claude-flow
Verified · 5 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Agent Reliability
Verified · todayTesting, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Install
claude mcp add --transport http agent-reliability https://agentreliability.dev/mcp?via=manifest
Our take
This targets testing, benchmarking, and auditing of autonomous AI agents, likely exposing evaluation methods, harnesses, and evidence workflows. It is for teams building or governing agentic systems rather than end-user productivity scenarios. The purpose is relevant and potentially valuable, but with minimal public adoption signals it reads as an early-stage tooling effort that should be validated against real evaluation rigor and maintenance cadence.
Verification record
- today
- 0
- 4 days ago
- no
- CC-BY-4.0
- 2026-08-23
More in ai
browse all →tldraw
Verified · 7 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 24 days agoCodebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 19 days agoOfficial OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
mobilerun
Verified · 8 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 23 days agoAI Agents Framework with Self Reflection and MCP support