Demo Features How It Works Questionnaires FAQ ★ Star on GitHub
Clone & Run →
Open source · Local-first · Evidence-only

The GRC tool that actually says
“I don’t know.”

Trusted by vCISOs, MSSPs, and compliance teams who can’t afford confident wrong answers.

Most compliance AI fabricates confidence. threep reads your actual policies, cites specific sections, and reports PARTIAL or NONE when evidence is missing. Auditors love it.

// under the hood

An evidence engine for compliance answers.

Most compliance AI demos look the same: upload some policies, ask a question, get a confident answer. threep is different under the hood. It separates what a control is asking from what your documents actually prove, so answers can be checked against policy support instead of model confidence.

The point is not just to generate an answer. It is to determine what your corpus actually supports, where support is partial, and where the claim should stop.
engine trace
01

Control-aware retrieval

Interprets the framework question before it goes searching for support.

query intent control family routing
02

Corpus-aware evidence

Searches your documents for proof, not just related language, and grounds answers in specific sections.

retrieval citations policy text
03

Answer-state discipline

Returns supported answers, PARTIAL support, or GAP when your corpus does not warrant a stronger claim.

supported partial gap
Open source on GitHub — MIT Licensed
threep — live query
STRONG confidence: 1.51 · 2 sources

Account management requirements are addressed in two policy sections with explicit provisioning, review, and termination procedures aligned to NIST AC-2.

User Access & Privilege Mgmt — §4.12 Access Control Policy — §5
Coverage matrix snapshot
AC-2STRONG
AU-6STRONG
CM-6PARTIAL
PE-3NONE
IA-5STRONG
IR-4PARTIAL
SC-7STRONG
RA-5PARTIAL
See it in action

Three screens. Zero guesswork.

Gap Detection Workflow
threep compliance answer showing AT-2 gap detection, evidence review, and created gap task
Assessment Review
threep assessment review showing mixed findings including insufficient evidence and evidence-backed responses
Policy Coverage Matrix
threep policy coverage matrix showing strong, partial, and gap indicators across controls

And one place to run it all.

threep workspace showing policy management, assessment tracking, and policy detail view
Built on NIST 800-53. Works with the frameworks that matter.
NIST 800-53
SOC 2
FedRAMP
TX-RAMP
ISO 27001
HIPAA
AC-2(a)User Access & Privilege Mgmt §4.12
AU-6Audit Review & Analysis §7.3
CM-6Configuration Settings §3.1.4
IA-5(1)Authenticator Mgmt §5.2
IR-4Incident Handling §8.1
PE-3Physical Access Control §2.6
RA-5Vulnerability Scanning §6.4
SC-7Boundary Protection §9.2
SI-4System Monitoring §7.5
CP-9System Backup §10.1
SA-11Developer Testing §4.8
PL-2Security Planning §1.3
AC-2(a)User Access & Privilege Mgmt §4.12
AU-6Audit Review & Analysis §7.3
CM-6Configuration Settings §3.1.4
IA-5(1)Authenticator Mgmt §5.2
IR-4Incident Handling §8.1
PE-3Physical Access Control §2.6
RA-5Vulnerability Scanning §6.4
SC-7Boundary Protection §9.2
SI-4System Monitoring §7.5
CP-9System Backup §10.1
SA-11Developer Testing §4.8
PL-2Security Planning §1.3
The honest comparison

Most tools give you confidence.
threep gives you accuracy.

Magic AI tools promise full automation but deliver significant rework. The difference between a compliant-sounding answer and a defensible one is whether anyone actually checked your policies.

What most compliance tools do

  • Generate dashboards from integrations — not from your actual documents
  • Produce plausible-sounding coverage even when evidence is absent
  • Report YES when your implementation is technically PARTIAL
  • Require cloud connectivity — your policy text leaves your environment
  • Lock you into a vendor's framework mapping you can't inspect

What threep does

  • Reads your actual policy documents — citations trace to specific sections
  • Requires evidence before reporting YES — otherwise returns PARTIAL or NONE
  • Turns gaps into actionable remediation tasks, not suppressed warnings
  • Runs entirely on your machine via Ollama — policy text never leaves
  • Open source — read, audit, and modify every line of logic
Capabilities

Built for real compliance work.

Not just search. Not just chat. A system that reads your policies, cites them honestly, and tells you exactly where the gaps are.

Evidence-Only Answers

Every answer cites specific policy sections. No evidence? The system says so instead of making something up.

Three-Lane Question Routing

Questions automatically route through policy, NIST control, or hybrid paths for the most relevant response.

Policy Management

Upload, edit, and reingest policy documents without leaving the browser. DOCX auto-converts to Markdown.

Gap Task Management

Turn coverage gaps into actionable work items — flag what's missing and track remediation progress.

Scheduled Assessment Runs

Run assessments on a daily, weekly, monthly, or custom cron recurrence — with timezone handling, holiday presets, and skip dates. Each run is a tracked job (queued, running, completed, failed, canceled) and artifacts deliver to a folder or HTTP endpoint.

Why open source wins

Your compliance logic shouldn't
be someone else's black box.

Fork it. Own it.

Every prompt, scoring weight, and routing decision is yours to modify.

Data never leaves.

Embeddings and LLM inference run locally via Ollama. Cloud is opt-in.

Full audit trail.

Every citation, every routing decision. Show auditors exactly how you got there.

MIT licensed.

Use in production. Modify for your org. Contributions welcome.

How it works

From raw policy docs to a
submitted questionnaire in five steps.

1

Upload

Add your policy docs (DOCX or Markdown)

2

Ingest

Policies are chunked, embedded, and indexed locally

3

Map

Sections map to NIST 800-53 controls automatically

4

Ask

Query or batch-run questionnaires against your docs

5

Export

Download answers as CSV, DOCX, or JSON

Open source

I'm tired of black-box compliance tools that lie to auditors.
So I open-sourced the whole thing.

threep is free, local-first, and built by someone who actually fills out vendor security questionnaires.

Differentiation

Showing a source is not the same
as proving the claim.

Many AI tools can attach citations. threep is designed to do the harder thing: evaluate whether the available evidence actually supports the answer, distinguish policy intent from implementation proof, and preserve uncertainty when the documents do not justify a stronger claim.

Traceability is the start

Knowing which document an answer came from is table stakes. threep records the excerpt, the file, the page, and the reasoning chain that produced the conclusion — so reviewers can audit the logic, not just the output.

Restraint is the difference

When evidence is thin, ambiguous, or silent on the question asked, threep says so. It does not synthesize a confident-sounding answer from weak material. Partial and unknown are first-class results.

Assessment is the core

Each answer distinguishes between what a policy states and what your environment actually demonstrates. Intent without implementation evidence is labeled as such — because that gap is exactly what auditors look for.

Transparency

Benchmarking threep for evidence discipline.

Most AI evaluations ask whether an answer sounds plausible. In compliance work, that is not enough. threep is evaluated on whether answers are grounded in real documentation, whether claims are inspectable, and whether gaps are stated honestly.

Grounding

Measures whether answers stay tied to the source corpus instead of attaching decorative or unrelated citations.

Restraint

Measures whether the system avoids overstating what the documents actually prove — especially when policy language exists without implementation evidence.

Output control

Measures whether answers stay readable, bounded, and structurally disciplined rather than sprawling or padded.

Coverage honesty

Measures when the right answer is PARTIAL or GAP — not forced certainty.

v1 baseline improvements
  • Citation duplication sharply reduced
  • Unsupported citation usage sharply reduced
  • Cross-document contamination reduced dramatically
  • Forbidden implementation verbs reduced to zero
  • PARTIAL introduced as a first-class answer state
  • Section sprawl capped and controlled

threep is not a substitute for human review, and these evaluations do not prove legal sufficiency or control effectiveness. They measure grounding, output discipline, and honesty about uncertainty. The evaluation harness runs in the open. See the open-source project →

FAQ

Common questions.

The short answers. No marketing language.

No — by default everything runs locally. Embeddings use sentence-transformers locally. The LLM runs via Ollama. OpenAI is available as an opt-in provider, but even then embeddings remain local.

A modern laptop with 16 GB RAM is enough to run qwen2.5:14b via Ollama. A GPU helps but isn't required. For batch work, 32 GB RAM and a consumer GPU is recommended.

Policy documents: .docx or .md (DOCX auto-converts). Questionnaires: .csv, .xlsx, or .txt. Exports: CSV, DOCX, or JSON.

Accuracy is bounded by your documents. threep reports PARTIAL or UNKNOWN rather than fabricating — threep would rather tell you it doesn't know than pretend it does. That's the whole point. Every answer includes a section citation. Quality improves with larger models and well-structured docs.

Built-in: NIST SP 800-53 Rev 5 and NIST CSF. The batch runner handles any free-form questionnaire — FedRAMP, TX-RAMP, SOC 2, ISO 27001, and vendor security reviews all work.

Yes. Scheduled Assessment Runs execute on a daily, weekly, monthly, or custom cron recurrence, with timezone awareness, holiday presets, and explicit skip dates. Each run is a tracked job with states (queued, running, completed, failed, canceled) and per-run artifacts you can review. Delivery options include writing to a folder or POSTing to an HTTP endpoint — useful for vCISOs and compliance teams that need a recurring cadence without manual execution.

Yes. MIT licensed, open source on GitHub. Self-host, modify, and use it in production at no cost. Contributions are welcome.

What's next

Roadmap

Q2 2026 Community plugins + batch export improvements
Q3 2026 threep.cloud — same evidence discipline, less operational drag

Want the managed path?

threep.cloud is the hosted version of threep for teams that want the workflow without self-hosting.

Visit threep.cloud Same evidence discipline. Different operating model.

Four commands. Real compliance answers.

Clone the repo, ingest your policies, and start answering audit questionnaires from your actual documents — not hallucinations.

git clone https://github.com/dllswbr/threep && cd threep && python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt && python3 ingest.py && uvicorn app:app --reload