io.github.LufeMC/kavalai

Kaval

Verified · 19 days ago

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Install

claude mcp add kaval -- npx -y @usekaval/[email protected]

Requires: KAVAL_API_KEY, KAVAL_BASE_URL

Our take

Adds a freshness check for agent workflows by testing whether an assumption still matches current external reality before taking action. It is best suited to agents that make decisions from cached knowledge or long-running plans where staleness matters. The positioning is sensible, but with minimal visible ecosystem signal it looks like a focused infrastructure tool that needs closer evaluation before production use.

reviewed by hand · 2026-07-09

Something wrong or dead here? Report it

Verification record

last verified
19 days ago
github stars
0
last commit
25 days ago
archived
no
license
Apache-2.0
latest version
0.8.2
in registry since
2026-07-20

github.com/LufeMC/kaval-clients

claude-flowai

claude-flow

Verified · 18 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 18 days ago

tldrawai

tldraw

Verified · 19 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 19 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 9 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 9 days ago

openmetadata-mcpai

OpenMetadata

Verified · yesterday

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked yesterday

mobilerunai

mobilerun

Verified · 21 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.4k starschecked 21 days ago

praisonaiai

PraisonAI

Verified · 8 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed9.1k starschecked 8 days ago