How to Compose Multi-Agent Teams with Omnigent: Claude Code, Codex, and Custom Agents
Step-by-step guide to installing Omnigent and composing a multi-agent team from Claude Code, Codex, and custom agents under unified policy control.
How-Tos
525 piecesHow to Use Kimi K2.7 Code with OpenClaw for Agentic Coding Tasks
Kimi K2.7 Code from Moonshot AI lands in OpenClaw 2026.6.7 — 1T-param MoE, 256K context, 30% fewer thinking tokens, open weights on HuggingFace.
OpenClaw v2026.6.6 Released — Comprehensive Security Boundary Hardening
OpenClaw v2026.6.6 tightens security across exec approvals, MCP stdio, sandbox binds, and agent ACP bypass patches — essential update for self-hosters.
Atlassian MCP HTTP+SSE Transport Deprecated — Migration Required Before June 30, 2026
Atlassian's MCP HTTP+SSE transport dies June 30. Migrate to Streamable HTTP at /v1/mcp now — all permissions carry over automatically.
Langflow CVE-2026-5027 Actively Exploited — Upgrade to 1.10.0 Now
Langflow path traversal flaw (CVE-2026-5027, CVSS 8.8) is being actively exploited — upgrade to 1.10.0 immediately.
Check Point Research: Critical LangGraph Vulnerability Chain Enables RCE via AI Agent Memory
Check Point discloses LangGraph SQLi-to-RCE vulnerability chain targeting AI agent memory — 50M+ monthly downloads at risk.
Rubrik Agent Cloud Launches for Anthropic Claude Code — Enterprise Governance and Rollback for AI Agents
Rubrik launches enterprise control plane for Claude Code agents with rollback, governance, and real-time policy enforcement at scale.
Anthropic Requires 30-Day Data Retention for Fable 5 and Mythos 5 — Privacy Tradeoff for Frontier Capability
Fable 5 and Mythos 5 mandate 30-day data retention — Zero Data Retention is off the table, forcing enterprise agentic workflow compliance reviews.
OpenClaw v2026.6.5 Released — Free Parallel Web Search, security.installPolicy, and 216-PR Stability Overhaul
OpenClaw v2026.6.5 lands free parallel web search and operator-controlled skill install policy in a 216-PR stability release.
OpenClaw v2026.6.6-beta.1 — Security Boundary Hardening Across Transcripts, Sandboxes, MCP, and Exec Approvals
OpenClaw's beta tightens exec approvals, transcript redaction, sandbox binds, and MCP boundaries — fail-closed on timeout is now the default.