AgentPulse, drift investigation for multi vs Context Mode Insight

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

An open-source MCP plugin (300,000+ developers) and a commercial Platform that builds Solutions on top. context-mode keeps raw data out of the LLM context window. Insight...

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 Context Mode Insight

An open-source MCP plugin (300,000+ developers) and a commercial Platform that builds Solutions on top. context-mode keeps raw data out of the LLM context window. Insight surfaces what your team is doing with the saved tokens. Works on Claude Code, Cursor, Copilot, Codex, Gemini, and 12 more. Solutions that show you what your team is doing with the AI tools they already run. Every gh issue list, every grep, every file read piles into the conversation and gets re-sent every turn.