The Vision for #W3C# has been published as a W3C Statement: As one of the editors, along with Chris Wilson (@cwilso), I’m both proud of this multi-year W3C Advisory Board effort, and grateful … #w3cVision# #w3cAB# #openWeb# #Vision#

Last week I participated in #w3cTPAC# 2024. It was quite packed, and often started early, from 8am informal breakfast meetings at a nearby IHOP, to Working Group, Community Group, and other small group meetings every day (but Wednesday) til 18:00. …

Comparing the full benefits of Ultimate Plus Edition. 10,000 FC Points ✔ Season 1-5 Premium Pass ✔ Hall of FUT Player Pick ✔ Pre-order #FC27# now:

New Neo-cypherpunk Summit speaker from @brave: @PryvitKyle x Staff Cryptographic Security Engineer He helps to promote a world where the web can be more private and secure for everyone. This vision led him to be an eager contributor to the design and development of standards in W3C and IETF. Loaded with a Bachelors of Arts in Computer Science from the University of Iowa, a penchant for applied cryptography, cybersecurity, privacy-enhancing technologies and a need to further enhance mankind's symbiotic relationship with technology. Kyle knows how to bring privacy to millions of people, integrate parallel economic systems, and sustain funding for open-source teams: 14 June, Berlin:

# Practical ways to use the Claude Agent SDK 📊 Visualize all agent activity in Datadog, Grafana, or Langfuse with OpenTelemetry. OpenTelemetry Observability exports agent traces, metrics, and logs via OTLP to external monitoring tools. 📌 Title: Observability with OpenTelemetry 🔗 URL: 🧩 Overview Enable with `CLAUDE_CODE_ENABLE_TELEMETRY=1` to export traces, metrics, and logs via OTLP to Honeycomb, Datadog, Grafana, Langfuse, and more. W3C trace context propagation automatically links agent traces to your application traces. 🛠 How to use it ```bash export CLAUDE_CODE_ENABLE_TELEMETRY=1 export CLAUDE_CODE_ENHANCED_TELEMETRY_BETA=1 export OTEL_EXPORTER_OTLP_ENDPOINT=https://your-collector:4318 ``` 🏗 Practical usage - Monitor "which tools were called, how long each took, how many tokens were used, and where failures occurred" in a single Datadog dashboard. - Get `claude_code.interaction` / `llm_request` / `tool` / `hook` spans with enhanced telemetry to visualize entire sub-agent delegation chains in one trace. - Inject ` / ` via `OTEL_RESOURCE_ATTRIBUTES` to build per-user audit trails and forward to SIEM. 💡 Use cases 🔍 Detailed trace analysis of agent execution 👥 Per-user audit trails 🚨 Bottleneck identification during failures ⚠️ Watch out The `console` exporter conflicts with the SDK's message channel — don't use it. For short-lived processes, shorten `OTEL_*_EXPORT_INTERVAL` to prevent missed flushes. #ClaudeAgentSDK# #AI#

Last two weeks I shipped myself 46 tickets, most closed and merged A few key things: - Memory now adapts to each user: preference nodes with weighted "prefers" edges personalize retrieval per user in the same graph, different answers depending on who's asking. -> great help from Lazar - recall() on a not-yet-built graph now returns instantly with a "memory warming up" marker instead of running a full graph search + LLM call. We found 511k wasted searches from empty-graph queries - New cognee-cli doctor: misconfiguration now fails loudly at first use with preflight checks, instead of surfacing as a cryptic error three steps later. - Every fact in your knowledge graph can now carry an audit-grade provenance trail (W3C PROV-O)