@letta-ai/letta-code 0.6.0 → 0.6.1

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.
Files changed (3) hide show
  1. package/README.md +16 -4
  2. package/letta.js +1122 -941
  3. package/package.json +2 -2
package/README.md CHANGED
@@ -20,10 +20,22 @@ npm install -g @letta-ai/letta-code
20
20
  ```
21
21
  Navigate to your project directory and run `letta` (see various command-line options [on the docs](https://docs.letta.com/letta-code/commands)):
22
22
 
23
- ## Memory and Skill Learning
24
-
25
- All agents in Letta are **stateful**: they maintain context forever and can self-edit their own [memory blocks](https://www.letta.com/blog/memory-blocks).
26
-
23
+ ## Philosophy
24
+ Letta Code is built around long-lived agents that persist across sessions and improve with use. Rather than working in independent sessions, each session is tied to a persisted agent that learns.
25
+
26
+ **Claude Code / Codex / Gemini CLI** (Session-Based)
27
+ - Sessions are independent
28
+ - No learning between sessions
29
+ - Context = messages in the current session + `AGENTS.md`
30
+ - Relationship: Every conversation is like meeting a new contractor
31
+
32
+ **Letta Code** (Agent-Based)
33
+ - Same agent across sessions
34
+ - Persistent memory and learning over time
35
+ - `/clear` resets the session (clears current in-context messages), but memory persists
36
+ - Relationship: Like having a coworker or mentee that learns and remembers
37
+
38
+ ## Agent Memory & Learning
27
39
  If you’re using Letta Code for the first time, you will likely want to run the `/init` command to initialize the agent’s memory system:
28
40
  ```bash
29
41
  > /init