Migrate to Pleach

Migration guides for the four most common starting points — AI SDK, LangChain, Anthropic Enterprise, OpenAI Enterprise.

Pleach composes underneath what you have today. The four migration guides below cover the most common starting points; each is structured the same way:

When to migrate, when not to — concrete signals.
What maps cleanly — the parts that translate 1:1.
What doesn't — the parts that change shape.
The minimum-viable migration — smallest diff that gets you to a working SessionRuntime.
What you keep — provider, enterprise contract, custom tools, existing UI.

You can stop at any step. The runtime works with a single provider, no plugins, no audit adapter, no checkpointer. Add capabilities as you need them.

From an LLM SDK or framework

Migrating from the Vercel AI SDK

Move from `streamText` + `useChat` to a `SessionRuntime`. Keep the AI SDK as your provider via `AiSdkProvider` — what changes is what wraps it.

Migrating from LangChain / LangGraph

Map `Runnable` chains and `StateGraph` checkpointers to Pleach's channel-and-graph substrate. Or bridge both worlds with `@pleach/langchain` instead of migrating.

From an enterprise vendor contract

You don't replace the contract — Pleach runs underneath it. SSO, ZDR, Workspaces / Projects, dedicated capacity, prompt caching, and snapshot pinning stay where they are. What Pleach adds: a hash-chained AuditableCall row in your own Postgres, per-axis cost rollup inside one Workspace, and replay determinism across snapshots.

Migrating from Anthropic Enterprise

Keep SSO, ZDR, Workspaces, the Admin API. The three downstream walls the contract doesn't cover, and how the AuditableCall row closes each one.

Migrating from OpenAI Enterprise

Keep SSO/SCIM, ZDR, Projects, the Usage API. The three downstream walls the contract doesn't cover, and how the AuditableCall row closes each one.

Compose, don't migrate

Sometimes the right call is to bridge, not migrate. The pages below cover the major composition patterns:

With the Anthropic SDK

`AnthropicSdkProvider` wraps `@anthropic-ai/sdk` directly — native prompt caching, extended thinking, beta flags pass through.

With the OpenAI SDK

Wire OpenAI's SDK through `AiSdkProvider` (`@ai-sdk/openai`) or implement `AgentProvider` directly.

With Mastra

Pleach as the audit + replay layer under Mastra's workflow-shaped agents.

With Inngest

Durable workflow orchestration under Pleach — `Inngest.send()` from inside a tool, audit-row-keyed by `turnId`.

@pleach/langchain

Bidirectional adapter — Pleach tools as `Runnable`s, LangChain tools as `UnifiedToolDefinition`s. Stay in both worlds.

MCP integration

Expose `@pleach/core` sessions over Model Context Protocol via `@pleach/mcp` — Claude Desktop, Continue, Zed clients.

Version migrations (`0.x` → future `1.0`)

Every shipping @pleach/* package is at 0.1.0 today under FSL-1.1-Apache-2.0. The 0.1.x → 1.0.0 jump is non-caretable — pin exactly. When the 1.0 cut lands, this page will host the codemod + per-SKU upgrade guide. See versioning for the current policy.

Not seeing your starting point?

The migration guides above are the most-asked patterns. If you're coming from a less common shape — CrewAI, AutoGen, LlamaIndex Workflows, OpenHands, Goose — the comparison page maps the capability overlaps row by row, and the getting-started path takes ~5 minutes regardless of starting point.

If a missing migration guide would actually move the needle for your project, open an issue on the @pleach/core repo — migration content is operator-prioritized, not speculatively written.