Letta Server (self-hosted) doesn't run on local machine. (exit with error on launch attempt)

[farzbood]

Describe the bug
The letta server command exit with error when attempt to run the self-hosted (installed with uv)
The sreenshots of error(s) plus local/dev environment + PostgreSQL 18 setup with pgvector 0.8.1 installed, attached.
Please describe your setup

• How are you running Letta?
  • pip (legacy) (via uv add)
  • Desktop (ADE installed)
• Describe your setup
  • What's your OS (Windows/MacOS/Linux)? Win10 x86_64
  • What is your docker run ... command (if applicable) N/A

Screenshots
If applicable, add screenshots to help explain your problem.
LETTA_PG_URI=postgresql+asyncpg://letta_selfhosted:letta2025@localhost:5432/letta_selfhosted
dev (.venv) environment and error (3 shots)

PostgreSQL setup (1 shot)

Additional context
Add any other context about the problem here.

• What model you are using

Agent File (optional)
Please attach your .af file, as this helps with reproducing issues.

---

If you're not using OpenAI, please provide additional information on your local LLM setup:

Local LLM details

If you are trying to run Letta with local LLMs, please provide the following information:

• The exact model you're trying to use (e.g. dolphin-2.1-mistral-7b.Q6_K.gguf)
• The local LLM backend you are using (web UI? LM Studio?)
• Your hardware for the local LLM backend (local computer? operating system? remote RunPod?)