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
| Integration | Best for | Status | Docs |
|---|---|---|---|
| Claude Code | MCP tools, memory skill, lifecycle hooks, and local runtime management. | Published; cloud planned. | Overview · Local |
| Codex | MCP tools plus a memory protocol skill for task-start recall and handoffs. | Manual; packaged plugin planned. | Overview · Local |
| OpenClaw | Plugin and skill bundle for cross-channel agent memory. | Source-only; cloud planned. | Overview · Local |
| Hermes Agent | Native Python memory provider with prefetch, turn sync, and explicit tools. | Source-only; cloud planned. | Overview · Local |
| Cursor | Published MCP server plus Cursor rules for durable memory behavior. | Manual; packaged plugin planned. | Overview · Local |
Frameworks
| Integration | Best for | Status | Docs |
|---|---|---|---|
| Vercel AI SDK | Pre-call retrieval and post-call ingest around generateText / streamText. | Published; cloud planned. | Overview · Local |
| OpenAI Agents SDK | Memory-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 |
| Mastra | Planned Mastra memory adapter. | Planned. | Overview · Local |
Shared memory surface
Most coding-agent integrations use the shared MCP server from atomicmemory-integrations:
| Tool | Purpose |
|---|---|
memory_search | Search durable memory by meaning. |
memory_ingest | Store durable facts, decisions, preferences, or exact session snapshots. |
memory_package | Build a token-budgeted context package. |
memory_list | Inspect 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.