Coding agents are closely associated with their model labs: developers use Claude Code with Claude and Codex with OpenAI’s models. The harness shapes the experience through its instructions, tools, context […]
Category: Agent Memory
Run Codex Your Way: Native Codex in SuperQode
Coding agents now run real commands against real repositories, and the teams adopting them have learned that the model is only one part of the system. The harness around the […]
Agent Engineering HQ Launched AgentEng: CLI, MCP, A2A and ACP Support for Agentic AI Events
We launched the Agent Engineering Conference to bring together the people building the systems around AI agents. Its Founders Edition takes place at Everyman, Canary Wharf, London, on 16 October […]
Introducing SuperQode v2: The Harness Interoperability Layer for Coding Agents over ACP, A2A and UHP
Today we are announcing SuperQode v2, the harness interoperability layer for coding agents. It is Apache-2.0, installs in one line, and leads with full Agent2Agent support, a hosted A2A agent […]
Headlong microharness in SuperQode Ecosystem Watch
Laude Institute recently released Headlong: Apache-2.0, under 10K lines of Bash, with shellm as a recursive language model core. A Headlong agent keeps thinking between messages. A Slack or Telegram […]
SuperQode on the Unified Harness Protocol and HarnessRouter
Coding harnesses have been arriving at a steady pace. Muse Code from Meta, fx from Vercel Labs, and Prime Agent from Prime Intellect all landed in recent months, each with its own loop, its own tools, […]
A2A Joins AAIF: What We’re Building Next
A2A, the agent-to-agent protocol Google launched in 2025, is now a formally hosted project at the Agentic AI Foundation. The announcement puts it alongside MCP, AGENTS.md, and Agentgateway under one governance roof. AAIF’s CTO, Manik […]
Introducing Coding Agent Harness Hub: Discover, Build and Optimize Harnesses
The coding-harness market has accelerated in the last month. Muse Code shipped as a terminal agent co-trained with Muse Spark 1.2. Prime Agent arrived as an open MIT Recursive Language Model (RLM) harness. Z.ai […]
SuperQode Supports DeepSeek Harness
DeepSeek released DeepSeek Harness on 13 August 2026, at the same time as the DeepSeek-V4-Pro model. The harness, invoked as dsh, is a TypeScript agent runtime published under the MIT license and described […]
Prime Agent Python Host Client: A Native RPC Host
In the latest post, Prime Agent in SuperQode, we described the first integration over Agent Client Protocol (ACP), compared Prime Agent with RLM Code, and documented the part that Python […]