AgapHost

Files

alvis d9668928c0 Hindsight: route consolidation/reflect to local gemma3:4b (kb#88) + rationale

Per-stage LLM routing so Hindsight's high-volume background jobs stop burning
the rate-limited Kimi subscription:
- CONSOLIDATION + REFLECT -> ollama/gemma3:4b via LiteLLM :4000 (local GPU, free)
- RETAIN (fact extraction) stays on Kimi (hindsight-llm) for quality
Fixes the Kimi 5h window maxing at 100% from ~1100 background calls/3h (dropped
to ~38%). Documents the reasoning in HINDSIGHT-MIGRATION.md section 10:
frequent/mechanical/background stages -> cheap local model; user-facing,
quality-critical, low-volume -> Kimi.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014t8Qg9gi7H7HtT8MncoXAB

2026-07-16 20:30:35 +00:00

adolf-llm

Adolf memory: migrate Cognee -> Hindsight + Kimi quota tooling

2026-07-15 19:53:21 +00:00

cognee

[Adolf] Swap cognee embedding to bge-m3 (1024-d, multilingual)

2026-07-06 05:56:58 +00:00

cognee-llm

cognee-llm: correct docs — it IS cognee's LLM backbone (Kimi path)

2026-07-05 13:19:18 +00:00

hindsight-llm

Adolf: decommission Cognee (H4) + standalone hindsight-llm + vault access