AI on Radar
Subscribe
Topic intelligence

Cross-source radar trends, not isolated headlines.

Topics connect real clusters, entities, source mix, and published decisions. Empty states are real; no trend is invented when the signals are not strong enough yet.

Topics
8,989
current graph
Top trend
46
dajiaohuang/dnd-dm-agent: Local-first LangGraph DND Dungeon Master agent with campaign memory, BGE-M3 RAG, character sheets, and NapCat QQ integration
TopicCategorySignalsMomentumLast seenTrend
dajiaohuang/dnd-dm-agent: Local-first LangGraph DND Dungeon Master agent with campaign memory, BGE-M3 RAG, character sheets, and NapCat QQ integration
dajiaohuang/dnd-dm-agent
Developer Tools162Jun 15, 2026Score46
DojoGenesis/cli: Dojo CLI — a Claude Code-inspired terminal for the AgenticGateway. Interactive REPL with slash commands, plugin system, hook runner, and SSE streaming.
DojoGenesis/cli
Developer Tools162Jun 15, 2026Score46
Treibs/kp-build: Citation-verified, agent-loadable knowledge packages — verified cites, grounded claims, and a falsification gate that proves it helps. The authoring engine for KPM.
Treibs/kp-build
Developer Tools162Jun 15, 2026Score46
Ow1onp/hermes-agent-skills: Production-grade skills for Hermes Agent - self-evolving, persona-aware, slash-command native
Ow1onp/hermes-agent-skills
Developer Tools162Jun 15, 2026Score46
88plug/searxng-mcp: Fast, token-efficient MCP server for SearXNG with stdio, streamable-http, Docker, and rendered fetch support.
88plug/searxng-mcp
Developer Tools162Jun 15, 2026Score46
leox255/termem: Cross-agent memory and session manager for the terminal. Recall, search, and resume Claude Code / Codex / Gemini / opencode / shell sessions. Shared memory via MCP, no model calls.
leox255/termem
Developer Tools162Jun 15, 2026Score46
CyberStrikeus/CyberStrike: AI-powered offensive security agent with 7,300+ actionable security skills. Autonomous pentesting powered by MITRE ATT&CK (2,000+ Atomic tests), CIS Benchmarks (1,500+ controls), OWASP, NIST. Lazy-loading, zero context pollution. Your AI red team.
CyberStrikeus/CyberStrike
Developer Tools162Jun 15, 2026Score46
AscendyProject/redteam: Adversarial agent-pair harness: one model writes code through a TDD pipeline, a second model reviews it, gated at human checkpoints. Apache-2.0.
AscendyProject/redteam
Developer Tools162Jun 15, 2026Score46
elliottwaves-20/agent-guard: Scan AI agent skills, plugins, and MCP servers for malicious code before installation - one scan, every agent (Claude Code, Codex, Gemini, Hermes, OpenClaw). Powered by cisco-ai-skill-scanner.
elliottwaves-20/agent-guard
Developer Tools162Jun 15, 2026Score46
WeThinkIn/AIGC-Interview-Book: 【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。
WeThinkIn/AIGC-Interview-Book
Developer Tools162Jun 15, 2026Score46