MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
Agent Standup (OSS, local) turns Claude Code, Codex, Mistral Vibe, and Cowork sessions into a live stand-up: desks, screen-share of real commands/diffs, voices, replay + recap; `npx @double_geste/agent-standup --open`; VS Code/Cursor extension and Claude Code plugin. Free; optional Halloween character pack from €2.
Show HN Weatherdeck (Oct 16): a read-only TV/phone status board fed by small pushers that shows which coding-agent lanes are waiting on you, honest progress ranges, silent sources, and deferred/owned work—not monitoring/alerts; demo mode with ship-deck theme; open source on GitHub.
MCP gateway is GA in Red Hat Connectivity Link 1.5 with tenant isolation, progressive tool discovery (discover_tools/select_tools), 2026-07-28 stateless HTTP support, NeMo guardrails on tools/call, audit logs, and Prometheus broker metrics so enterprise agents route governed MCP traffic on OpenShift.
Local-first npm app: isometric office UI where each Claude Code session gets a desk; red windows flag waits for you, with tmux integration—watch many agents without scrolling terminals.
CLI reads Claude Code transcripts to show per-turn context cost—what ships before the first keystroke, unused payload, and skills that never reached the agent—so you can trim defaults instead of guessing.
Standalone Avior on the SolarWinds Platform lets IT teams define measurable goals, coordinate specialized agents across hybrid estates, and act under risk-tiered autonomy (dangerous steps need human approval) with audit trails, rollback, data masking, least-privilege tools, and MCP to third-party systems—available via guided onboarding from Oct 14, 2026.
Public beta: send OTel traces from Claude Managed Agents, Messages API, and SDKs to any OTLP destination (Langfuse, LangSmith, Grafana, Datadog, Sentry, etc.) so model calls, tool use, and MCP steps land beside the rest of the stack under GenAI semantic conventions.