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
9,051
current graph
Top trend
45
Agent-Post-Office/agentpostoffice-cloudflare: Self-hosted email infrastructure for AI agents on Cloudflare Workers
TopicCategorySignalsMomentumLast seenTrend
Agent-Post-Office/agentpostoffice-cloudflare: Self-hosted email infrastructure for AI agents on Cloudflare Workers
Agent-Post-Office/agentpostoffice-cloudflare
Developer Tools160Jul 11, 2026Score45
SunMe1977/HermesClawZero-ConfigSidecar: HermesClaw Zero‑Config Sidecar is a lightweight local vector‑memory engine for Hermes and OpenClaw. It runs as a zero‑config sidecar, providing fast embeddings, persistent memory, and instant retrieval for agents and MCP tools. Built for speed, simplicity, and full local control.
SunMe1977/HermesClawZero-ConfigSidecar
Developer Tools160Jul 11, 2026Score45
api-evangelist/civic: Civic APIs.json profile
api-evangelist/civic
Developer Tools160Jul 11, 2026Score45
AgentMaturity/AgentMaturityCompass: Evidence-based maturity framework for AI agents — 235 questions, 5 layers, CLI + SDK. Score, red-team, and ship with proof.
AgentMaturity/AgentMaturityCompass
Developer Tools160Jul 11, 2026Score45
natureco-official/natureco-cli: A powerful CLI for AI-powered chat, automation, and multi-platform integrations — terminal-native alternative to Claude Code & OpenClaw. Chat with your bots, automate workflows, and connect Telegram, Discord, Slack & more.
natureco-official/natureco-cli
Developer Tools160Jul 11, 2026Score45
Alices5723/n8n-telegram-voice-transcription-bot: Transcribe and summarize Telegram voice messages using an automated n8n workflow powered by Groq.
Alices5723/n8n-telegram-voice-transcription-bot
Developer Tools160Jul 11, 2026Score45
zbl1998-sdjn/MASE-agent-memory: Governed white-box memory for LLM agents: every fact carries a mechanically-verified evidence span, every rejected hypothesis is documented. Local-first (SQLite+FTS5), 1000+ tests. LV-Eval-256k 91.94% / NoLiMa-32k literal 96.43% on a local 7B — negative results disclosed.
zbl1998-sdjn/MASE-agent-memory
Developer Tools160Jul 11, 2026Score45
Azerax/Starfish: Governance for AI agents: a deny-by-default policy layer for Claude Code and agent/skill builds. Every tool call is authorized, contained, and audited. Apache-2.0.
Azerax/Starfish
Developer Tools160Jul 11, 2026Score45
zacharygcook/agent-skills: A curated collection of practical, evidence-backed skills for coding agents.
zacharygcook/agent-skills
Developer Tools160Jul 11, 2026Score45
ComplexAR/Insight-Engine: Verified, defensible investigation of high-stakes, complex, contested, and wicked problems — a Claude Code & Claude Cowork plugin: source-tiered web verification, a disconfirmation pass, grade-locked decision briefs, and audience rendering, architected around the ICD-203 analytic tradecraft standards.
ComplexAR/Insight-Engine
Developer Tools160Jul 11, 2026Score45