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 […]
Author: Shashikant Jagtap
Londoner, Agentic AI, Agent Experience, Agentic Co-Intelligence, Agent Frameworks
SuperQode Themes, Vim Mode and an Enhanced Developer Experience for Everyday Coding
Recently, there is a lot of talk around harnesses and self-improving software. SuperQode was not designed initially for developer experience, and every coding task it was harness layer that can be used […]
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 […]
RLM + A2A in SuperQode: Building a More Durable Recursive Coding Harness
We recently released SuperQode with a native Recursive Language Model harness. Getting that harness working was an important step. Making it useful for longer coding tasks required more work: reliable […]
SuperQode: A Jev Engineering–Aligned Coding Agent
Since we published SuperQode 2.5, the work on the terminal has been about making the harness usable as a daily coding surface: connect a provider or an agent, stay in […]
SuperQode 2.5: Polished TUI, WorkOrders and Herdr
When we launched SuperQode, we built it as a harness layer for coding agents. The first optimisation was agent experience: CLI surfaces, A2A, ACP, UHP, MCP, and the other protocol […]
Jev Tool Routing Across Open Coding Harnesses with SuperQode
When TypeSafe introduced Jev, it added a different intelligence primitive to the agent stack. Large language models generate open-ended text, code, commands, and plans. Jev receives state plus typed questions, […]
Introducing the SystemOne Harness in SuperQode
Introducing the SystemOne harness in SuperQode: a dedicated decision layer for the native coding loop, with Jev from TypeSafe AI as the supported live model. Your coding model writes code […]
Jev in SuperQode: a harness for your code and workflows with Jev agent
Coding agents are getting better at writing code. The expensive part is the swarm of small judgments around every tool call: allow this bash line, block that curl, ask a […]