Compliance infrastructure

Your AI agent just broke production.
It didn't know.

mati blocks AI agents from touching dangerous code until they prove they know what's dangerous about it — and keeps the audit trail your compliance team needs.

System · Live
 
Languages
 
Resolution
 
Init
 
LLM calls
Enforcement

Hard enforcement,
not suggestions.

mati intercepts file reads at the hook level. Access is denied until the agent consults the verified knowledge record for that file.

01Agent issues a read
02mati denies — knowledge required
03Agent calls mem_get(path)
04mati allows — context in memory
mati hook·Read request
Agent
~
mati
File
charges.rs
$ Agent issues Read on src/billing/charges.rs
What it prevents

The failure mode
is always the same.

An actor with write intent had no access to the institutional knowledge that would have prevented the mistake. mati makes that knowledge structurally unavoidable.

Scenarios01/ 04
Without mati

Contractor makes a 'minor performance fix' to a data pipeline. No one flags it as HIPAA-covered. Audit exposure 6 months later.

With mati

mati blocks the read. The agent consults the gotcha: 'Every read/write to patient_records must call audit_log::record_phi_access.' The audit trail logs the consultation.

For regulated teams

Built for teams
handling PHI.

mati generates the audit trail your SOC 2 auditor will ask for. Every agent action, every DENY decision, every policy consultation — logged, timestamped, and exportable.

On-premZero network calls · no telemetry
For auditors

What your
auditor sees.

Every enforcement decision, cryptographically signed and auditor-ready. Your audit trail started the day you installed mati.

mati · enforcement audit
Enforcement Audit Report
Signed
Project
acme-health / patient-api
Period
2026-03-24 → 2026-04-24
Hash chain
valid (intact) · head → genesis
Every event cryptographically linked to the previous. Tamper-evident by design.
License
Enterprise · 12-seat
33
Events
7
Denials
9
Allowed
0
Bypasses
✓ Signed·fingerprint a27ea8528f81a45cEd25519 · rfc-8032
Live output

What your agent sees.

~ mati explain src/billing/charges.rs
 
Purpose
Confidence
Staleness
Blast radius
Cluster
 
─ [critical]idempotency-key
─ [high]zero-amount-validation
verifying record00/15sha · a8e4f1c
~ mati diff main
 
● [critical]src/billing/charges.rs 2 gotchas
● [critical]src/data/patient_records.rs 2 gotchas
● [high]src/auth/session.rs 1 gotcha
○ [normal]src/api/handlers.rs documented
○ [normal]src/config/database.rs documented
? [unknown]src/utils/helpers.rs no record
 
scanning diff00/10branch · main
Language coverage

12 languages.
Real codebases.

Every resolution rate is verified against a real-world open-source project. No toy fixtures, no synthetic benchmarks.

LanguageResolutionVerified againstEdges
Rust97%ripgrep342
Python100%httpx124
TypeScript97%vitest2,147
Go98%hcl190
Java95%jsoup740
C100%mimalloc129
C++95%nlohmann/json619
Ruby/Railsstructuraldiscourse2,622
Haskellmeaningfulaeson223
Scalapartialzio-json21
JavaScriptsharedvitest—
ElixirfixtureMix—
File-level intelligence

Your agent sees what matters.

Blast radius

diagram
direct: 18 · transitive: 12 · tier: critical

Co-change clusters

diagram
billing (5 files · cohesion 0.87)

Staleness propagation

diagram
from session.rs · +0.15 d1 · +0.05 d2
How it compares

Not a memory tool.
Not a linter.

mati answers a different question: has this actor proven they understand what's dangerous about this file — and can we prove it to an auditor?

CapabilitymatiAI memoryLintersADRs
Block reads until knowledge consulted●———
Compliance audit trail●———
On-prem, zero network calls●—●●
Per-file gotchas with confidence scoring●———
Works without any LLM calls●—●●

Your AI agent just refactored a payment flow and removed the fraud check. With mati, that's structurally impossible — the agent can't read the file until it proves it knows about the fraud check.

The problem mati was built to solve
Enterprise

Free for developers.
Paid for compliance teams.

Cloud compliance tools automate paperwork. mati enforces compliance at the code level — before the code ships.

Open source
Free
MIT licensed · No telemetry
  • 01Full enforcement engine
  • 0212-language import resolution
  • 03Blast radius & co-change clusters
  • 04Enforcement event recording
  • 05365-day event retention
  • 06Claude Code & Codex support
View on GitHub
Enterprise
SOC 2 TYPE IIHIPAA
Enterprise
For compliance teams at regulated companies
  • 01Signed audit PDF export
  • 02Cryptographic chain of custody
  • 03License-verified enforcement reports
  • 04Extended retention controls
  • 05Direct support from the founder

Signed audit export aligned with SOC 2 Type II and HIPAA evidence requirements.

Priced per engineering team, not per seat.
Get a demo
Get started

Running in your repo in 15 minutes.

~ install
# Homebrew (macOS + Linux)
$ brew install ioni-dev/tap/mati

# Cargo — builds from source
$ cargo install mati

# Cargo — prebuilt binary, no compile
$ cargo binstall mati
~ quickstart
# Scan your repo (zero AI calls, <1s)
$ mati init --claude

# See what mati knows about a file
$ mati explain src/billing/charges.rs

# Add a gotcha
$ mati gotcha add src/billing/charges.rs \
    -r "Never remove the idempotency_key"
FAQ

Questions, answered.

The short version of how mati works, what it touches, and why it's different.

What is mati?

mati is compliance infrastructure for AI-assisted engineering. It blocks AI coding agents from reading or editing dangerous code until they prove they understand the per-file constraints ("gotchas"), and it records an audit trail for compliance teams. mati runs on-prem with zero network calls and works without any LLM calls.

How does mati stop AI agents from breaking production code?

mati intercepts file reads at the hook level and denies access until the agent consults the verified knowledge record for that file. For example, before editing a payments file the agent must acknowledge a constraint such as keeping an idempotency check that was added after a fraud incident, so it cannot silently remove safeguards.

Does mati make LLM calls or send code to the cloud?

No. mati works without any LLM calls and makes zero network calls. It runs entirely on-prem, which is what makes it suitable for regulated environments handling sensitive or compliance-covered code such as HIPAA data.

What programming languages does mati support?

mati supports 12 languages: Rust, Python, TypeScript, Go, Java, C, C++, Ruby/Rails, Haskell, Scala, JavaScript, and Elixir, with knowledge-resolution rates up to 100%.

How is mati different from agent memory, linters, or ADRs?

Unlike agent memory, linters, or ADRs, mati hard-blocks file reads until the required knowledge is consulted, produces a compliance audit trail, and scores per-file gotchas by confidence — all on-prem with zero network calls. Memory and ADRs are passive; mati is enforcement.

Does mati provide a compliance audit trail?

Yes. Every time an agent consults a gotcha before editing a file, mati logs the consultation. Compliance teams get a verifiable audit trail showing exactly what the agent knew before it made each change.