4 Commits

Author	SHA1	Message	Date
Claude	6a1255dfdb	feat: LLM router with local (Ollama) and cloud (OpenAI) backends ... - lyra.config.load() reads env into a frozen Config dataclass - lyra.llm.complete(messages, backend) routes to Ollama /api/chat or OpenAI chat completions - lyra.llm.embed(texts) calls OpenAI embeddings - .env.example switched from Anthropic to OpenAI to match available key	2026-05-16 06:10:48 +00:00
Claude	b2523c2561	chore: project scaffold (uv, .env.example, README, lyra package)	2026-05-16 06:01:08 +00:00
Claude	faf4e8a1aa	chore: nuke legacy code, keep design docs for restart ... Preserved on the archive branch. Keeping only the architecture and design thinking that survives the rewrite: - docs/ARCH_v0-6-1.md (Inner Self / Executive / Chat / Persona model) - docs/ARCHITECTURE_v0-6-0.md (predecessor architecture) - docs/PROJECT_SUMMARY.md (project history and rationale) - docs/PROJECT_LYRA_COMPLETE_BREAKDOWN.md (detailed design notes) - docs/ENVIRONMENT_VARIABLES.md (multi-backend env conventions) - docs/LLMS.md - docs/TRILLIUM_API.md (for future tool integration) Removed: all service code (cortex, core/relay, neomem, rag, sandbox, persona-sidecar), docker-compose, migration/logging docs, stale root test scripts, CHANGELOG.	2026-05-16 05:57:07 +00:00
claude	a5f3e0248a	env cleanup round 2	2025-11-26 03:18:15 -05:00