Agent Harness: Plan, Delegate, Verify
Inside Agent Harness: why Pro keeps serious work in one agent, when Ultra workers help, and how exact-action approvals and verification shape the result.
Agents Articles
Browse Agents articles and practical insights from Agent Zero.
Skill Synthesizer: From Fix to Procedure
Follow Skill Synthesizer from a completed conversation to a discoverable SKILL.md, and separate confidence, artifact validation and useful transfer.
Durable Execution for Agent Zero: Crash, Restart, Continue
A deep look at Alessandro Frau's experimental Durable Execution plugin: how it journals every model and tool call, recovers interrupted chats after a crash, and refuses to repeat actions it cannot prove are safe.
HOW THE HELL DO I... Get the most out of Agent Zero?
Get more from Agent Zero with the connector and Launcher: host files, shell access, browser automation, desktop control and practical setup steps.
HOW THE HELL DO I... Use A0 Swarms?
Episode 4: build a useful Agent Zero swarm. Learn setup, worker prompts, the live panel, workspaces and remote agents—and when native parallel is the better fit.
How the Hell Do I... Use Projects? Workspaces Your Agent Actually Understands
Part 2 of 'How the hell do I... with Agent Zero'. Projects give a chat its own instructions, files, memory, secrets, skills, MCP servers, agent profiles and model presets. Here is what a project really is, what changes the moment you activate one, and how to get the most out of it.
How the Hell Do I... Nest My Plugins? Meet Plugin Nester
Part 1 of 'How the hell do I... with Agent Zero'. Plugin Nester installs community plugins as managed nested children, scans them before they are linked, groups them into project and profile bundles, and lets the agent manage them itself. Here is how to use it properly.
Memory That Ages Like Wood: Tree Ring Memory for Agent Zero
Tree Ring Memory is a local-first, Rust-native memory lifecycle layer that keeps fresh memory sharp, compresses old memory into rings, keeps hard lessons visible as scars, and promotes verified truths to heartwood. Here is why it is a strong complement, or a full alternative, to Agent Zero's built-in memory.
Your Browser. Your Agent. Meet the Agent Zero Chrome Bridge
The upcoming Agent Zero Chrome Bridge lets your agent work inside the Chrome you already use, with your logins and tabs, while every consequential action waits for your approval. Use cases, architecture, safety model and setup.
A0 Self-Improvement: Why RLM + GEPA Beats Either Alone
How the A0 Self-Improvement plugin combines recursive long-context analysis with reflective prompt evolution—and why authority, replay, canaries, and a bounded autopilot loop matter more than the optimizer brand.
Agent Zero v3: A Sneak Peek Inside the Sandbox
Agent Zero's third major iteration is moving agent-run code and heavyweight tools into isolated, disposable gVisor sandboxes.
Work in Progress: Spynel — One Conversation, Many Agents at Work
Jan Tomášek previews Spynel, a new orchestration layer that turns established AI coding harnesses into one durable, review-driven workflow from desk or phone.