claude-configs/skills/cognitive-memory
Cal Corum 4770c15429 Add --if-changed flag to embed, configurable Ollama model, hourly timer
- embed --if-changed compares memory ID sets to skip when unchanged
- --ollama-model config flag to switch models without code changes
- _ollama_embed now accepts model param, respects config throughout
- Switched default to qwen3-embedding:8b (70+ MTEB vs nomic's ~52)
- Hourly systemd timer for embedding, daily timer no longer embeds
- Fixed PATH for uv in both systemd services

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 14:54:21 -06:00
..
client.py Add --if-changed flag to embed, configurable Ollama model, hourly timer 2026-02-19 14:54:21 -06:00
feature.json Cognitive Memory v3.0: rich edges, hybrid embeddings, MCP server 2026-02-19 14:11:18 -06:00
mcp_server.py Cognitive Memory v3.0: rich edges, hybrid embeddings, MCP server 2026-02-19 14:11:18 -06:00
migrate.py Add new skills, commands, scripts; update Paper Dynasty workflows 2026-02-13 14:10:21 -06:00
PROJECT_PLAN.json Add new skills, commands, scripts; update Paper Dynasty workflows 2026-02-13 14:10:21 -06:00
SCHEMA.md Cognitive Memory v3.0: rich edges, hybrid embeddings, MCP server 2026-02-19 14:11:18 -06:00
SKILL.md Cognitive Memory v3.0: rich edges, hybrid embeddings, MCP server 2026-02-19 14:11:18 -06:00