Agents

A working tutorial: install pg-synapse, write a tool, register an LLM profile, create an agent as a row, run it from SQL, attach a reactive trigger. All copy-pasteable.

pg-synapse is a Postgres-native agent loop runtime in Rust. Invoke LLM agents from SQL, with tools that read and write your database under the caller’s grants.

Guided spec conductor: an assertive interview that turns a fuzzy idea, or a pile of existing code, into one agent-ready SPEC.md — by interrogating why, researching what you don’t know, and pulling in other models to attack your reasoning.

Postgres-native agent-loop runtime in Rust. Invoke an LLM agent and its tool dispatch from SQL like a stored procedure — the agent reads and writes your tables directly, with a small trait-based kernel and everything else as a plugin.

TDD/spec planner that turns product intent into small, deterministic Bob campaigns — one observable behavior per slice, with the verify command and scope caps frozen up front.

Autonomous build → verify → judge loop. Bob drives a coding CLI in an isolated git worktree, gates the result on your own test command, and only applies the change once it converges.

A library of opinionated Claude Code skills, rules, agents, and slash commands that turn an AI coding session into an actual workflow — scope before planning, research before content, tests before claims, evidence before opinions.

Multi-model LLM debate and second-opinion validation. Broadcasts a prompt to several models — HTTP providers or local CLIs — has them argue over N rounds, and returns a synthesized answer plus an agreement/disagreement report.

The practical follow-up to the goldfish-memory post. Bring a Postgres database with pgvector and an agent that talks to users; an hour later you’ve got two-tier memory bolted on. Staging, realtime and consolidate cells, three scheduling options, three reader patterns, and an LLM fact extractor — Python and Rust both.

Agent memory has two completely different jobs — fast context for the next reply, and curated truth three weeks later — and most people try to do both with one tool. Here’s the two-tier pattern I built chunkshop’s memory layer around, the late-event bug that silently eats conversations, and why ‘just use pgvector’ isn’t the whole answer.