@letta-ai/letta-code 0.5.1 → 0.5.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -166,17 +166,82 @@ letta --agent <id> --unlink # Remove Letta Code tools from agent, then start
166
166
  #### Interactive Commands
167
167
 
168
168
  While in a session, you can use these commands:
169
+
170
+ **Agent Management:**
169
171
  - `/agent` - Show current agent link
170
- - `/model` - Switch models
171
- - `/toolset` - Switch toolsets (codex/default)
172
+ - `/swap` - Switch to a different agent (prompts with agent selector)
172
173
  - `/rename` - Rename the current agent
174
+ - `/download` - Download agent file locally (exports agent configuration as JSON)
175
+
176
+ **Configuration:**
177
+ - `/model` - Switch models (prompts with model selector)
178
+ - `/toolset` - Switch toolsets (codex/default/gemini)
179
+ - `/system` - Switch system prompt (change agent behavior preset)
173
180
  - `/stream` - Toggle token streaming on/off
181
+
182
+ **Tools & Memory:**
174
183
  - `/link` - Attach Letta Code tools to current agent (enables Read, Write, Edit, Bash, etc.)
175
184
  - `/unlink` - Remove Letta Code tools from current agent
185
+ - `/init` - Initialize agent memory for this project (guides agent to organize memory blocks based on current context)
186
+
187
+ **Skills:**
188
+ - `/skill` - Enter skill creation mode (optionally: `/skill <description>`)
189
+
190
+ **Background Processes:**
191
+ - `/bashes` - Show background shell processes (displays shells started with `run_in_background=true`)
192
+
193
+ **Session Management:**
176
194
  - `/clear` - Clear conversation history
177
195
  - `/exit` - Exit and show session stats
178
196
  - `/logout` - Clear credentials and exit
179
197
 
198
+ #### Background Shell Processes
199
+
200
+ When running long-running commands (like dev servers, test watchers, or builds), the agent can use `run_in_background=true` with the Bash tool. Use `/bashes` to view all background processes:
201
+
202
+ ```bash
203
+ /bashes # Shows running background shells with their IDs and commands
204
+ ```
205
+
206
+ The agent can monitor background process output using the `BashOutput` tool and terminate them with `KillBash`.
207
+
208
+ #### Memory Initialization
209
+
210
+ The `/init` command helps the agent organize its memory blocks based on your project context:
211
+
212
+ ```bash
213
+ /init # Guides agent to analyze project and structure its memory
214
+ ```
215
+
216
+ This is useful when:
217
+ - Starting fresh in a new project
218
+ - Reorganizing an existing agent's memory structure
219
+ - After sharing project documentation (like AGENTS.md or README)
220
+
221
+ The agent will analyze available context and create/update memory blocks like:
222
+ - **`project`** - Build commands, architecture, conventions
223
+ - **`human`** - Your coding preferences and communication style
224
+ - **`ticket`/`context`** - Current task or debugging context
225
+
226
+ See [Memory Configuration](#memory-configuration) for more details on memory blocks.
227
+
228
+ #### Skill Creation
229
+
230
+ The `/skill` command enters an interactive mode for creating new skills:
231
+
232
+ ```bash
233
+ /skill # Enter skill creation mode
234
+ /skill "Python testing helper" # Start with a description
235
+ ```
236
+
237
+ Skills are modular packages that extend Letta Code with specialized knowledge or workflows. The agent will guide you through:
238
+ 1. Defining the skill's purpose and scope
239
+ 2. Creating the skill structure (SKILL.md + optional resources)
240
+ 3. Writing effective instructions and bundled scripts
241
+ 4. Validating and packaging the skill
242
+
243
+ Created skills are saved to your `.skills` directory and automatically discovered on next session.
244
+
180
245
  #### Managing Letta Code Tools
181
246
 
182
247
  Letta Code provides tools like `Bash`, `Read`, `Write`, `Edit`, `Grep`, `Glob`, and more. You can attach or remove these tools from any agent:
@@ -328,6 +393,28 @@ Permissions are also configured in `.letta/settings.json`:
328
393
  }
329
394
  ```
330
395
 
396
+ ## Updates
397
+
398
+ Letta Code automatically checks for updates on startup and installs them in the background.
399
+
400
+ ### Auto updates
401
+
402
+ * **Update checks**: Performed on startup
403
+ * **Update process**: Downloads and installs automatically in the background
404
+ * **Applying updates**: Updates take effect the next time you start Letta Code
405
+
406
+ **Disable auto-updates:**
407
+ Set the `DISABLE_AUTOUPDATER` environment variable in your shell:
408
+ ```bash
409
+ export DISABLE_AUTOUPDATER=1
410
+ ```
411
+
412
+ ### Update manually
413
+
414
+ ```bash
415
+ letta update
416
+ ```
417
+
331
418
  ## Self-hosting
332
419
 
333
420
  To use Letta Code with a self-hosted server, set `LETTA_BASE_URL` to your server IP, e.g. `export LETTA_BASE_URL="http://localhost:8283"`.