9 posts tagged with "agents".
Pi Durable ♥ Actors: One Agent, One Owner, Any Worker
I have always thought of agents as actors with, well, agency. Pi Durable's one-owner rule makes that almost literal: give each agent its own harness and it is an actor. I spread scripted agents over two worker nodes, killed one, and watched where the work went.
This Post Has Tools: A Hands-On Look at WebMCP
WebMCP lets a web page hand an agent tools instead of pixels. This post registers its own tools, and you can call them from the page. What WebMCP is, when to use it, how it differs from MCP, and when not to bother.
DeepSeek Harness on a Claude Subscription in 120 Lines
DeepSeek Harness has no way to use a Claude subscription, so I wrote a plugin for it. Its model seam is stateless like Pi's, which meant I could borrow pi-claude-code for the hard part and dsh's own pi-ai adapter for the rest.
Two Harnesses Walk into a Claude Subscription
OpenCode and Pi (via pi-claude-code) can both use a local Claude Code login. OpenCode keeps a Claude Code session open across tool calls, while Pi runs a fresh worker for each step and replays the transcript.
Code Mode That Survives a Crash: Durable Scripts in Pi Durable
Code mode lets the model write a script that calls tools. Pi Durable makes that script resume after a restart without rerunning finished calls. What code mode is, how durable replay works, and when to reach for it.
Pi Durable: A Look at the Future of Agent Harnesses
Pi Durable's building blocks: persisted tasks, conversations, application state, and agents whose work can survive the process that started it.
Jev at the Branches: The State Machine Is the Agent
A state-machine architecture in which deterministic code owns the plan and the facts, while Jev supplies bounded judgment only at decision branches.
Managing Context Windows with pi /tree: Branches, Summaries, and Subagent-like Workflows
How I use pi's /tree to manage context windows in long coding sessions, when to choose /tree vs /fork, and patterns that feel like lightweight subagents without leaving one session.
Supercharged Code Reviews: How AI Subagents Make Human Reviewers Superhuman
Speed up your team's code reviews with AI-powered analysis that catches what humans miss and prepares focused insights, making reviewers more effective without replacing their expertise.