kort3x.ai by metAgentic.ai

kort3x.ai (Kortex) gives AI agent teams what they lack most: durable, inspectable shared memory and governance. It manages work as Markdown and YAML tickets called neurons, groups them into assemblies and big goals (BHAGs), applies soft standards for readiness and risk, and runs a local queen orchestrator loop that keeps a swarm on task.

There is no database and no server to run. The brain is just files, so everything an agent knows or decides can be grepped, diffed, reviewed, and version-controlled in git, exactly like code. Humans and agents work from the same source of truth.

Key Capabilities

• Neurons, Assemblies, and BHAGs – Structured units of work from a single task up to organization-level goals, with progress rolled up automatically.
• Soft Standards – Preflight readiness and risk checks before work starts, with explicit approvals and auditable overrides.
• Queen Orchestrator – A local loop that routes work to the right agents and keeps long-running swarms coherent.
• MCP Tool Layer – The brain is exposed to AI agents as Model Context Protocol tools, so any MCP-capable assistant can create, query, move, and approve work.
• Git-Native by Design – Every decision and status change is a file change: reviewable in pull requests, recoverable from history, portable anywhere git goes.
• Fast and Local – A single Rust CLI. No infrastructure to stand up, nothing to babysit.

Why It Matters

Agentic AI fails quietly when context lives in chat history: work gets repeated, decisions get lost, and no one can audit what the swarm actually did. kort3x.ai moves that context into durable, human-readable files with governance built in, which is what makes multi-agent systems dependable enough for real operations.

kort3x.ai is the coordination layer behind our own multi-agent development work, including the swarms that build and run skew.ai and pox.news.

Get Early Access