AmeNetwork/aser

Aser is a lightweight, self-assembling AI Agent frame.

What it solves

Aser provides a minimalist and modular framework for building AI agents, allowing developers to assemble complex agentic behaviors with very little code.

How it works

It uses a modular architecture where an Agent object can be configured with various components including specific LLM models, tools, memory storage, knowledge bases for RAG, and tracing. It supports a wide range of interaction patterns, from simple chat interfaces to complex multi-agent orchestrations (sequential, parallel, reactive, and hierarchical).

Who it’s for

Developers who want a versatile, low-boilerplate framework to quickly prototype and deploy AI agents across different platforms like Discord, Telegram, and Farcaster.

Highlights

  • Multi-Agent Orchestration: Supports router, sequential, parallel, reactive, and hierarchical agent patterns.
  • Extensive Integration: Built-in support for Model Context Protocol (MCP), Model Smart Contract Protocol (MSCP), and Google's Agent2Agent (A2A) protocol.
  • Flexible Deployment: Includes examples for CLI, API servers, and various social media clients.
  • Advanced Capabilities: Features support for Chain of Thought (CoT), Text2SQL, and a self-coding tool that allows agents to create their own tools.

Related

  • Project
    rollingSirius/equity-research-skill

    An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.

  • Project
    himself65/trade-skills

    A plugin for AI coding agents that provides an options trading knowledge base, featuring 38 historical case studies and pitfalls structured in the Open Knowledge Format.

  • Project
    hashgraph-online/registry-broker-skills

    A set of skill definitions and tools for the Universal Agentic Registry, allowing AI assistants to discover, chat with, and register AI agents across multiple protocols.

  • Project
    lzwme/finance-quant-skills

    A collection of specialized AI agent skills for quantitative finance, enabling LLMs to handle financial data APIs, backtesting frameworks, and trading strategy development.