Running Agents Feather DB ā Living Context Engine šŖ¶ Search and explore AI product intel with semantic graph queries
view post Post 243 We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) ā 500 questions across real multi-session conversations, up to 115K tokens each.**Score: 0.693** Ā· GPT-4o full-context baseline: 0.640Full 500-question run with Gemini-Flash: **$2.40**Per-axis breakdown:ā Info-extraction: **0.942**ā Knowledge-update: **0.714**ā Multi-session: **0.606**ā Temporal: **0.477** ā the hard one, Phase 9 addresses thisArchitecture: Hybrid BM25+dense Ā· adaptive temporal decay Ā· embedded (no server) Ā· p50 = 0.19ms Ā· MITpip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results See translation Reply
Sleeping Agents clawID ā AI Asset Watermarking š¾ Invisible & visible watermarking for AI-generated images
Sleeping Agents clawID ā AI Asset Watermarking š¾ Invisible & visible watermarking for AI-generated images
Running Agents Feather DB ā Living Context Engine šŖ¶ Search and explore AI product intel with semantic graph queries