GraQle — give your AI a memory of how your organisation actually works
Turn policies, decisions, documents and codebases into a persistent knowledge graph, so your AI agents reason over what your organisation already knows instead of rebuilding a partial picture every session.
pip install graqle
Models change. Tools change. Your institutional knowledge should not.
Works with your stack today — 13 LLM backends plus any custom HTTP endpoint (Anthropic, OpenAI, Bedrock, Ollama, Gemini, Groq, DeepSeek, Together, Mistral, OpenRouter, Fireworks, Cohere, llama.cpp), fully offline with Ollama or llama.cpp, and inside Claude Code, Cursor, VS Code + Copilot or Windsurf via 85 MCP tools. Local-first: no telemetry, and your source never leaves your machine.
60-second proof — no code required
Works on a folder with no code in it at all.
# 1. Turn organisational documents into a typed graph
graq scan docs ./policies
# → 3 files → 12 nodes: 3 Document + 9 Section, linked by SECTION_OF
# 2. Teach it a rule that lives in nobody's file
graq learn knowledge "vendor DPA must be signed before any data access" --domain policy
# → auto-links the rule to the vendor-onboarding doc AND its "Due diligence" section
# 3. Ask across the whole body of knowledge
graq run "what approval is needed for a large refund?"
# → answer + confidence + evidence trail + the sections consulted
# 4. Audit what the organisation has taught it
graq learned
Step 2 is the one that compounds — and the one prompt engineering cannot replace, because it needs a persistent typed graph as the substrate. GraQle worked out where that rule belonged on its own.
The same graph, for code
graq scan repo . # functions, classes, imports, calls
graq run "what breaks if I change the payment module?"
graq impact payments.py # blast radius
Software architecture is the deepest-mapped domain today — a wedge, not the boundary.
Why this matters now
Agents are getting far more capable and still start from zero every session. Models are becoming cheaper and interchangeable, which makes the intelligence layer above them — not the model itself — the thing worth owning.
GraQle sits above the model:
- Relationships, not files. Assistants see documents and files. GraQle sees how a policy, a decision and the code implementing it relate.
- Memory that compounds. Policies, decisions and lessons become durable graph nodes, not chat history.
- Model independence. Switch providers or IDEs without rebuilding the intelligence layer.
What you get
| Capability | Command |
|---|---|
| Blast radius before a change | graq impact payments.py |
| Cross-file security audit | graq run "find every auth bypass risk" |
| Architecture Q&A for onboarding | graq run "how does checkout work end to end?" |
| Persistent lessons | graq learn knowledge "..." |
| Audit what the graph has been taught | graq learned |
| Documents, policies, ADRs into the graph | graq scan docs ./docs |
| Pre-change safety check | graq preflight "refactor the auth layer" |
| CI/CD governance gate | graq predict "..." --fail-below-threshold |
Beyond code
pip install "graqle[docs]" # PDF / DOCX / PPTX / XLSX parsers
graq scan docs ./docs # architecture docs, runbooks, specs
graq learn doc ./policies/ # policies, ADRs, decision records
Documents become Document and Section nodes, linked by SECTION_OF — and to any code that implements them. Markdown, text, RST and AsciiDoc work with the base install; the richer formats need the [docs] extra and are reported — never silently skipped — when it's missing.
Configuring your stack
Switching backend is one line — the graph is the constant, the model is a swappable input:
# graqle.yaml
model:
backend: ollama # or: anthropic, openai, bedrock, gemini, groq...
model: llama3
graq init # detects your IDE and wires the MCP tools
Trusted answers
Every result carries confidence, graph_health, active_nodes and evidence pointers. Below the confidence floor, GraQle refuses rather than guesses. With no LLM configured it labels output as a placeholder and attaches no confidence score.
Governed autonomy
When agents move from reading to writing, graq gate-install routes write/edit/bash operations through governance gates: plans required for risky changes, secret scanning on commits, full audit trail. For deployed systems, GovernedRuntime.attest() records what your AI decided, anchored to the public Sigstore Rekor transparency log — verifiable by any third party.
Optional compliance surfaces for regulated deployments cover the EU AI Act, SOX/COSO, ISO/IEC 42001 and GDPR claim limits; compliance frameworks are authorable as data.
→ Full documentation on GitHub
Pricing
| Free | Pro ($19/mo) | Team ($29/dev/mo) | |
|---|---|---|---|
| CLI + SDK + 85 MCP tools | Unlimited | Unlimited | Unlimited |
| 13 LLM backends + custom | ✅ | ✅ | ✅ |
| Graph nodes | 1,000 | 25,000 | Unlimited |
| Cloud sync | 1 project | 3 projects | Unlimited |
| Shared team graphs + lessons | — | — | ✅ |
Built by Quantamix Solutions B.V. · Patent pending EP26167849.4 · Local by default · Your code never leaves your machine
1 maintainer
Metadata
1 maintainer
Release files for graqle 0.84.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| graqle-0.84.1.tar.gz | 5.2 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| graqle-0.84.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 7.2 MB
Release files / graqle-0.84.1.tar.gz
| Download URL | graqle-0.84.1.tar.gz |
|---|---|
| Size | 5.2 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0687fe4d77e603540f00db4533e5c71f17ccf637549f8a849c8a55e0222141a6
|
|
BLAKE2b-256 checksum How to use checksums |
206530f4adec8302f097ec5e4d671f2307895ea943ca8a54c2720fd8f631d54e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 23, 2026.
Transparency logRelease files / graqle-0.84.1-py3-none-any.whl
| Download URL | graqle-0.84.1-py3-none-any.whl |
|---|---|
| Size | 2.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6ec607537c97de0745684234f53e92d4194dca421786a3a91916044147cc2c63
|
|
BLAKE2b-256 checksum How to use checksums |
2b681a418972b5243f1c0b5bc94452eab76f6043b200748dad82fe628a1b69a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 23, 2026.
Transparency log
