Skip to main content

Integrations

Agent index: llms.txt

AtomicMemory adds durable memory to coding agents, AI frameworks, and terminal workflows through the same provider-backed memory layer. Choose the host you use, install the local integration, and point it at your AtomicMemory backend.

Coding agents

IntegrationBest forStatusDocs
Claude CodeMCP tools, memory skill, lifecycle hooks, and local runtime management.Published; cloud planned.Overview · Local
CodexMCP tools plus a memory protocol skill for task-start recall and handoffs.Manual; packaged plugin planned.Overview · Local
OpenClawPlugin and skill bundle for cross-channel agent memory.Source-only; cloud planned.Overview · Local
Hermes AgentNative Python memory provider with prefetch, turn sync, and explicit tools.Source-only; cloud planned.Overview · Local
CursorPublished MCP server plus Cursor rules for durable memory behavior.Manual; packaged plugin planned.Overview · Local

Frameworks

IntegrationBest forStatusDocs
Vercel AI SDKPre-call retrieval and post-call ingest around generateText / streamText.Published; cloud planned.Overview · Local
OpenAI Agents SDKMemory-aware run() flows and optional function tools.Published; cloud planned.Overview · Local
LangChain (JS)Planned chat memory and tool wrappers.Planned.Overview · Local
LangGraph (JS)Planned graph-store memory layer next to checkpointers.Planned.Overview · Local
MastraPlanned Mastra memory adapter.Planned.Overview · Local

Shared memory surface

Most coding-agent integrations use the shared MCP server from atomicmemory-integrations:

ToolPurpose
memory_searchSearch durable memory by meaning.
memory_ingestStore durable facts, decisions, preferences, or exact session snapshots.
memory_packageBuild a token-budgeted context package.
memory_listInspect recent scoped memories.

Framework integrations use the TypeScript or Python SDK directly, but keep the same loop: retrieve before the agent acts, ingest after useful work completes, and scope memory by user, agent, namespace, or thread.

Terminal users can use the AtomicMemory CLI for direct search, ingest, profile setup, and hook generation.

Backend choice

Integrations are backend-agnostic. The SDK's MemoryProvider model lets the same integration point at self-hosted atomicmemory-core or another registered provider by configuration.

Contributing

Source lives at atomicstrata/atomicmemory-integrations.