diff --git a/README.md b/README.md
index 7480a7c..ac3ab5a 100644
--- a/README.md
+++ b/README.md
@@ -58,7 +58,7 @@ Provider backends are the model-facing boundary; the agent loop is independent o
 
 Tool execution uses the configured Landlock/landrun sandbox. Operations requiring an approved escape use the bypass namespace and broker, which applies policy and approval controls rather than providing an unrestricted escape.
 
-Persistent memory is provided by OptMem through `memory_recall` and `memory_remember`; Ollie does not maintain a second memory-file format. History management renders context, tracks usage and cost, caps oversized tool output, and compacts older material when necessary.
+Persistent memory is provided by [OptMem](https://github.com/VictorTaelin/OptMem) through `memory_recall` and `memory_remember`; Ollie does not maintain a second memory-file format. History management renders context, tracks usage and cost, caps oversized tool output, and compacts older material when necessary.
 
 ## Frontends
 
diff --git a/doc/architecture.md b/doc/architecture.md
index 2ee94d1..aec8057 100644
--- a/doc/architecture.md
+++ b/doc/architecture.md
@@ -68,7 +68,7 @@ Remote execution does not replicate the agent runtime or introduce a second RPC
 
 ### No competing memory store
 
-Persistent memory is owned by OptMem. Ollie exposes memory through tools rather than maintaining a second memory database or synchronization layer.
+Persistent memory is owned by [OptMem](https://github.com/VictorTaelin/OptMem). Ollie exposes memory through tools rather than maintaining a second memory database or synchronization layer.
 
 These omissions are deliberate composition choices, not missing extension points. New behavior should first be expressed as a tool, a 9P file operation, a session, or a shell workflow before adding a new runtime subsystem.
 
@@ -86,7 +86,7 @@ The architecture is split by responsibility:
 
 ## Configuration and data
 
-Installed runtime data includes backend configuration, agent definitions, prompt templates, skills, and tool executables. Backend credentials, endpoints, models, and compaction models are configured in `backends.conf`. Runtime paths follow XDG configuration and data locations. OptMem owns persistent memory storage; memory tools call it directly.
+Installed runtime data includes backend configuration, agent definitions, prompt templates, skills, and tool executables. Backend credentials, endpoints, models, and compaction models are configured in `backends.conf`. Runtime paths follow XDG configuration and data locations. [OptMem](https://github.com/VictorTaelin/OptMem) owns persistent memory storage; memory tools call it directly.
 
 ## Multi-agent operation
 
diff --git a/doc/evolution.md b/doc/evolution.md
index c6b752d..9caf31b 100644
--- a/doc/evolution.md
+++ b/doc/evolution.md
@@ -12,7 +12,7 @@ This made the control plane protocol-agnostic. A shell, editor, GUI, or another
 
 The tool design went through external MCP servers, scripts, and a single built-in execution path. The current design keeps tools outside the agent loop in `toolsrv`, a separate 9P process. Executables describe themselves with metadata, and the registry discovers and loads them lazily.
 
-This removed built-in-tool and prompt-bloat pressure. File, code-intelligence, memory, reasoning, and web capabilities use the same external-tool boundary. OptMem became the owner of persistent memory rather than Ollie maintaining a competing memory directory.
+This removed built-in-tool and prompt-bloat pressure. File, code-intelligence, memory, reasoning, and web capabilities use the same external-tool boundary. [OptMem](https://github.com/VictorTaelin/OptMem) became the owner of persistent memory rather than Ollie maintaining a competing memory directory.
 
 ## 3. Planning became session state