traqr.dev·working document·rev. 2026.06

Persistent memory and an agent harness for Claude Code.

TraqrOS is the system I built to run my own projects. A Postgres memory database my agents actually use. A config file that generates the whole development harness. And Guardian, which merges the pull requests those agents ship while I’m asleep. It’s open source, and the pieces install separately — this page shows how each one works.

systemTraqrOS
operatorone developer
statusin production
licenseMIT, open source
clientsClaude Code · Cursor · Codex
protocolMCP
storageyour Postgres 15+
costfree

§ 00·field notes

Live numbers from the instance that runs this site, checked 2026-06-10. No marketing math.

memories in the production database6,588
commits on the monorepo's main branch2,149
most recent merged pull request#1827
apps running on the system10
developers1

§ 01·memory

It remembers what it learned.

Every session, your AI rediscovers your codebase from scratch. TraqrDB is a memory database in your Postgres — agents store what they learn as they work, and load it back before the same mistake happens twice.

fig. 1 — the same gotcha, stored in session 1, recalled in session 47. Real tool calls, replayed.

traqr — install

§ 02·harness

One config file. The rest is generated.

Write .traqr/config.json, run npx traqr render. The CLI generates everything your AI needs to work on the project like it’s been there for months.

.traqr/config.json
{
  "project": {
    "name": "my-saas",
    "type": "code"
  },
  "memory": {
    "supabaseUrl": "...",
    "embeddingProvider": "openai"
  },
  "vcs": "github",
  "skills": ["ship", "einstein"],
  "worktrees": {
    "slots": ["feature1", "bugfix1"]
  }
}
01

CLAUDE.md

The project intelligence file — conventions, app routing, memory triggers, workflow rules. Your AI reads it before touching anything.

02

Slash commands

/ship, /einstein, /bethesda, /daily-brief, /call — 50-odd skills, generated from your config and tuned to your project.

03

Memory MCP server

Twelve tools: store, search, context, browse, enhance, pulse, archive, audit, read, correct, forget, purge.

04

Worktree slots

Parallel branches with port assignments, shell aliases, and a pre-push hook that keeps everyone off main.

05

Guardian

The automated PR lifecycle — rebase, build, merge, sync the other slots, write what it learned back to memory.

06

Obsidian vault

Research docs, agent diaries, decision records, daily briefs. The knowledge that doesn't fit in a commit message.

§ 03·skills

The index.

Skills are slash commands — each one a documented procedure the AI follows. These are the ones I use most; the full set is generated from your config.

shipmove code from slot to main5
/shipcommit, build, push, open the PR, notify Slack
/resyncpre-flight rebase with impact analysis
/syncsync every worktree slot after a merge
/simplifyreview changed code for reuse and efficiency
/nextphasepick up the next phase of a Linear project
researchunderstand before building4
/einsteindeep research with parallel subagent waves
/bethesdaautonomous exploration — agents find their own work
/debatestructured devil's advocacy on a decision
/deepreflectmeta-analysis of how the agents are performing
coordinatekeep the fleet in sync5
/coschief-of-staff awareness across all slots
/daily-briefmorning intelligence from every data source
/callprocess a meeting transcript into structured notes
/checkpointmid-work save to memory and the vault
/deciderecord a decision with its full context
setupstand up an instance5
/traqr-initinitialize TraqrOS on any project
/traqr-updateupgrade in place, preserving your sections
/traqr-system-slackwire Slack routing and Block Kit
/traqr-system-guardianconfigure the automated PR lifecycle
/traqr-system-cronsstandardized cron auth and escalation

…and ~30 more. Each one is a markdown file you can read, edit, or delete.

§ 04·agents

PRs merge while I sleep.

Agents work in parallel git worktrees, one slot per branch. When one ships a PR, Guardian takes it from there: rebase, build, merge, sync the other slots, and write what it learned back to memory.

fig. 2 — the four most recent agent-merged PRs in this repo, read from the GitHub API when this page was built (June 10, 2026). Titles as the agents wrote them.

guardian — merge log
06:48#1823fix(pokotraqr): Clerk webhook PostHog identify survives the serverless freeze
07:04#1825fix(nooktraqr): alert tracking survives across serverless instances — /tmp to KV
07:06#1826fix(nooktraqr): /marketing Slack command reads email metrics from KV, not a ghost file
07:08#1827docs: proxy-invariant catalog gains the Storage layer; drop the rotting count
00:35slots synced: feature1 feature2 bugfix1 devops1
00:35learnings extracted → memory

§ 05·install

Take the piece you want.

The memory server stands alone — most people start there. The CLI generates the full harness. Both run on your infrastructure: any Postgres 15+, GitHub or GitLab (auto-detected from your remote), any embedding provider, Slack or none.

path a

Just the memory

The MCP server, pointed at your Postgres. Twelve tools, works with Claude Code, Cursor, Codex, or any MCP client.

path b

The full harness

Memory plus the generated CLAUDE.md, skills, worktree slots, and Guardian. Everything this page describes.

published packages · versions checked 2026-07-02

traqr-memory-mcpv0.2.22The MCP server. Twelve memory tools, an interactive setup wizard, works with any MCP client.@traqr/memoryv0.2.33The TypeScript library underneath — multi-strategy retrieval, entity extraction, bring your own Postgres.@traqr/cliv0.1.11traqr init, traqr render, traqr status, traqr verify.@traqr/corev0.1.24Config schema, template engine, VCS abstraction for GitHub and GitLab.
source on GitHubnpmjoin the alpha →