🧠 Automated AI Knowledge Base for Product Managers — 4-pillar system with self-evolving knowledge graph. Updates every 4h.
-
Updated
Jun 20, 2026 - HTML
🧠 Automated AI Knowledge Base for Product Managers — 4-pillar system with self-evolving knowledge graph. Updates every 4h.
TokenSched — a CPU-scheduler-style token-budget admission controller for coding agents: pre-allocate budget per sub-task, down-tier or preempt low-value work before the window blows.
Curated Hermes Agent skills & runbooks — personal knowledge workflows, ready to drop into your own agent. | 精选 Hermes Agent Skill 合集,记录和分享 hermes-agent 使用经验,开箱即用。
idemstep — exactly-once idempotency for agent side-effects
Signed manifest + scope-drift detector for Claude Code skills.
Forensic timeline that shows which bash command your AI ran at 3am
Structured verification gate for AI agent edit loops — AST-level proof that edits actually landed
An LLM agent action space for legacy Windows desktop apps — drives WinForms / SCADA / old-school thick clients via the UIA accessibility tree
AI 落地情报雷达 · 真实案例追踪 / 行业趋势 / 付费简报选题
Context-budget profiler for Claude Code sessions — a flame-graph of where your tokens actually go.
Zero-config CLI that audits a JS/TS repo for AI-generated code slop and emits a single SlopScore (0-100) plus a ranked file heatmap.
Scan the code your AI coding agent reads, before it obeys hidden prompt-injection instructions.
N agents, 1 human: an approval triage queue for coding agents — wrap, serve, attach, approve from your phone.
Offline, explainable CLI + library that detects when a hosted LLM silently refuses or shapes its answer
Catch hidden agent-instruction / prompt-injection payloads in your npm/pip/go dependencies — SARIF output, CI-ready.
Harness-neutral proxy that keeps your coding agent's KV cache alive across turns
Transparent DeepSeek prefix-cache spend profiler — wrap your client, see hit/miss P&L per request, stop silently busting the cache
skvet — pre-install risk scanner for agentic skill bundles: stars-orthogonal shell/hook/network safety score
skillprov — verify declared vs observed capabilities for agent skills
Add a description, image, and links to the ai-radar topic page so that developers can more easily learn about it.
To associate your repository with the ai-radar topic, visit your repo's landing page and select "manage topics."