The toolbox that keeps your AI stack honest.

Great tools drift. Trust shouldn't.

agentic-kit exists because of a very specific, very modern kind of heartbreak. You wire up an AI agent stack — persistent memory, self-learning, security scanning, background workers — and it's glorious. Then one npm upgrade later, some of it is quietly off. Not crashed. Not erroring. Just… silently doing nothing, while printing "OK."

These aren't hypotheticals. Each of these really happened, and each one now has a guard in the kit that traces back to a filed upstream issue:

Most tooling starts at the outer ring — what it does. agentic-kit starts at the center: the conviction that in a fast-moving agent ecosystem, proof beats promises. Everything else on this page is that belief, mechanized.

Open the drawers

You install exactly one package by hand. Everything else — the whole stack below — is installed, wired, healed, and verified for you by ak setup. Here's what ends up under management:

The workbench — every daily-driver verb

Power-user plumbing lives under ak x … (verify, harvest, statusline, mcp pick, reference sync…) — ak --help --all lists the lot. And every mutating command takes --dry-run and prints its plan, with reasons, before touching anything.

The convergence loop

Everything the kit does is one loop, run over and over for the life of your machine: detect what's drifted, converge back to healthy, prove the result against the real CLIs. Three verbs, three commands.

What that looks like — a real ak status, from a real machine

This is an unedited capture from the maintainer's own machine while writing this page. Note the two ⚠ rows: honest drift, each naming exactly what sync would do about it. A status that's all green all the time isn't honest — this one earns its checkmarks.

$ ak status
  ✓ versions    ruflo 3.34.0 (latest)
  ✓             agentic-qe 3.13.10 (latest)
  ✓             @openai/codex 0.147.0 (latest)
  ✓             opencode-ai 1.18.15 (latest)
  ✓ ruvnet-brain release v4.0.28 (latest)
  ✓ self        kit 4.0.0-alpha.41 (latest)
  ✓ natives     native better-sqlite3 in 1 agentdb location(s)
  ✓             ruflo memory runtime native (memory, cli)
  ✓ memory      native-agentdb active writer: 2253 active entries
  ✓ security    @claude-flow/security + aidefence present (defend functional)
  ✓ learning    1337 patterns learned, 1400 trajectories (this project)
  ✓ aqe         agentic-qe initialized here; RVF store healthy
  ✓ agentdb     agentdb 3.0.0-alpha.17 (coherent with ruflo)
  ✓ mcp         claude-flow registered (user scope), all families allowed
  ✓ hosts       claude 2.1.226 (external — self-managed)
  ✓             claude auth: oauth (subscription, $0)
  ✓             codex 0.147.0 (npm) · oauth (subscription, $0)
  ✓             opencode 1.18.15 (npm) · oauth (subscription, $0)
  ⚠ providers   provider config drifted (want claude+codex+opencode)
                → sync re-applies provider env + aqe router
  ⚠ routing     12 activities → 12 agent overrides — llm-config.json out of sync
                → sync re-applies agentOverrides
  ✓ daemons     2 running (one per active project is expected)
  ✓ blocks      CLAUDE.md managed blocks in sync (9 in registry)
  ✓ statusline  activation footer present and current
  ✓ qe-court    qe-court panel valid (vendor-diverse, jury independent of writer)

Abridged only by removing a few repeated sub-rows for width — every line shown is verbatim. The full output runs 38 lines and covers 23 subsystems.

The honesty mechanisms — how "proven" is built in

Two chairs at the same workbench

The kit was built by and for agentic engineers — people composing multi-agent systems who need their substrate to be provably on. But its "one command, self-healing" shape makes it just as useful if you'd rather never think about any of this. Both chairs are legitimate.

The shared payoff: extra lift. Your AI-assisted sessions inherit persistent memory, grounded knowledge, quality gates, and honest status — without you maintaining any of it by hand.

What ak setup actually touches

One command, three concentric scopes. Knowing which is which is the whole trick to feeling safe: machine scope is global packages, user scope is your config files, project scope only triggers when you run it inside a git repo.

Where it gets genuinely clever

Past the install-and-heal loop, three features do the heavy lifting for day-to-day work: multi-host execution, the honest statusline, and the local dashboard.

Feature file · 03

The dashboard — observation only, localhost only

One command opens a self-contained local web app on 127.0.0.1:7431, guarded by a per-session token, that never mutates anything. Five areas: About (a plain-words directory of everything the kit installed, and why), Overview (what's installed, wired, and routed — plus machine-wide intelligence), Usage (scorecards, limits, and sessions indexed from your local Claude/Codex/OpenCode transcripts), Observability (live and historical agent activity on an interactive canvas, with masked transcript evidence), and System (what the stack occupies on your machine — storage, runtime, catalog, and a project census).

Every capture below is real — taken from the maintainer's machine while this page was being written. First, Overview: the same subsystems as ak status, with the two warnings front and center and what sync would do about each:

127.0.0.1:7431 · #overview/summary · token-guarded

The Usage area turns your local transcripts into a scorecard — sessions, token volume, API-equivalent cost (clearly labeled list-price equivalent, not what a subscription bills), split by host, with a cost-per-day chart and a when-you-work heatmap:

127.0.0.1:7431 · #usage/score

And Observability, watching live agent activity. This capture is pleasingly recursive: the session it's following is the Claude Code session that was writing this very page:

127.0.0.1:7431 · #observability/live

A maintainer sibling, ak admin on :7432, tracks the project's own telemetry — repo traffic, npm momentum, CI state — with the same token discipline and zero external fetches from the page itself. Notice the tone: tiles say what they count and what they can't ("ak ships no opt-in counter — an honest gap, not a zero"):

127.0.0.1:7432 · ak admin · maintainer-only

Three ways in — pick your risk appetite

# Path A, in full — this is genuinely the whole thing:
npm install -g @pacphi/agentic-kit@next   # alpha channel until 4.0.0 GA
ak setup       # machine + user + (inside a repo) project — prompts disclosed
ak status      # see the proof: every subsystem, ✓/⚠/✗
ak dashboard   # and here's your stack, in a browser

From then on, the entire maintenance story is one habit: when in doubt, ak sync.

Straight answers