Search Results for "agent"

Claude How-To is a visual, example-driven guide for learning Claude Code. It covers basic concepts, memory, slash commands, hooks, skills, subagents, MCP configuration, plugins, and advanced agent workflows. The project is designed as a practical learning path rather than a simple list of notes. It includes copy-paste templates that users can apply directly to their own projects. The guide also uses diagrams and structured examples to explain not only how features work, but why they matter in a real development workflow. Its main value is helping developers move from casual Claude Code usage to more organized, automated, and agent-driven software development.

...The agent runs on LangGraph and can be explored locally through LangGraph Studio, an API, and generated API documentation. Environment settings control model choices, search services, MCP servers, and other research behavior. The repository also includes evaluation scripts for Deep Research Bench, enabling reproducible comparisons across difficult multilingual tasks.

...It orchestrates agents that can generate research questions, perform literature reviews, execute experiments, analyze results, and synthesize findings into structured outputs like reports or code. Each agent operates with clear roles — such as researcher, analyst, and summarizer — and they communicate through a task-management interface that ensures progress tracking and iterative refinement. The system emphasizes modularity, so teams can swap in new reasoning modules, data retrieval strategies, or domain knowledge bases depending on the research topic. ...

...It can automatically generate code for experiments, run them in a sandbox environment, and analyze the results with statistical methods. The platform also uses multi-agent debate and automated peer review processes to refine research findings and improve paper quality. By combining literature discovery, experimentation, and writing automation, AutoResearchClaw aims to turn research ideas into conference-ready papers with minimal human intervention.

PocketFlow Tutorial Codebase Knowledge is a project that demonstrates how to build an AI agent capable of analyzing arbitrary codebases and generating beginner-friendly tutorials that explain how they work, turning complex source code into clear educational content. The repository builds on a lightweight 100-line LLM framework and uses natural language models to inspect repository structures, identify core abstractions, map dependencies, and articulate the reasoning behind code design and interactions. ...

...Agents learn behaviors in a shared ecosystem that supports long-term training and emergent dynamics across large populations. The project is built to test scalability in multi-agent reinforcement learning, with features such as procedurally generated terrain and configurable game mechanics. While the original release has since been succeeded by newer versions maintained outside OpenAI, it remains a landmark framework for studying large-scale agent interactions in complex environments.

java-based complete Agent (Artificial Intelligence) Framework with all the features you might expect in an Agent Framework: Mobility, Autonomy, Distributed communication, Agents can be written in Java, Jython, or Beanshell.

Gikot is a desktop agent framework for 2channelers!

An AI educational effort to make realtime multi agent environments. started from scratch with python.