serversdown
f3530cf4ae
Mid-size models (gpt-4o-mini, qwen2.5-14b) resist persona instructions — help-desk closers and feelings-disclaimers leak through regardless. Route live chat to a stronger model while keeping bulk consolidation cheap: - config: CHAT_MODEL (default gpt-4o), distinct from CLOUD_MODEL (gpt-4o-mini) - llm.complete gains a `model` override; chat.respond uses chat_model on cloud, consolidation paths keep cloud_model - persona: reword the "no sign-off" rule so genuine questions are welcome and only reflexive customer-service closers are discouraged Verified: on gpt-4o she owns her mood without disclaimers and drops most help-desk tails — clearly more in-character than mini/qwen. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Lyra
A persistent, autonomous AI assistant. From-scratch rewrite of an earlier attempt.
The design thinking that survives the rewrite lives in docs/ — start with docs/ARCH_v0-6-1.md. The previous implementation is preserved on the archive branch.
Status
Pre-MVP. Building toward the smallest useful version: chat with persistent memory across sessions.
Setup
uv sync
cp .env.example .env
# fill in ANTHROPIC_API_KEY and point LOCAL_BASE_URL at your Ollama
Architecture
The long-term target is the cognitive split in docs/ARCH_v0-6-1.md — Inner Self as the seat of consciousness, Executive for hard reasoning, Cortex Chat for drafting, Persona for voice. The MVP implements only the chat + memory baseline. Cognitive layers come back one at a time.