5 min read
Two ways to run keyes.ai services
The same engine — Vector, Memory, GitDB — runs as a managed service or inside your own cloud account. A short note on what each shape is for, and what's actually built.
Blog
Notes on GitDB, agent-to-agent workflows, and building a database for the AI-coding era.
- 7 min read
What 100% recall could mean for AI search engines
AI-native search is a real category now — Exa alone is a $700M business — and the open technical question is the same one we keep running into. The retrieval layer either finds the right document or it doesn't, and at scale most stacks settle for "approximately".
- 8 min read
What 100% recall could mean for AI customer service agents
AI customer service agents are a real category now — Decagon alone is a $4.5B business — and the most expensive failure mode in production is hallucinating a policy. A lot of that comes down to the retrieval layer.
- 7 min read
What complete recall could mean for AI trading agents
AI is becoming a real participant in trading, and the memory layer has to satisfy two requirements that usually pull against each other — millisecond latency and 100% recall under audit. Here's how UQL approaches that.
- 6 min read
Memory APIs in 2026 — where we fit beside mem0 and Supermemory
Two memory services lead the agent-memory category — mem0 and Supermemory. Both are well-engineered for conversational personalization. Here's where ours sits and where each of theirs is the better choice.
- 7 min read
What 100% recall could mean for legal AI (and other high-stakes memory)
Legal AI tools hallucinate 17–33% of the time per a peer-reviewed Stanford study. A lot of that comes from retrieval, not generation. Here's the memory-layer math, and what we benchmarked.
- 7 min read
Why we don't use brute-force or mmap for 100% recall
The standard paths to 100% vector recall are GPU brute-force and mmap-backed indexes. Both work; both have a property that ruled them out for the workloads we kept seeing. A look at the design space and where we landed.
- 5 min read
Vector databases in 2026 — where we fit beside Pinecone, Qdrant, and Milvus
Three production vector databases dominate the category. A neutral look at what each one does, what we do, and how the trade-offs compare.
- 4 min read
3072-dim is the new hard mode for vector search
text-embedding-3-large produces 3,072-dim vectors, and most vector pipelines truncate them to stay performant. Here's what happened when we benchmarked the full dimension end-to-end.
- 6 min read
100% recall, on disk, no GPU
The conventional wisdom on vector search is that you have to pick two of three — recall, speed, footprint. Here's what our engine does on the dbpedia-openai benchmark.