Lobu

Point any MCP client at Lobu. No Lobu agent runtime orlobu.config.tsis required.

# Claude Code claude mcp add --transport http lobu https://lobu.ai/mcp # Codex codex mcp add lobu --url https://lobu.ai/mcp

Complete OAuth when prompted, connect the sources you want to share, and ask your agent to use Lobu when it needs shared context.

The same MCP endpoint works withChatGPT, Claude Desktop, Gemini CLI, Cursor, and custom MCP clients.lobu memory initdetects Claude Code, Codex, Gemini CLI, and Cursor, and prints manual setup steps for Claude Desktop and ChatGPT.

Ask from Claude Code, Codex, or ChatGPT:

What did we decide about enterprise onboarding, and what changed since the last release?

Lobu searches shared, durable organizational memory under the caller's permissions, regardless of which agent asks. The answer can combine connected discussions, project activity, customer records, saved decisions, and typed company entities without rebuilding that context from scratch in every chat.

Hand work to a persistent Lobu specialist

Ask our customer-researcher specialist to review the latest feedback and propose the next three interviews.

The agent discovers the specialists available to you, selects the right one, delegates the task, and brings the result back. The specialist has its own identity, instructions, tools, durable conversations, and access policy.

To the user this stays one conversation in their primary agent. The specialist itself persists: it remains available to other authorized people and agents instead of disappearing with the current chat.

Instead of every agent rebuilding the same state through per-session tool calls, Lobu runs a shared data layer:

- Connect once.Polls, webhooks, APIs, and agent-written connectors feed one append-only event log.
- Know once.Events can be indexed as searchable knowledge and linked to typed entities such as companies, projects, incidents, and customers.
- Use from any agent.Authorized MCP clients read and contribute to the same organizational state according to their grants.
- Delegate when useful.Persistent Lobu specialists can own a role, conversation history, tools, and recurring responsibilities.
- Keep control.Identity, source permissions, approvals, credential brokering, provenance, and audit stay server-side.

MCP is for doing. Lobu's event graph is for knowing.

The primitives don't change between a single person's accounts and an entire company's stack — only what's connected does. Identities, entities, events, history, and policy work the same way at either scope.

PERSONAL COMPANY WhatsApp Gmail Calendar Mac Slack GitHub CRM DB \ | | / \ | | / +------+-------+-----+ +------+-----+---+ \ / +------- LOBU -------+ | identities | | entities + events | | history + policy | +---------+----------+ | shared agent context +------------+------------+ | | "When is Alice home?" "Why is Acme at risk?"

1. Add shared context to existing agents

Agents can search and save memory, query structured entities, inspect connected sources, and delegate to Lobu specialists without moving to a new chat interface or adopting Lobu's runtime.

Create a specialist for a durable responsibility: customer research, support triage, release coordination, incident follow-up, or an internal domain. People can talk to it from the Lobu web app or Slack, while other agents can call the same specialist over MCP.

npx @lobu/cli@latest init my-specialist cd my-specialist npx @lobu/cli@latest run npx @lobu/cli@latest chat -c local "hello"

lobu runstarts the local stack with an embedded Postgres database by default and opens the web UI on:8787. It applies the project'slobu.config.tsautomatically only in embedded mode. To use external Postgres, setDATABASE_URL, ensure pgvector is available, then authenticate and apply the project to that runtime separately.

3. Build with the CLI and TypeScript SDK

The same governed data and operations are available without an agent:

npx @lobu/cli@latest memory run # list the memory tools npx @lobu/cli@latest memory run search_memory '{"query":"onboarding"}' npx @lobu/cli@latest memory exec \ 'export default async (_ctx, client) => client.entities.list({ limit: 5 })'

import { client, searchMemory } from "@lobu/client"; client.setConfig({ baseUrl: "https://lobu.ai", headers: { Authorization: Bearer ${process.env.LOBU_TOKEN} }, }); const hits = await searchMemory({ path: { orgSlug: "my-org" }, body: { query: "onboarding" }, });

Mint a token withlobu token create. The MCP tools and typed SDK operations share the server-side tool registry and access rules;lobu memory runandlobu memory execdispatch through the MCP endpoint.

Typed entities connect that history to the things you care about:Company,Project,Customer,Incident, or schemas you define. Corrections supersede old facts rather than erasing their provenance.

Connectors are extensible. You can build them in TypeScript, and coding agents can use Lobu's connector contract and validation flow to create integrations for sources Lobu does not ship with.

A Lobu specialist has a stable role, instructions, memory, tools, and conversation history. It can be reached from web chat or Slack and called by external agents throughclient.conversations.send.

Specialists use role files for identity and instructions:IDENTITY.md,SOUL.md, andUSER.md. Guardrails can inspect input, output, and tool calls. Destructive MCP calls require in-thread approval unless they are explicitly pre-approved throughdefineAgent({ tools: { preApproved } })inlobu.config.ts; action results return to the shared event log.

External agents do not ask users to write delegation code. They pass scripts like these to Lobu'squery_sdkandrun_sdkMCP tools:

// Discover specialists through query_sdk. export default async (_ctx, client) => { const { agents } = await client.agents.list(); return agents; };

// Delegate through run_sdk and wait for the specialist's reply. export default async (_ctx, client) => { return client.conversations.send({ agent_id: "customer-researcher", thread: "enterprise-onboarding", text: "Review the latest customer feedback and propose the next three interviews.", }); };

Automations are versioned background responsibilities activated manually, on a schedule, by a connector event, or by another Automation's durable output. They read governed sources, persist structured results, and can notify Slack, open a ticket, or start agent work while nobody is in chat.

Shared context and delegation over MCP do not require Lobu to execute code for the calling agent. When a Lobu specialist needs a shell, the built-in runtime provides lightweightjust-bashexecution. Remote sandbox providers such as Vercel Sandbox can be connected for workloads that need stronger isolation or more compute.

Which sandbox runs the code is a deployment choice. Lobu provides the shared context, permissions, and governance around it.

- Agent frameworkshelp developers implement an agent loop. Lobu gives agents and people a shared organizational state and a place to keep persistent specialists.
- Direct MCP integrationsexpose tools from one provider. Lobu continuously builds durable, cross-source context that every authorized agent can reuse.
- Agent runtimeshost a particular agent. Lobu lets people keep using Claude Code, Codex, ChatGPT, or their own runtime and add Lobu only where shared context or delegation is useful.
- Workflow enginesencode a graph of predetermined steps. Lobu Automations handle durable triggers and background responsibilities, while agents decide how to complete open-ended work.

Runtime configuration is managed through the web app or the same org-scoped REST API used by the CLI. Locallobu.config.tsprojects support validation and repeatable apply workflows.

npx @lobu/cli@latest login npx @lobu/cli@latest org set my-org npx @lobu/cli@latest agent list

Permissions and audit stay on Lobu's gateway. Lobu MCP servers and the credential-brokering layer handle provider and connector credentials, OAuth and token refresh, and third-party API proxying. Workers receive scoped placeholders or short-lived provider-derived access, never OAuth tokens or durable stored credentials. Destructive MCP calls require in-thread approval unless explicitly pre-approved, and connected data remains organization-scoped.

The built-injust-bashand embedded execution modes are policy and convenience boundaries, not VMs for hostile code. Use a remote sandbox provider when the workload needs a stronger isolation boundary.

We are working with technical teams that already use Claude Code, Codex, ChatGPT, or custom agents and want those agents to share company context or delegate to persistent specialists.

Atlaso is a memory layer for AI tools — connect once and it automatically recalls the context that matters across Claude Code, Cursor, Codex, and every AI tool you use.

Privacy-first local memory vault every AI shares over MCP. Markdown + SQLite on your machine; Claude, ChatGPT, Cursor, and any MCP client read and write it live. No cloud, no account, no telemetry.

Cross-vendor AI memory over MCP. One semantic memory store, readable and writeable from every MCP client — Claude, ChatGPT, Cursor, Windsurf, Zed, Kimi.

Generate random word pairs for the Imposter party game directly via Claude or Cursor. Let AI host your next social deduction game!

You decide what Claude remembers about you. LocalKeep is a personal timeline you curate—titled, dated, editable banks on your machine—then Claude looks them up via MCP instead of inventing uneditable cloud memory.

Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.

Persistent project context for AI coding agents: captures decisions, rationale, and rejected paths so agents stay consistent across Claude, Cursor, Codex, and any MCP enabled platform.

Private persistent memory for Claude, ChatGPT & Gemini via MCP — semantic search, zero-code setup.

Turn LinkedIn saved posts into a queryable knowledge base you can search, chat with, and connect to Claude or ChatGPT through MCP.