I built a database for AI agents
Hey HN, I just spent the last few weeks building a database for agents. Over the last year I built PostHog AI, the company's business analyst agent, where we experimented on giving raw SQL access to PostHog databases vs. exposing tools/MCPs. Needless to say, SQL wins. I left PostHog 3 weeks ago to work on side-projects. I wanted to experiment more with SQL+agents. I built an MVP exposing business data through DuckDB + annotated schemas, and ran a benchmark with 11 LLMs (from Kimi 2.5 to Claude Opus 4.6) answering business questions with either 1) per-source MCP access (e.g. one Stripe…
In plain words
This is a database built for AI agents that uses SQL and annotated schemas to help agents query business data from multiple sources. It's designed for developers building AI agents that need to answer business questions across platforms like Stripe and HubSpot. The creator benchmarked it against other approaches and found it achieved significantly higher accuracy while using far fewer tokens and running faster than traditional tool-based methods.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I just spent the last few weeks building a database for agents. Over the last year I built PostHog AI, the company's business analyst agent, where we experimented on giving raw SQL access to PostHog databases vs. exposing tools/MCPs. Needless to say, SQL wins. I left PostHog 3 weeks ago to work on side-projects. I wanted to experiment more with SQL+agents. I built an MVP exposing business data through DuckDB + annotated schemas, and ran a benchmark with 11 LLMs (from Kimi 2.5 to Claude Opus 4.6) answering business questions with either 1) per-source MCP access (e.g. one Stripe MCP, one Hubspot MCP) or 2) my annotated SQL layer. My solution consistently reached 2-3x accuracy (correct vs. incorrect answers), using 16-22x less tokens per correct answer, and being 2-3x faster. Benchmark in the repo! The insight is that tool calls/MCPs/raw APIs force the agent to join information in-context. SQL does that natively. What I have today: - 101 connectors (SaaS APIs, databases, file storages) sync to Parquet via dlt, locally or in your S3/GCS/Azure bucket - DuckDB is the query engine — cross-source JOINs across sources work natively, plus guardrails for safe mutations / reverse ETL - After each sync a Claude agent annotates the schema: table descriptions, column docs, PII flags, relationship maps It works with all major agent frameworks (LangChain, CrewAI, LlamaIndex, Pydantic AI, Mastra), and local agents like Claude Code, Cursor, Codex and OpenClaw. I love dinosaurs and the domain was available, so it's called Dinobase. It's not bug free and I'm here to ask for feedback or major holes in the project I can't see, because the results seem almost too good. Thanks!
Does the same job
all alternatives →
Dreambase Data Agent SkillsApr 2026 · dreambase.com · ▲146Analytical skills for data agents running on Supabase
- DADeepSQL – A self-hostable DBA agent for Postgres and MySQLJul 2026 · deepsql.ai · ▲52
Hi HN - I'm Venkat, founder of Stayflexi (YC), CMU CS grad and Ex-Oracle Query Engine team (patents in core databases) DeepSQL started as an internal tool to stop our own databases from becoming the bottleneck they were becoming (13,000+ hotels in production). It worked well enough that we're releasing it. DeepSQL is an AI agent that operates a database the way a senior DBA and Data Engineer would 1. Fixes slow queries (we cutdown DB spend by 4x) 2. Fixes DB bloat (blocks unnecessary schema changes, in vibecoded setup) 2. BI dashboards(we removed spend on tableau, retool and appsmith) 3.…
Papermark AgentsJun 2026 · papermark.com · ▲143Let AI agents run your next deal, fundraise or data room
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app