EdTech Tracker

← Coding lens

labs agent

tool judged 3% likely a named technique or architecture

First seen
2026-01-20
Independent sources
3
Articles
15
Last 4 weeks vs prior
0 vs 2

See how it has spread across media tiers

Mentions over time

Articles per week (by publish date) using the term, in any spelling.
01.532026-W032026-W332026-W40
Table view
WeekArticlesSources
2026-W0311
2026-W0821
2026-W2921
2026-W3132
2026-W3311
2026-W3421
2026-W3621
2026-W3911
2026-W4011

In their words

That claim is backed by a Vitest suite (63 tests across five files) that exercises each layer against an in-memory fake of the NAMS client: Try It today npm install @neo4j-labs/nams-ai-provider ai @ai-sdk/provider @neo4j-labs/agent-memory zod Get a free API key at memory.neo4jlabs.com → MEMORY_API_KEY=sk-nams-… Swap one line in your chat route Your agent remembers from the next deploy npm install

Agent memory ( Neo4j Labs) : neo4j-agent-memory ( https://neo4j.com/labs/agent-memory/ ), also known as Neo4j Agent Memory Service (NAMS), gives conversational agents persistent, structured memory.

What RAGAS, PromptFoo and DeepEval do for Python, AgentEval does for .NET Neo4j Agent Memory & NAMS ( Documentation ) NAMS – Agent Memory Console https://neo4j.com/labs/agent-memory The full story (longer read): AgentMemory for .NET: Persistent AI Agent Memory Engine | Jose Luis Latorre posted on the topic | LinkedIn Thanks to Zaid Zaim for the early encouragement, and to Michael Hunger for surfac

Top skills include: - find-skills (322K+ installs) — Meta-skill that helps discover other skills - vercel-react-best-practices (167K+ installs) — React and Next.js patterns from Vercel Engineering - web-design-guidelines (127K+ installs) — UI/UX best practices The CLI tool makes installation trivial: # Search for skills npx skills find react performance # Install a skill npx skills add vercel-labs

Instead of asking an AI to parse raw HTML or CSS selectors, agent-browser provides a compact accessibility tree with refs like @e1, @e2 — dramatically reducing token usage: # Traditional approach: ~3000-5000 tokens Full DOM/HTML → AI parses → CSS selector → Action # agent-browser approach: ~200-400 tokens Compact snapshot → @refs assigned → Direct interaction Installing agent-browser# Install the

Use it to: discover new skills to enhance your agents browse skills by category and popularity track usage stats and installs across the ecosystem Get started with npx skills add vercel-labs/agent-skills and explore skills.sh .