AI & Agents MCP servers

Shared memory for teams and their AI agents: Markdown concepts with typed links in shared bundles.

Start and follow atoma builds; read their runs, traces, agent registry and skill catalogue.

Governed decision engine: yes/no, score, choice and rank answers about cases, from past outcomes.

One wiki for all your agents: pages read and written over MCP, a link graph, and broken-link checks.

Relay for messages and schema-checked tasks between AI agents.

Build, test and publish Olbrain AI agents from Claude Code, Codex or Claude.ai.

Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect.

Marketplace where AI agents hire and pay other agents in USDC on Base, through on-chain escrow.

Rooms where agent sessions across machines, people and providers work together.

Connect agents to Lycatra knowledge, memory, collaboration, schedules, notifications, and teams.

The operating system for self-organised AI agent teams.

Shared workspace where Claude, ChatGPT, Codex and Grok share files, tasks, decisions and handoffs.

Hand a task to another person's AI agent, or take paid tasks. Paid only when the work passes.

Context engineering for AI coding agents: product context, project missions, and 360 memory.

Human-agent interface for projects: you prioritize and decide, your AI agents execute. Over MCP.

Secure and manage MCP servers through the Speakeasy AI Control Plane from your agent.

Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.

Build and operate Dapr Workflows and Durable Agents on Diagrid Catalyst. Sign-in required.

Person-owned AI memory: portable context for any MCP client.

Deploy the apps you build with AI, with databases and domains, and call 200+ AI models on one key.

Shared task layer for AI agents: tasks, handoffs and decisions that persist across tools.

Crash-test your AI agent on real professional decisions, graded against what actually happened.

Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.

Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.

End-to-end agent-managed company brain. Docs, diagrams, plans, databases, agents, Knowledge Graph.

Agent skills for Claude, Codex and Cursor: find, install and load skills from one connector.

A legal body for AI agents: a real company, a verified human and spending rules on Arc (testnet).

Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.