What Is an Agent Harness?

kept by lunabelle sep 28

An agent harness is the execution layer around an LLM that manages loops, tools, context, and guardrails, turning model predictions into usable work.

The Making of Claude Code \ Anthropic
Anthropic shares the inside story of Claude Code's development from an internal CLI tool to a widely used coding agent, highlighting design decisions and team insights.
also on Aider, Cursor, Claude Code, #ai-agents, #ai-coding, #software-engineering, #developer-tools
hasp · model 01
Hasp is a local secret broker that injects credentials into coding agent processes without the agent ever reading the plaintext value.
also on Aider, Cursor, Claude Code, #ai-agents, #developer-tools
Give Your Coding Agents a Memory You Own
funes provides a local, searchable memory layer for coding agents like Claude Code and Codex, letting them retrieve past decisions without rebuilding context.
also on Hugging Face, Codex, Claude Code, #ai-agents, #ai-coding, #developer-tools
Over 30 new plugins join the Cursor Marketplace
Cursor adds over 30 new plugins from partners including Atlassian and Datadog to extend its AI-powered coding agent's capabilities across infrastructure and productivity tools.
also on Hugging Face, Cursor, #ai-agents, #ai-coding, #developer-tools