At Superagentic AI, we have published a new MLX 4-bit conversion of Gemma 4 31B IT for Apple Silicon workflows. The model is now available on Hugging Face at SuperagenticAI/gemma-4-31b-it-4bit-mlx. […]
Meta-Harness: A Self-Optimizing Harness Around Coding Agents
Stanford AI lab just released the Meta Harness paper which covers the meta harness strategy that self-optimise. Most conversations about coding agents focus on the model. People compare model quality, […]
Harness Engineering: Why It’s Suddenly the Hottest Topic in AI Agent Engineering
If you build agents, you already know the feeling: the model is smarter than ever, yet your agent still flakes on long tasks, loses context, or ships brittle code. The […]
Turbocharge Pydantic AI + SurrealDB RAG with TurboAgents and TurboQuant
Google Research released the TurboQuant, the game changing compression technique also Superagentic AI released the TurboAgents to showcase the use of the TurboQuant in the real Agentic AI systems. This post […]
Introducing TurboAgents: Supercharge Your Agents with TurboQuant
Google research released the TurboQuant the technique that compress the context for LLMs. The next bottleneck in agent systems is not just model quality. It is retrieval cost, memory pressure, […]
Introducing Agentnetes: Self-Discovering AI Agent Swarms, On Demand
On 21 March, I attended Zero to Agent London, a hackathon hosted by Google DeepMind and Vercel. The challenge was simple: build something with agents. The result was Agentnetes, an […]
CodexOpt: Optimize AGENTS.md and SKILL.md for Codex with GEPA-Inspired Feedback
Modern coding agents are getting better fast. But for most teams, one problem remains stubbornly manual: the instructions that shape agent behavior. A repo might have an AGENTS.md. It might […]
A2A v1 in SuperOptiX: Expose, Connect, and Orchestrate AI Agents
A2A v1 has just been announced, the first stable release of the Agent-to-Agent protocol. A2A, short for Agent-to-Agent, is an open protocol for communication between AI agents. It defines how […]
Agent Engineering 101 at GDG London: How to Build Reliable AI Systems
Last week I had the chance to speak at GDG London Build with AI 2026. My session, Agent Engineering 101: How to Build Reliable AI Systems, is now live as […]
OpenClaw ACP: What Coding Agent Users Need to Know About Protocol Gaps
An analysis of where OpenClaw’s ACP bridge works, where it diverges from the protocol, and when it is not suitable for your coding agent workflow. OpenClaw ACP Is a Bridge, Not […]