diff --git a/packages/ai/README.md b/packages/ai/README.md
index 829bb567..b1b2230a 100644
--- a/packages/ai/README.md
+++ b/packages/ai/README.md
@@ -1,6 +1,6 @@
 # `launchdarkly-ai-python`
 
-Convenience barrel package for the LaunchDarkly AI Python SDK. Re-exports the complete public API of [`launchdarkly-ai-server`](../client/README.md) — install this instead of `launchdarkly-ai-server` for the simplest setup.
+Convenience barrel package for the LaunchDarkly AI Python SDK. Re-exports the complete public API of [`launchdarkly-ai-server`](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md) — install this instead of `launchdarkly-ai-server` for the simplest setup.
 
 ## Installation
 
@@ -40,7 +40,7 @@ asyncio.run(main())
 
 ## `inspect_config(key, context)`
 
-Reads an AI Config flag variation **without invoking any AI provider**. Re-exported from `launchdarkly-ai-server` — see the [full reference there](../client/README.md#inspect_configkey-context).
+Reads an AI Config flag variation **without invoking any AI provider**. Re-exported from `launchdarkly-ai-server` — see the [full reference there](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md#inspect_configkey-context).
 
 ```python
 from launchdarkly_ai_python import inspect_config
@@ -73,8 +73,8 @@ result = await evals.run(
 )
 ```
 
-`LD_API_TOKEN` is required. Configure `LD_SDK_KEY` — or initialize your own client with `init_client(client=...)` — to emit one `$ld:ai:offline-evals:generation` event per generated row, plus one `$ld:ai:offline-evals:criterion` event per `(row, criterion)` when `criteria` are supplied, through the standard SDK event transport. The SDK reports scores; LaunchDarkly rules on them at ingest. A judge served by a different provider than `generation` needs a handler for it in `judge_handlers`. Each row's tool calls are recorded during generation and rendered into the judge's `{{message_history}}`, between the row input and the generated output, so a rubric can grade the tool trajectory as well as the final answer. Use `LD_API_BASE_URI` for staging or local management API traffic; it is separate from the SDK delivery setting `LD_BASE_URI`. Evaluation-run links use the explicit `ui_base_uri` option or `LD_UI_BASE_URI`, defaulting to `https://app.launchdarkly.com`; set it when the project is not in production, or a run created elsewhere still links to the production app. See the [core evaluations guide](../client/README.md#run-an-evaluation-from-code).
+`LD_API_TOKEN` is required. Configure `LD_SDK_KEY` — or initialize your own client with `init_client(client=...)` — to emit one `$ld:ai:offline-evals:generation` event per generated row, plus one `$ld:ai:offline-evals:criterion` event per `(row, criterion)` when `criteria` are supplied, through the standard SDK event transport. The SDK reports scores; LaunchDarkly rules on them at ingest. A judge served by a different provider than `generation` needs a handler for it in `judge_handlers`. Each row's tool calls are recorded during generation and rendered into the judge's `{{message_history}}`, between the row input and the generated output, so a rubric can grade the tool trajectory as well as the final answer. Use `LD_API_BASE_URI` for staging or local management API traffic; it is separate from the SDK delivery setting `LD_BASE_URI`. Evaluation-run links use the explicit `ui_base_uri` option or `LD_UI_BASE_URI`, defaulting to `https://app.launchdarkly.com`; set it when the project is not in production, or a run created elsewhere still links to the production app. See the [core evaluations guide](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md#run-an-evaluation-from-code).
 
 ---
 
-All exports, types, and behaviors are identical to `launchdarkly-ai-server`. See the [core client README](../client/README.md) for the full API reference.
+All exports, types, and behaviors are identical to `launchdarkly-ai-server`. See the [core client README](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md) for the full API reference.
diff --git a/packages/claude-agents/README.md b/packages/claude-agents/README.md
index 09578fbf..0e9f2137 100644
--- a/packages/claude-agents/README.md
+++ b/packages/claude-agents/README.md
@@ -55,7 +55,7 @@ asyncio.run(main())
 
 ### Agent graphs — `claude_graph()`
 
-Runs a LaunchDarkly agent graph with the Claude agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_claude_agents_handler()]`. See the [core client docs](../client/README.md#graphkey-options) for the full `graph()` API.
+Runs a LaunchDarkly agent graph with the Claude agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_claude_agents_handler()]`. See the [core client docs](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md#graphkey-options) for the full `graph()` API.
 
 ```python
 import asyncio
diff --git a/packages/client/README.md b/packages/client/README.md
index b2607d4e..b752af4f 100644
--- a/packages/client/README.md
+++ b/packages/client/README.md
@@ -4,7 +4,7 @@ The core package for the LaunchDarkly AI Python SDK. It owns the LaunchDarkly cl
 
 All handler packages (`launchdarkly-ai-*`) depend on this package.
 
-> **Tip:** for the simplest install, use [`launchdarkly-ai-python`](../ai/README.md) instead. It re-exports this package's full API and is the recommended default for most applications.
+> **Tip:** for the simplest install, use [`launchdarkly-ai-python`](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/ai/README.md) instead. It re-exports this package's full API and is the recommended default for most applications.
 
 ## Installation
 
diff --git a/packages/langchain-agents/README.md b/packages/langchain-agents/README.md
index 71599fed..bb97f015 100644
--- a/packages/langchain-agents/README.md
+++ b/packages/langchain-agents/README.md
@@ -81,7 +81,7 @@ asyncio.run(main())
 
 ### Agent graphs — `langchain_graph()`
 
-Runs a LaunchDarkly agent graph with the LangChain agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_langchain_agents_handler()]`. See the [core client docs](../client/README.md#graphkey-options) for the full `graph()` API.
+Runs a LaunchDarkly agent graph with the LangChain agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_langchain_agents_handler()]`. See the [core client docs](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md#graphkey-options) for the full `graph()` API.
 
 ```python
 import asyncio
diff --git a/packages/openai-agents/README.md b/packages/openai-agents/README.md
index 70fb27b1..3ad77e6e 100644
--- a/packages/openai-agents/README.md
+++ b/packages/openai-agents/README.md
@@ -55,7 +55,7 @@ asyncio.run(main())
 
 ### Agent graphs — `openai_graph()`
 
-Runs a LaunchDarkly agent graph with the OpenAI agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_openai_agent_handler()]`. See the [core client docs](../client/README.md#graphkey-options) for the full `graph()` API.
+Runs a LaunchDarkly agent graph with the OpenAI agent handler pre-bound. Equivalent to calling the base `graph()` with `handlers=[create_openai_agent_handler()]`. See the [core client docs](https://github.com/launchdarkly/python-ai-sdk/blob/main/packages/client/README.md#graphkey-options) for the full `graph()` API.
 
 ```python
 import asyncio