LIVE-Last scan updating-53 sources active-1012 signals today-DEVELOPER Agent-Inspect: Local Execution Trees for TypeScript AI Agents
AI 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
6,589
current graph
Top trend
46
deverman/FocusRelayMCP: Fast native Swift OmniFocus MCP server and CLI for macOS. Let AI assistants safely read, update, complete, and organize tasks and projects through documented Omni Automation APIs.
TopicCategorySignalsMomentumLast seenTrend
deverman/FocusRelayMCP: Fast native Swift OmniFocus MCP server and CLI for macOS. Let AI assistants safely read, update, complete, and organize tasks and projects through documented Omni Automation APIs.
deverman/FocusRelayMCP
Developer Tools162Jul 19, 2026RDR46
bilalbentoumi/pi-vsc: Pintra — Pi Agent for VS Code
bilalbentoumi/pi-vsc
Developer Tools162Jul 19, 2026RDR46
forefy/.context: AI Agent Skills for Security Auditing to generate triaged, industry grade report findings, code locations, pocs, attacker story flow graphs and more
forefy/.context
Developer Tools162Jul 19, 2026RDR46
santosh/lalalangchain: Learning LangChain by example — self-contained lessons (agents, memory, multimodal) on local Ollama.
santosh/lalalangchain
Developer Tools162Jul 19, 2026RDR46
1tsRajOwO/oryven: Lumen — private local AI desk agent. MIT · free forever · on-device with Ollama. macOS, Windows, Linux.
1tsRajOwO/oryven
Developer Tools162Jul 19, 2026RDR46
Leisure-Auf1/A3-Multi-Agent-System: Research Prototype: 12-Agent Personalized Learning System. Multi-agent collaboration, EventBus, Memory Layer, 6 resource types, self-improvement loop.
Leisure-Auf1/A3-Multi-Agent-System
Developer Tools162Jul 19, 2026RDR46
emanuelmerino481/loop-importer: Import existing research projects into review-first Agent Loops without executing source code
emanuelmerino481/loop-importer
Developer Tools162Jul 19, 2026RDR46
88plug/recover-from-false-positive: Recover Claude Code sessions after an Anthropic API output-classifier false positive. JSON-aware .jsonl log surgeon: removes the triggering message + refusal turn, re-stitches the parentUuid chain so the session resumes cleanly, cleans old sessions, installs a per-repo CLAUDE.md framing guard.
88plug/recover-from-false-positive
Developer Tools162Jul 19, 2026RDR46
88plug/scientific-method: Falsification-first investigation + invention workflow for Claude Code: hypothesis ledgers, controlled experiments, REFUTE-first verification, and provable invention.
88plug/scientific-method
Developer Tools162Jul 19, 2026RDR46
88plug/trigger-my-training: Ground-first reflex for Claude Code: the agent judges complexity from its own training, grounds before acting, and is hard-blocked from the irreversible step until it has.
88plug/trigger-my-training
Developer Tools162Jul 19, 2026RDR46