ProjectDNA
LIVE BETA · 3 PILOT SLOTS OPEN
The engineering brain for AI-native teams

Every decision your team made is in here.
Ask it. See it. Ship on it.

ProjectDNA reads every PR, commit and ADR in your repos and compresses them into one cited brain — so your team can ask it anything, see what everyone’s working on, and hand the same memory to Claude, Cursor & Copilot.

Start your pilot →Watch 60s demo ▶
Works with◇ Claude↗ Cursor⌘ Copilot~ Windsurf// Cline
Cited answers·Read-only GitHub App·No source code stored·~10-min setupCLAUDE · CURSOR · COPILOT · WINDSURF · CLINE
◇ ChatLIVE
Ask the brain

Ask your whole codebase in plain English. Every answer cited to the PR, commit or ADR it came from.

▤ InsightsLIVE
See the work

PR aging, review latency and throughput across every repo ProjectDNA has indexed.

⛓ AgentsSOON
Arm your agents

Feed the same cited memory to your AI agents over MCP — no re-reading the repo each session.

◇ Chat · live

Ask your codebase like a teammate.

Plain-English questions across every repo you’ve indexed. Every answer is grounded in — and cited to — the PR, commit or ADR it came from. Grounded in your code, not guessed.

  • Cross-repoone question spans your whole org, not one file.
  • Always citedPR #, commit SHA, ADR title, timestamp.
  • Branch-awareanswers reflect the branch you’re on.
Why did we move memory generation to a background queue?
⚙ searched 3 repos · read 4 sources
To keep ingest off the API request path — a large repo could block the request for minutes. It was moved onto a BullMQ worker so generation runs async. The decision is recorded in ADR-07 and shipped in PR #88.
ADR-07 · Async memory generationPR #88 · b71f
34
PRs merged · 30d
7.2h
median review latency
5
open PRs aging
+12%
throughput vs prev
Aging PRs — waiting on review
#103 feat/auth6d
#97 billing-refactor4d
#88 mem-pipeline2d
▤ Insights · live

See what your team is actually doing.

The same ingested history, read a second way — engineering activity across every repo. No extra instrumentation, no agent in your CI. Just what GitHub already knows, made legible.

  • Throughput & review latencyhow fast work actually moves.
  • Aging PRswhat’s stuck waiting on a review, ranked.
  • Honest gapsmetrics we can’t yet derive show as “not yet connected,” never faked.
⛓ Agent memorySOON

Soon: hand the same cited brain to your agents.

An MCP server is on the way, so any MCP-speaking agent can pull your project’s memory in-context — cited to source — instead of re-reading the repo every session.

◇ Claude↗ Cursor⌘ Copilot~ Windsurf// Cline
Inside ProjectDNA

A queryable library of your project — not a copy of your code.

For every PR, commit, branch, ADR and doc, we generate a compressed memory document with sources. Your AI retrieves what it needs — never trains on your code.

  • PR memoryWhat changed, why, files affected, risks introduced
  • Commit memoryCoalesced summaries — trivial commits filtered automatically
  • Branch memoryCurrent goal, progress, open questions, suggested next steps
  • ADR memoryOne memory per decision document, kept fresh on edit
  • Doc memoryREADME + docs/ + architecture/ — what your team has already written
  • Project memoryThe whole repo, distilled — purpose, stack, domains, instructions
PR#42 · auth: refresh-token rotation2d
merged · a8f3c1 · cited 12× by agents
ADR07 · Async memory generation1w
accepted · docs/adr/07.md
COMMIT9c2e · refactor billing module3d
feat/billing · 4 files · 217 lines
DOCdocs/api/payment.md3d
last touched · cited 5× by agents
BRANCHfeat/auth · 12 commits aheadlive
open PR #103 · waiting for review
PR#88 · BullMQ for memory pipeline1w
merged · b71f · cited 8× by agents
ADR12 · Tenant isolation strategy2w
superseded by ADR-14
COMMITe3a0 · README updates5d
main · README.md
How it works

Three steps. Ten minutes. One pilot.

Install once. Memory generation runs continuously in the background. You can start asking questions within minutes.

01

Connect

Install the read-only GitHub App on the repos you want. No source code ever stored. Webhook signature verification, encrypted tokens, signed DPA.

~30 seconds
02

Remember

We summarize every PR, commit, branch and ADR into compressed memory — automatically, in real time. Secret scanning + PII redaction before persistence.

~5 minutes for first repo
03

Use

Ask the brain in chat, see the work in Insights, or — soon — connect your AI agents over MCP. Every answer cited: PR #, commit hash, ADR title.

chat & insights live today
Security & privacy

Your repo. Your data.
Always.

ProjectDNA was built by engineers who'd never connect this to their own repos if it weren't safe to.

READ FULL FAQ →

No source code stored

We fetch diffs on demand, hold them encrypted for ≤24h, then drop them. We store only summaries.

No AI training on your data

Signed DPAs with Anthropic (ZDR addendum) and OpenAI (Enterprise). Monitored monthly.

Tenant isolation, verified

A 100-pair cross-org fuzz test runs on every code change we ship. Cross-tenant leaks fail the build.

GDPR + LGPD compatible

Signed DPAs, Standard Contractual Clauses, tamper-evident audit logs. Export anytime. Hard delete within 30 days. Regional residency available on Enterprise.

Pilot program — 3 slots open

Be one of the first three teams
to give your AI real memory.

Pilot includes: up to 10 repos, all 6 memory types, audit logs, founder-priority support, DPA + sub-processor agreement, manual invoicing. €79/mo for the duration of the pilot.

NO CREDIT CARD · CANCEL ANYTIME · DPA INCLUDED