Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
uvx graqle==0.27.0Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add com.graqle-graqle -- uvx graqle==0.27.0รันในเทอร์มินัล
{ "mcpServers": { "com.graqle-graqle": { "command": "uvx", "args": [ "graqle==0.27.0" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Turn the context your organisation already has — codebases, documents, policies, decisions and workflows — into a persistent typed knowledge graph, so Claude Code, Cursor, Copilot and other agents reason over architecture, dependencies, prior lessons and evidence instead of re-reading disconnected files every session.
Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.
pip install graqle
Website · Quickstart · How it works · Governed autonomy · Regulated deployments · Changelog · VS Code Extension
Your organisation already knows the answer. It just can't hand it to an AI.
The refund threshold lives in a policy document. The reason you retain records for seven years is in an ADR nobody re-reads. The incident that moved validation into the service layer is in someone's head. The dependency that makes payments fragile is in the code. Every one of those is real knowledge — and none of it is connected to any of the others, so no model can reason across it.
Each AI session starts from zero and rebuilds a partial picture from whatever files fit in the context window. Then the window closes and the picture is gone.
GraQle builds that connection once, keeps it, and grows it.
Point GraQle at policies, ADRs, runbooks or specs. Nothing else needed — this works on a folder with no code in it at all.
pip install graqle
# 1. Turn a folder of 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
# → extracts the entity "DPA", then SEMANTICALLY_RELATED-links the rule to
# the vendor-onboarding document AND to 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 exact sections consulted
# 4. Audit what the organisation has taught it
graq learned
Step 2 is the one that compounds, and the one no amount of prompt engineering replaces: it needs a persistent typed graph as the substrate. GraQle found where that rule belonged on its own — you never told it which document to attach it to.
Markdown, text, reStructuredText and AsciiDoc parse with the base install. PDF, DOCX, PPTX and XLSX need pip install "graqle[docs]" — without it those files are skipped and reported, never silently dropped.
Where a codebase is part of the picture, it enters the same graph and connects to the documents that govern it:
graq scan repo .
# → functions, classes, modules, imports, calls — architecture mapped in seconds
graq run "what breaks if I change the payment module?"
# → traces cross-file call + import chains, activates the relevant subgraph
graq impact payments.py # blast radius before you touch anything
Software architecture is the deepest-mapped domain today — typed down to the function — and for engineering teams it is usually the fastest way to see the value. It is a wedge, not the boundary.
The first time you run GraQle, it knows what you gave it. After a month, it knows your patterns. After a year, it holds the policies, decisions, architectural lessons and document context your organisation accumulated — and activates the relevant ones on the work that is about to repeat an old mistake.
This is the part that survives model churn. When you switch provider or IDE, the graph is unchanged. You are not re-teaching a new model what your organisation knows; you are pointing a different model at intelligence you already own.
Own the intelligence your models and agents create. Enterprises can own their data and still lose the reasoning state accumulated inside external AI tools — the decisions, the corrections, the hard-won context. The graph is a local file you control.
SECTION_OF, SEMANTICALLY_RELATED, IMPORTS, CALLS, DEFINES. Taught knowledge is auto-linked to the documents and code it concerns. This is what makes reasoning across sources possible.confidence, graph_health, active_nodes and evidence pointers. Debate is a reasoning mechanism, not a proof of truth: agents sharing a model family, a prompt template or a source document are correlated, so their agreement is not independent confirmation.The pipeline runs through five named phases — ANCHOR → ACTIVATE → GENERATE → VALIDATE → COMMIT. Each phase is governance-gated, evidence-attached and audit-logged.
API defaults: confidence_threshold=0.65 (refusal floor), gate_threshold=0.60 (gate-status floor). Both configurable per call.
You don't need another UI. GraQle runs inside the tools your team already has.
// .mcp/config.json
{ "graqle": { "command": "graq", "args": ["mcp", "serve"] } }
85 MCP tools — every operation Claude Code, Cursor, VS Code Copilot or Windsurf needs, exposed as a governed tool with confidence scores, evidence pointers and audit-trail entries. No prompt engineering, no glue code. (Each tool is also aliased kogni_* for backward compatibility.)
graq init # detects your IDE, wires the tools, writes the project constitution
graq init renders one rulebook for every client — Claude Code → CLAUDE.md, OpenAI Codex → AGENTS.md, Cursor → .cursorrules, Windsurf → .windsurfrules — so editing it once keeps them all in sync.
Anthropic · OpenAI · AWS Bedrock · Ollama · Gemini · Groq · DeepSeek · Together · Mistral · OpenRouter · Fireworks · Cohere · llama.cpp — plus any custom HTTP endpoint.
# graqle.yaml — smart task routing
backends:
reasoning: anthropic/claude-sonnet-4-6 # quality work
embedding: bedrock/titan-v2 # cheap + fast
summaries: ollama/llama3 # local + free
Runs fully offline with Ollama or llama.cpp. Route different task types to different providers, or race two providers and take the first useful answer. The graph is the constant; the model is a swappable input.
Every reasoning result carries the signals that make it inspectable rather than magical:
confidence — an opaque score between 0.0 and 1.0; below the floor, GraQle refuses instead of guessing.graph_health — whether the graph had enough connected context to answer well.active_nodes — exactly which parts of your system informed the answer.These are not only governance features. They are what lets a human decide whether to act on an answer.
If no LLM backend is configured, GraQle labels its output as a placeholder and does not attach a confidence score — an unconfigured install never looks like a real answer.
Reading is low-stakes. Writing and acting are not. As soon as an agent can edit files, run commands or take production actions, you need something stronger than a good prompt.
graq gate-install # one-time, project-local
This routes native write/edit/bash operations through GraQle's governance gates and adds a permissions backstop to .claude/settings.json. Plans required for risky changes. Trade-secret scanning on commits. Path-traversal hardening on subprocess capture. CG-01 through CG-20 — all on, all auditable.
Governance here is what lets you give agents more autonomy, not less. The gate is the reason a write-capable agent is a reasonable thing to run.
For deployed systems, the same substrate records what your AI decided:
from graqle.governance.runtime import GovernedRuntime
gov = GovernedRuntime(salt="your-deploy-salt")
def score_application(app):
decision = model.predict(app) # your deployed AI, untouched
gov.attest( # <-- the one added line
domain="loan", model_id="credit-risk-v4",
inputs={"applicant_ref": gov.pseudonymize_ref(app.id)}, # PII-safe
output={"decision": decision.label, "reason_code": decision.reason},
)
return decision
Capture is out-of-band — 0 ms added to your write path. Records are canonicalised (RFC 8785), Merkle-rooted (RFC 6962), ed25519-signed and anchored to the public Sigstore Rekor transparency log, so any third party can verify a record without access to your infrastructure, or ours.
graqle govern serve --config graqle.yaml # continuous anchoring worker
graqle govern health # JSON snapshot for any monitor
Same graph, same evidence model, same audit substrate. Most teams start with build-time and never need the second mode — that's fine, and it's why it lives here rather than in the hero.
→ SECURITY.md · Report vulnerabilities to [email protected]
If you operate in a regulated environment, the same substrate produces compliance evidence. If you don't, skip this section — nothing above depends on it.
GraQle is EU AI Act–aligned by design — signals, audit trail and disclosure primitives for your own Article 9 risk-management file. Articles 6, 9, 12, 13, 14, 15, 25, 50 became applicable on 2026-08-02. GraQle is NOT itself a high-risk AI system (no Annex III category applies) and is NOT a GPAI provider under Article 51; we provide evidence inputs, and never say compliant or certified — a CI invariant blocks any release that introduces such a field.
Compliance packs are data, not code — a framework is two files (pack.yaml + schema.json), no Python and no engine change. SOX/COSO ships today as x-sox; ISO/IEC 42001, NIST AI RMF, SOC 2 and HIPAA are authorable the same way. The claim-limits taxonomy records what each decision does not claim.
The free tier is real: the verifier, the runtime attestation path and the continuous anchoring worker are all in the open-source SDK.
The durable return is not the token bill — inference prices keep falling. It is less context reconstruction, fewer architectural mistakes, faster change validation, team knowledge that outlives the session, easier model switching, and safer autonomy when agents start writing.
Token cost is supporting evidence for that, not the reason to adopt: activating a relevant subgraph costs fewer tokens than repeatedly feeding a model whole files. A sourced case study puts a 4-developer team on a 50,000-node codebase at −53% against a flat-file baseline in year one.
→ Read the full case study — math, sources, and a snippet to re-run it on your own numbers.
graq rebuild (--headless / --json, exit codes).Core methods are patent-pending: EP26167849.4 (filed 2026-03-25), EP26162901.8 (CIP), and EP26166054.2 (CogniGraph divisional). The SDK source is fully auditable under the GraQle License — see LICENSE. Reimplementation of the patented methods outside this SDK requires a separate patent license.
→ github.com/quantamixsol/graqle — issues, discussions and contributions welcome.
GraQle is built by Quantamix Solutions. The intelligence that survives when the model, the agent and the interface change.
Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.
{ "mcpServers": { "com.graqle-graqle": { "command": "uvx", "args": [ "graqle==0.27.0" ] } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Graqle ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-08 Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.