breadcrumbs an agent leaves while working with you, kept in a space on your PDS.
Joshua Gu on Twitter / X
Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.🚨 While this is a good idea, we show a surprising result: systems… pic.twitter.com/XHFVaDcr4l— Joshua Gu (@astrogu_) May 20, 2026
Hermes Workspace · Your AI agent’s command center
Chat, memory, skills, terminal, and files — one interface for everything your agent does.
Charly Wargnier on Twitter / X
an AI agent literally destroyed all of this guy's production data 🤯Total AI disaster, yet totally predictable.here's the story:> Cursor agent (Opus 4.6) tries to fix a staging bug> Finds an unscoped Railway CLI token> Guesses an API call> Wipes Prod DB & 3 mos of backups… https://t.co/24KfDhMtVz— Charly Wargnier (@DataChaz) April 27, 2026
oops! your pds is gone :( - matt's not blog
a short story of scams & a devops eng. worst nightmare
The Lore Version Control System - Lore Developer Documentation
A reference document explaining the rationale, goals, and theoretical design of Lore. This is not a peer-reviewed paper; it is a public-facing standalone description of the system, intended to make the why of Lore - the problems it was built to solve and the design choices that follow from those problems - as legible as a reader can make it without reading the source code.
ndrstnd: understand what your coding agent actually did
A local comprehension workspace that turns agent-produced branch diffs into an evidence-linked story.
Architecture of this PDS — PDS docs
This chapter is the map. It explains how the code under [src/](../src/) is
Claude Code Unpacked
What actually happens when you type a message into Claude Code? The agent loop, 50+ tools, multi-agent orchestration, and unreleased features, mapped from source.
Cognition | Agent Trace: Capturing the Context Graph of Code
We’re excited to join in Cursor, Cloudflare, Vercel, git-ai, OpenCode and others in support of [Agent Trace](https://agent-trace.dev/). As described in the spec, Agent Trace is an open, vendor-neutral spec for recording AI contributions alongside human authorship in version-controlled codebases.
mdsnd
Paste this into your agent (Claude Code, Cursor, pi, ChatGPT…) — it posts its first note immediately:
Just published a repo that's doing nightly builds for several spaces-enabled PDSes. It's mostly for @happyview.dev testing, but I figured some others may get some use out of it as well. Lemme know if there are any other PDS implementation I should add! #atproto
GitHub - happyproto/pds-test
github.comBuilding a PDS the Hard Way agent.io/posts/building-a-pds
Building a PDS the Hard Way
agent.io
