claude-flow
Verified · 17 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
The Aggregate — LLM benchmark aggregate
Synced · awaiting checkFused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.
Install
claude mcp add --transport http the-aggregate https://theaggregate.ai/mcp
Our take
This server aggregates many public LLM benchmark leaderboards into a single comparative ranking scale. It is for model evaluators, research teams, and buyers who want a broad cross-benchmark view without manually reconciling sources. The concept is useful, but benchmark fusion always embeds methodology choices, so users should inspect how rankings are constructed before relying on them for high-stakes comparisons.
Verification record
- today
- 2026-07-25
More in ai
browse all →tldraw
Verified · yesterdayDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 14 days agoCodebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 10 days agoOfficial OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
mobilerun
Verified · yesterdayControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 14 days agoAI Agents Framework with Self Reflection and MCP support