Models know the world. Nora knows you.
Each AI session sharpens the next — measured, cited, audit-ready.
Every session produces patterns, decisions, and fixes — organizational learnings that should carry forward but vanish when the tab closes. Nora captures them automatically and grounds every AI reply in your team's facts — so each answer cites what your team actually knows.
Kernora provides the decision layer for AI-assisted work — grounded in your private data, built on the open Factlet protocol, audited like code, run on your hardware. BYOK · zero telemetry · on-prem for regulated work.
DEMO · sample data · not real customer factlets
Memory and grounded context for AI-assisted work.
Grounding and memory are the same artifact — a verified body of facts your team owns (conventions, specs, history, decisions) that the model can cite. Nora builds it from your repo and sessions, maintains it as work evolves, and serves it to every agent — solo to company-wide, supervised or autonomous.
Stop the model from making things up about your codebase.
Generic AI gives generic advice. Your team has hard-won decisions, regrets, and conventions that aren't in any training set — and they conflict with the obvious answer often enough that "obvious" is dangerous.
f###
Per-fact egress consent
Kernora builds a factbook from your repo, docs, ADRs and tickets — then grounds every reply in your team's facts, forcing each answer to cite what it used. Open standard, audit-it-yourself.
Stop teaching your AI the same thing every session.
A session ends, the context window dies, the lesson dies with it. Tomorrow morning you'll explain again why the migration script can't run inside a transaction. The third time you explain something is the third time you've wasted that prompt.
Every session ends with new facts proposed, verified, and merged into the same factbook. Tomorrow's prompt starts where yesterday's ended.
A queryable, citable knowledge base — AI-ready and version-controlled with your repo.
A factbook is plain markdown plus a structured index in .nora/ next to your code. The model can't quote a fact without naming it.
How Nora maintains it — a continuous loop, not a one-time import.
From repo & sessions
Reads code, ADRs, tickets, docs. Watches every Claude / Cursor / Kiro session as it happens — supervised or autonomous. Each captured fact gets an ID, source, decided-on date, and privacy tier.
When sessions end
Nora extracts decision candidates, dedups against existing facts, flags contradictions, scores AI Leverage for the session.
Trust ladder
Facts enter as proposed, auto-promote to candidate after N uses without contradiction, you approve canonical from the dashboard.
To every agent
Injected via MCP or system prompt — Claude, GPT, Gemini, or local. Same factbook, every model, every session.
Click any f### chip in a reply to open its decision trail.
See what it cites, why your team decided it, what it superseded, who applied it last. Git-tracked alongside your code.
Built on the open Factlet protocol — your factbook is portable, your tooling isn't locked to us.
One factbook in the middle. Five sources, five surfaces, five guarantees.
Nora maintains the five elements of the Factlet protocol in the middle box — facts flow in from your tools, out to every model you use, with provenance and consent attached.
Grounding works. Independently measured.
In an open, pre-registered eval across Claude Sonnet 4.6, GPT-4.1, and Gemini 2.0 Flash (2026-05, N=6 models), supplying the model with a team-specific factbook reduced harmful shipping recommendations 4× and high-risk recommendations 20× — same direction across all three vendors. Nora is the reference implementation that gets your factbook generated, kept current, and into the model's context.
Reduction in high-risk shipping recommendations with a factbook in context.
N=6 models, held-out prompts, blind-judged. Methodology and raw data on GitHub — factlet-ai/evals.
See the methodology + raw data on GitHub →Know what your factbook doesn't cover.
A representative-query batch runs nightly. You see which questions your team will ask that your factbook can't ground — and a concrete list of facts to add. Not a score: a punch list.
of 184 representative queries hit FactSignal ≥3 (2026-05).
Up from 42% two weeks ago.
Bucketed histogram · 184 queries (2026-05)
The 0–1 bar buckets are the productive output: 70 queries your team will ask but your factbook can't ground. Click a bucket to see the queries; click a query to see the proposed-fact diff.
28 queries · click to propose facts.
Verified nightly. Falsifiable. Sharable with your team in one screenshot.
"Why not just use Memory Bank?"
Memory Bank documents what your project is. Kernora captures what your team decided — and why — automatically.
You write, you maintain, it drifts.
- — You write and update markdown files by hand
- — Stores project docs — stack, conventions
- — Loads everything at session start
- — Drifts silently when you forget to update
- — Flat files — human-readable, not queryable
Automatic capture, typed, decayed.
- ✓ Hooks capture intelligence during sessions
- ✓ Stores decisions, reasoning, alternatives
- ✓ Injects only what's relevant to this session
- ✓ Auto-decay plus
nora revisefor corrections - ✓ Structured graph — queryable via MCP
Memory Bank is a journal you write every day. Kernora is a colleague who was in every meeting.
One command. Solo to team to production.
Install in 30 seconds for individuals. Sync your own S3 bucket for teams. Deploy as a sidecar for autonomous agents in production. Same factbook, end to end.
VS Code · Cursor · Kiro
One-click install. Starter factbook seeded from your repo in ~30 seconds. View on VS Code Marketplace →
Claude Code · Claude Desktop
Registers Kernora as an MCP server. Restart your agent and the factbook tools appear.
Autonomous agents in production
Sidecar to your agent runtime — CI bots, scheduled agents, customer-facing agents. Headless MCP, BYOK secret management, audit log to your S3, decisions auto-promoted by trust ladder. Per-fact egress consent, encrypted at rest, your bucket and keys throughout.
Why we built this.
I was shipping a product with Claude Code, Kiro, and Cursor — sometimes three agents in parallel. Hundreds of sessions. Thousands of decisions. And the same thing kept happening: I'd solve a problem on Tuesday, and on Friday the AI would suggest the exact approach I'd already rejected. The models got smarter every quarter — but everything I taught them evaporated every session.
The better a session went, the more I lost when it ended. Reusable patterns, architectural rules, hard-won fixes — none of it carried forward unless I manually wrote it down. The METR study showed experienced developers are measurably slower with AI — not because the tools are bad, but because the context cost of re-explaining your codebase eats the productivity gain. Anthropic's own data: engineers fully delegate only 0–20% of tasks despite using AI in 60% of their work. What slows real teams down is missing context, not missing model capability.
The more you work, the smarter your AI gets. Automatically.
Built products and led teams at Amazon. Built startups. Now building the local memory layer that grounds AI for AI-assisted work — visibility into how developers, managers, and organizations adopt, measure, and benefit from AI tooling.