Sahaj.blogs

Day page

30 Sept 2026

Paper summary

Paper summary: Raven: The Harness of Harnesses for Composable Agentic Intelligence

Raven is an open-source multi-agent ecosystem that automatically builds and evolves specialised model–harness pairs and orchestrates them across domains through a Host Agent, with stored experience turned into reusable skills.

  • Each model plus harness is treated as a composable unit of intelligence.
  • A Host Agent decomposes goals, matches subtasks to specialised agents and integrates results.

Read the post →

Study

Agentic AI · Model Context Protocol (MCP)

MCP standardises how applications expose tools, resources and prompts to LLM clients; an MCP server built with the official Python SDK and queried from an in-process client.

  • MCP is a protocol, not a framework: any MCP client can use any MCP server's tools and resources.
  • Tools are actions the model can call; resources are data the client can read.

Read the post →