system for automating program synthesis and bug fixing by integrating large language models with codebase analysis and iterative refinement loops. The framework features an agentic development server that exposes task execution interfaces to remote agents through a structured protocol. This allows for the remote execution of development tasks and the embedding of autonomous program synthesis capabilities into external software projects. The toolset covers AI-driven project scaff

Autoresearch is an autonomous machine learning research agent and architecture search framework. It employs a closed-loop system to programmatically rewrite training and architecture source code to discover optimal language model configurations. The system iteratively modifies code and evaluates performance metrics to improve model quality based on a target objective. It optimizes model performance and training efficiency by tracking validation bits per byte, which allows for a fair comparison of architectural changes independently of vocabulary size. The framework manages the full training

Conductor is an agentic coding tool that plans, generates, and manages software features through structured tracks and human-reviewed plans. It operates as a plan-driven code generator, reading structured plan files to determine the sequence of tasks and their dependencies before executing any code generation or modification. The system also functions as a feature specification manager, defining features in formal specification files that capture goals, requirements, and implementation steps as machine-readable documents. The tool distinguishes itself through a git-history-based undo system t

This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ

This project is a multi-agent development framework and orchestrator designed to coordinate autonomous AI agents for software engineering tasks. It functions as an engine that plans, implements, and reviews complex code changes across multiple files and isolated worktrees from a command line interface. The system distinguishes itself through a multi-agent coordination layer that decomposes tasks into sequential phases and applies changes across isolated worktrees to validate solutions. It maintains project-specific knowledge and constraints across sessions via context persistence using dedica

Wolverine is an AI code repair tool and self-healing Python runtime designed to monitor scripts for runtime crashes and automatically recover the source code. It functions as an automated script recovery tool that identifies failures and utilizes large language models to propose and apply corrections. The system operates through an iterative debugging cycle that captures traceback data and feeds it back into a language model to refine fixes through trial and error. To ensure safety, it includes a human-in-the-loop verification mechanism that requires manual approval before generated code chan

Evolver is a self-evolving AI agent framework that uses gene expression programming to autonomously improve agent behaviors through a continuous five-step loop of scanning, selecting, mutating, validating, and solidifying. It functions as an auditable evolution system that records every mutation and selection step, and can translate natural-language problems into executable Python code for automated grading and evaluation. The framework distinguishes itself through a distributed architecture that enables multiple agents to collaborate and share learned experiences across a network. It operate

Llamacoder is an AI-powered web application generator that transforms natural language prompts into functional application prototypes. It uses large language models to synthesize code and layouts, enabling the creation of small-scale software and interactive user interfaces from text descriptions. The project specifically leverages the Llama 3.1 405B model to produce executable React components. It provides a self-hosted environment for generating and previewing interactive code artifacts, featuring a real-time preview loop and sandboxed component rendering to safely display generated interfa

ROMA is an agentic workflow engine and recursive task orchestrator designed to coordinate autonomous agents in the execution of complex workflows. It functions as a multi-agent framework that decomposes high-level goals into atomic subtasks and manages their execution through a dependency graph. The system distinguishes itself through a hierarchical plan-execute loop that recursively decomposes objectives and synthesizes results from leaf-node tasks upward. It ensures execution purity via atomic task isolation, assigning dedicated storage directories to individual tasks to prevent data interf

AutoKeras is an automated machine learning framework and Keras AutoML library designed to discover the most effective deep learning model structures for a given dataset. It functions as a tool for deep learning architecture search, eliminating manual hyperparameter tuning by automatically searching for and optimizing neural network architectures. The framework provides capabilities for benchmarking and refining neural network designs to maximize performance. It includes a system for containerized machine learning deployment, allowing environments to be packaged into containers to ensure consi

Open Interpreter is a local language model agent framework that enables the deployment of autonomous agents capable of controlling a local operating system and its applications. It provides an execution environment where language models can run code and scripts directly on a computer to automate system tasks. The framework includes a computer control interface that allows language models to interact with web browsers and native user interfaces through programmatic commands. To ensure system stability, it utilizes a secure sandbox environment for the execution of model-generated code. The sys

Kiro is an AI-powered development tool and multi-agent workflow orchestrator. It functions as a context-aware code generator and coding assistant that transforms natural language requirements into structured implementation plans and production-grade code. The system distinguishes itself through multi-agent task decomposition, where complex requirements are broken into sequenced tasks and assigned to specialized agents. It features multi-model orchestration to select specific language models based on reasoning complexity, cost, and latency, and includes a headless command-line interface for id

Gop is a general purpose programming language and cross-language compiler designed to unify assets and libraries from multiple programming ecosystems into a single shared environment. It translates high-level source code into executable binaries using specialized backends tailored for different target environments. The project features a system for natural language programming, transforming human-readable instructions written in plain English into executable code. It also functions as a cross-language tool that imports and integrates external libraries and assets from different language ecosy

AlphaCodium is an LLM code generation framework and automated programming benchmark designed to solve programming problems through iterative generation and testing. It functions as an iterative code refinement system that improves the precision of generated code by comparing outputs against expected results and re-prompting the model. The project implements a flow engineering pipeline, using a structured sequence of prompting stages to refine code through a cycle of generation, evaluation, and correction. This approach allows the system to process programming datasets and measure the accuracy

Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk