REA
Verified · 12 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
plzebo
Verified · 31 days agoCost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.
Install
claude mcp add plzebo -- npx -y [email protected]
Our take
Plzebo appears to benchmark agent loops on cost, time, and success rates across model mixes, which makes it relevant for teams comparing orchestration setups or evaluation economics. The use case is specialized but legitimate for AI tooling researchers and platform engineers. With very low adoption signals and a fairly ambitious promise around verifiable receipts, it reads as an early-stage utility that likely needs hands-on validation.
Verification record
- 31 days ago
- 0
- 3 mo ago
- no
- MIT
- 0.2.0
- 2026-07-30
More in ai
browse all →claude-flow
Verified · 41 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
tldraw
Verified · 42 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 32 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 24 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
Mobilerun
Verified · 44 days agoLet AI agents control Android and iOS devices on Mobilerun Cloud: screen, input, apps, workflows.