Alvis 1718d70203 Fix system prompt: agent now correctly handles memory requests ...

- Tell agent that memory is saved automatically after every reply
- Instruct agent to never say it cannot store information
- Instruct agent to acknowledge and confirm when user asks to remember something
- Fix misleading startup log (gemma3:1b → qwen2.5:1.5b)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-02-23 05:22:08 +00:00

openmemory

Switch extraction model to qwen2.5:1.5b, fix mem0migrations dims, update tests

2026-02-23 05:11:29 +00:00

agent.py

Fix system prompt: agent now correctly handles memory requests

2026-02-23 05:22:08 +00:00

ARCHITECTURE.md

Add Adolf architecture doc and integration test script

2026-02-23 04:52:40 +00:00

potential-directions.md

Switch extraction model to qwen2.5:1.5b, fix mem0migrations dims, update tests

2026-02-23 05:11:29 +00:00

test_pipeline.py

Switch extraction model to qwen2.5:1.5b, fix mem0migrations dims, update tests

2026-02-23 05:11:29 +00:00

Description

Persistent AI assistant (Telegram, GPU, memory)

493 KiB

Languages

Python 98.9%

JavaScript 0.7%

Dockerfile 0.4%