You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+5-3Lines changed: 5 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -197,7 +197,8 @@ The tinyMem CLI is your primary way to interact with the system from your termin
197
197
|`run`|**Command Wrapper**| To run a script or tool (like `make` or `npm test`) while "reminding" it of project context. |`tinymem run make build`|
198
198
|`proxy` / `mcp`|**Server Modes**| To start the "brain" that connects tinyMem to your IDE or AI client. |`tinymem mcp`|
199
199
|`doctor`|**Diagnostics**| To fix the system if it stops working or has configuration issues. |`tinymem doctor`|
200
-
|`addContract`|**Agent Setup**| To automatically configure your AI agents to use tinyMem properly. |`tinymem addContract`|
200
+
|`init`|**Project Bootstrap**| Creates `.tinyMem`, writes the config, and installs the correct agent contracts for your model size. |`tinymem init`|
201
+
|`update`|**Refresh**| Re-runs migrations and downloads whichever agent contract matches your configuration. |`tinymem update`|
201
202
202
203
### Writing Memories
203
204
Think of writing memories as "tagging" reality for the AI.
@@ -298,12 +299,13 @@ When tinyMem is running in MCP mode, your AI agent (like Claude or Gemini) gains
298
299
### AI Agent Directives
299
300
**CRITICAL**: If you are building an AI agent, you MUST include the appropriate directive in its system prompt to ensure it uses tinyMem correctly.
300
301
301
-
**Quick Setup:** Run `tinymem addContract`to automatically create these files in your project.
302
+
**Quick Setup:** Run `tinymem init` once to bootstrap `.tinyMem`, create config, and install the correct agent contract for your model size. Use `tinymem update` later to rerun migrations and refresh the contract (it will download the small or large version that your configuration points to).
Copy file name to clipboardExpand all lines: examples/Aider.md
+1-2Lines changed: 1 addition & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -35,7 +35,7 @@ Aider needs to be told to talk to `localhost:8080` instead of the real API.
35
35
aider \
36
36
--openai-api-base http://localhost:8080/v1 \
37
37
--openai-api-key dummy \
38
-
--model openai/qwen2.5-coder# Prefix 'openai/' tells Aider to use generic client
38
+
--model openai/rnj-1# Prefix 'openai/' tells Aider to use generic client
39
39
```
40
40
41
41
> **Critical:** You MUST use the `openai/` prefix for the model name (e.g., `openai/qwen2.5-coder` or `openai/gpt-4`). This forces Aider to use its generic OpenAI client, which respects the custom API base. If you just say `--model gpt-4`, it might try to hit the official OpenAI API directly.
0 commit comments