AgentPulse, drift investigation for multi vs Stele

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read what your project already decided, so context survives between tools and sessions.

About AgentPulse, drift investigation for multi

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next. What did change is the payload it receives from writer, starting at the same run. So critic is probably downstream damage, not the source. After the change, writer responses run ~180% longer and drop the section structure critic expects, earlier payloads were structured summaries, newer ones read as prose. If restoring the format fixes critic, make the fix in writer.

About Stele

Shared memory for AI coding agents. Claude Code, Cursor and Codex read what your project already decided, so context survives between tools and sessions. Only one of these agents knows this was tried last spring and rolled back. KNOW-142 : a captcha on checkout shipped last spring and was reverted after two weeks. The bot traffic is real, though it spikes on release days and is quiet the rest of the time. A gate armed only during a release window would avoid repeating that.