heurist-network/heurist-agent-framework

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

What it solves

Heurist Agent Framework provides a modular system for building AI agents that can operate across multiple platforms (Telegram, Discord, Twitter, Farcaster, and REST APIs) with consistent behavior. It specifically addresses the gap in specialized Web3 intelligence by integrating with Heurist Mesh, a marketplace of over 30 specialized AI agents focused on crypto analytics, blockchain data, and wallet analysis.

How it works

The framework uses a component-based architecture where a CoreAgent orchestrates various plug-and-play components. These components handle specific tasks such as personality management, knowledge retrieval from vector databases (Postgres/SQLite), and media processing (voice and images).

To handle complex tasks, the framework implements higher-level reasoning patterns called Workflows, including RAG (AugmentedLLMCall), Chain of Thought reasoning, and deep research workflows. It also supports the Model Context Protocol (MCP) to integrate external tools and specialized agents from the Heurist Mesh ecosystem.

Who it’s for

Developers building AI agents or agentic applications that need to be deployed across various social media platforms or require deep, specialized knowledge of the Web3 and cryptocurrency space.

Highlights

  • Multi-platform Support: Native integration for Telegram, Discord, Twitter, and Farcaster.
  • Web3 Specialization: Access to 30+ curated crypto-expert agents via Heurist Mesh.
  • Modular Architecture: Plug-and-play components for personality, knowledge, and conversation management.
  • Advanced Reasoning: Built-in workflows for Chain of Thought and hierarchical research.
  • MCP Integration: Full support for the Model Context Protocol for extensible tool execution.

Related

  • Project
    Shy2593666979/AgentChat

    A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.

  • Project
    wanikua/danghuangshang

    A multi-agent collaboration system based on the OpenClaw framework that organizes AI agents into a hierarchical government or corporate structure for efficient task delegation and execution.

  • Project
    KroMiose/nekro-agent

    A highly extensible AI bot framework that enables LLMs to execute code in secure sandboxes and interact across multiple chat platforms via a unified adapter architecture.

  • Project
    get-convex/agent

    A framework for building AI agents on Convex with persistent chat threads, tool calling, and real-time streaming updates.

  • Project
    evalstate/fast-agent

    A flexible framework for building multimodal AI agents and workflows with deep Model Context Protocol (MCP) integration and advanced orchestration patterns.