Blog

Notes on GitDB, agent-to-agent workflows, and building a database for the AI-coding era.

  • 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.

  • 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.

  • 5 min read

    Engineers leave. Source code shouldn't.

    A look at real, documented cases where departing engineers walked out with the codebase — and what GitDB does to make that materially harder.

  • 6 min read

    GitDB vs GitHub Enterprise — what each is for

    GitHub has been built for human developers for over 15 years. GitDB has been built for AI agents from day one. Both are correct designs — for different actors. A look at what each one fits.

  • 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

    Why robots forget, and what I'm doing about it

    An honest look at the on-device data problem facing humanoid robots and self-driving stacks — and the embedded engine I built to fix it.

  • 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.

  • 5 min read

    How GitDB cut our AI coding bill by 95%

    A walk-through of the actual token math — where the savings come from, what they don't help with, and how I'd reproduce them in your codebase.

  • 5 min read

    A real day with an agent swarm on GitDB

    A walk-through of four coding agents shipping a feature in parallel — what each one did, where they handed off, and what the bill looked like.

  • 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.

  • 6 min read

    Agent-to-Agent workflows in GitDB

    How GitDB coordinates multi-agent code workflows without ever putting source on a developer machine — and why a database, not a filesystem, is the right substrate for it.

  • 6 min read

    What GitDB is, and why I built it

    AI coding agents spend 60–80% of their tokens just finding things in the codebase. That's grep hell. Here's what we built underneath instead.