AgentBreakWatch

Early signal

Track breaking changes across 258 AI Agent SDKs & MCPs

Launched 17d ago

Signal

Velocity

What this means

30%Vote pace is below typical for AI Agents.

Running at 30% of comparable launches.

+30%Launching in a 30% WoW growing category.

Open Source had 129 launches this week vs 99 last.

15Founder Conviction Index: 15 — low signal.

Few of the conviction sub-signals (reputation, velocity, buyer-intent, tagline clarity) are firing yet.

Prediction

Top-5 finish probability

today

Projected end-of-day votes

3range 2–4

Trajectory

stable

Vote pace holding steady.

Speed vs peers

0.3×

178 AI Agents launches

About

AgentBreakWatch tracks release velocity, breaking changes, and MCP tools/list schema drift across 258 production AI Agent SDKs and Model Context Protocol servers on npm and PyPI. Paste your package.json, requirements.txt, pyproject.toml, ormcp.json to spot archived servers and breaking upgrades in 5 seconds, or query our free MCP server directly from Cursor and Claude Code.

AI Summary

AgentBreakWatch monitors release velocity and breaking changes across 258 AI Agent SDKs and Model Context Protocol servers on npm and PyPI. Users can quickly identify archived servers and breaking upgrades by pasting configuration files or querying the MCP server directly.

Attention & discussion velocity

Performance

Velocity0

Vote pace vs average

Momentum0

Sustained over 6h

Virality0

Spread × engagement

Engagement—

not measured

Signal sources

2 of 6 active

Launch tracking5 readings since we picked it up
AI analysisAI Agents
Comment intelligencethread not yet analysed
Outside discussionnot checked — domain is a storefront or shared
Revenue signalsno match on this domain
Editorial scoringbelow the signal threshold for this pass

A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.