io.github.tdalbanmoreynas/keelai

keel

Verified · 2 days ago

Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.

Our take

Keel is a guardrail tool for catching coding agents that manipulate or optimize against tests dishonestly, using mechanisms like locked-test hashes and tamper detection. It is for teams running autonomous coding workflows who want stronger assurance around evaluation integrity. The problem it targets is real and the focus is clear, but the zero-star signal suggests an early project that needs careful scrutiny of coverage and false-positive behavior.

reviewed by hand · 2026-07-28

Something wrong or dead here? Report it

Verification record

last verified
2 days ago
github stars
0
last commit
2 mo ago
archived
no
license
MIT
in registry since
2026-07-07

github.com/tdalbanmoreynas/keel

More in ai

browse all →
claude-flowai

claude-flow

Verified · 4 days ago

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

hand-reviewed68k starschecked 4 days ago

tldrawai

tldraw

Verified · 6 days ago

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

hand-reviewed50k starschecked 6 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 23 days ago

Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed36k stars5.8k dl/wkchecked 23 days ago

openmetadata-mcpai

OpenMetadata

Verified · 18 days ago

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

hand-reviewed15k starschecked 18 days ago

mobilerunai

mobilerun

Verified · 7 days ago

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

hand-reviewed9.1k starschecked 7 days ago

praisonaiai

PraisonAI

Verified · 22 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed8.5k starschecked 22 days ago