Architectural Blueprints.Workflows & Customer Guide.
A comprehensive, transparent guide to how MithunAI works, what you do as a customer, and what our engine does behind the scenes.
Explore our end-to-end system topology, compile-time security invariants, syntax-aware AST ingestion pipelines, and honest abstention guarantees designed for technical buyers and non-technical stakeholders alike.
Unified high-throughput proxy with semantic caching, dynamic routing & token firewall.
Visual graph orchestration for multi-agent loops, sandboxed tools & human verification.
Read-only context server for Claude Desktop, Cursor, and Windsurf IDEs.
Continuous git repository ingestion with branch patterns and glob filters.
Compile-time OrganizationScope injection guarantees zero cross-tenant leakage.
Parses code trees, Markdown, and technical manuals without tearing scope.
Every answer is constructed strictly from retrieved evidence with source anchors.
Deterministic refusal when evidence is absent, eliminating plausible hallucinations.
Deploy on private AWS, GCP, or on-premises Kubernetes with zero telemetry.
Lightning-fast Server-Sent Events delivering token streams with minimal latency.
Unified high-throughput proxy with semantic caching, dynamic routing & token firewall.
Visual graph orchestration for multi-agent loops, sandboxed tools & human verification.
Read-only context server for Claude Desktop, Cursor, and Windsurf IDEs.
Continuous git repository ingestion with branch patterns and glob filters.
Compile-time OrganizationScope injection guarantees zero cross-tenant leakage.
Parses code trees, Markdown, and technical manuals without tearing scope.
Every answer is constructed strictly from retrieved evidence with source anchors.
Deterministic refusal when evidence is absent, eliminating plausible hallucinations.
Deploy on private AWS, GCP, or on-premises Kubernetes with zero telemetry.
Lightning-fast Server-Sent Events delivering token streams with minimal latency.
What You Do vs. What MithunAI Does Deeply
You provide the knowledge and choose your channels. MithunAI handles the complex AST parsing, secret redaction, dense vector math, security guards, and citation verification automatically.
Knowledge Ingestion
Setting up your unified company documentation and repository index.
Paste your GitHub repo URL or upload your PDFs and docs.
Takes under 60 seconds. No manual chunking, no embedding configuration, no infrastructure provisioning.
Syntax-aware AST parsing & pgvector HNSW indexing.
Tree-sitter extracts code structures, entropy scanners redact credentials, GatewayEmbedder generates vectors, and pgvector builds partition graphs.
Deployment & IDE Setup
Making answers reachable to your engineers, support staff, and visitors.
Add MCP config to Cursor or paste the widget script tag.
One JSON file in .cursor/mcp.json or one script tag on your public documentation site.
Perimeter defense & identity token minting.
Enforces request-time HTTP Origin allowlists, assigns non-human WIDGET_VISITOR principal roles, and isolates visitor sessions.
Querying & Verification
Receiving answers you can verify against source code and documentation.
Ask questions naturally in plain language or code.
Query how functions work, ask policy details, or request troubleshooting steps.
Reciprocal rank fusion & ADR 0010 grounding check.
Fuses BM25 and vector search. If verified, streams answers with exact line citations. If missing, honestly declines rather than hallucinating.
Security & Support
Maintaining complete control, audit logs, and compliance.
Review audit logs and triage unanswered questions.
Inspect where your docs have gaps and invite support staff when needed.
Compile-time tenancy & consented support sessions.
Applies unalterable SQL AST invariants, guarantees zero outbound telemetry, and enforces time-limited ActorType.SUPPORT sessions.
Enterprise System Architecture & Data Flow
Detailed technical schematics showing how data moves from customer sources into secure partitions, and how queries are evaluated against strict grounding invariants.
End-to-End Enterprise Architecture Topology
- • Developer IDE (MCP)
- • Web Widget (.js)
- • REST / SSE Stream
- • Admin Console
- • Origin Allowlist
- • Entropy Redactor
- • Prompt Firewall
- • Bearer Token Auth
- • < 45ms Semantic Cache
- • Tree-sitter AST
- • BM25 + Vector RRF
- • ADR 0010 Grounding
- • pgvector HNSW
- • OrganizationScope
- • Redis Sessions
- • Zero Egress VPC
Deterministic Grounding & Honest Abstention Flow (ADR 0010)
Hybrid RRF searches indexed AST chunks in tenant-scoped partition.
assess_evidence() calculates score against 0.850 strict threshold.
Every Platform Feature, Architecturally Explained
Explore how each delivered capability in the MithunAI platform works, what you do as a customer, and the architectural guarantees that enforce it.
Universal Source Ingestion
WHAT YOU DO (CUSTOMER EXPERIENCE)
Customer connects a GitHub repo URL, documentation domain, or uploads PDF and Word files through the console or API.
WHAT MITHUNAI DOES DEEPLY (ENGINE AUTOMATION)
Engine automatically parses syntax trees using Tree-sitter, strips secrets via Shannon entropy scanners, generates embeddings, and indexes into pgvector.
ARCHITECTURAL IMPLEMENTATION & CODEBASE LOCATION
Four native connectors unified behind a single SourceConnector port. Ingestion jobs are asynchronous Celery tasks with SHA-256 content deduplication.
Key Architecture Decision Records (ADRs)
Every critical security boundary and product invariant in MithunAI is backed by an authoritative Architectural Decision Record.
Honest Abstention as Default Engine Policy
Establishes that the answering engine must explicitly state "I do not know" when the indexed corpus lacks sufficient evidence, rather than extrapolating or guessing.
Widget Visitors as Non-Human Principals
Defines widget deployments as non-human principals authorized through the existing pipeline. Request-time origin allowlists stop cross-site embedding attacks.
Read-Only Model Context Protocol Tool Server
Guarantees that external IDE clients cannot execute write, delete, or mutation requests over MCP. Tools are strictly confined to reading indexed knowledge.
Consented Read-Only Support Access Sessions
Allows MithunAI support engineers to assist customers only with explicit opt-in consent. Zero credential sharing; conversations remain private; all actions logged.
Boundaries that are enforced, not documented
The platform is built as layered modules with a dependency rule that a linter checks on every change. The foundation layer imports nothing from the layers above it, so the platform core cannot come to depend on the features built on top of it.
The module dependency rule
Each layer may depend only on those listed beside it. The foundation depends on nothing.
experiencedepends onplatform, knowledge, ai, agents, workflowworkflowdepends onplatform, ai, knowledge, agentsagentsdepends onplatform, ai, knowledgeknowledgedepends onplatform, aiaidepends onplatformplatformdepends onnothing
Checked by a linter
The import rule is machine-enforced in continuous integration, not left to review.
Every capability has an API
Each capability is reachable by a client other than our own interface, so the platform is integrable rather than a closed application.
The transport holds no logic
The HTTP layer parses, calls the module that owns the capability, and serialises. There is no behaviour in it that a reviewer would have to find twice.
Deployable where your data has to live
The platform runs as a containerised deployment, so it can be operated in an environment you control rather than only as a hosted service.
Where a grounded assistant earns its place
These are the workloads the delivered platform supports today: grounded question answering over knowledge you connect, inside an organisation boundary.
Codebase-Grounded Lookups in Cursor & Claude
Engineers query internal repository architecture without switching context. MithunAI indexes syntax-preserving AST chunks, code trees, and design RFCs into tenant-isolated pgvector tables.
// packages/gateway/src/auth/jwt.ts:42
export async function verifyTenantToken(req: Request) {
const scope = compileOrganizationScope(req.headers);
return jwt.verify(req.token, scope.publicKey, {
algorithms: ['RS256'],
issuer: `https://auth.internal/${scope.orgId}`
});
}Technical documentation assistance
Answer product and API questions from your own documentation, with citations a reader can follow back to the page — and an abstention when the docs genuinely do not say.
Engineering knowledge retrieval
Connect repositories and internal documentation so engineers can ask questions across them without the answer inventing an API that does not exist.
Support enablement
Give a support team a grounded assistant over the same documentation the product ships, where every answer shows its evidence.
Regulated and multi-tenant environments
Operate one platform across organisations where isolation, authorization and an audit record are conditions of running at all.
Technical questions, answered directly.
Everything an enterprise architect or security officer needs to verify before deploying MithunAI.
Connect your documentation. Give your customers and teams answers they can check.
MITHUNAI is in active development toward its first release. If you are evaluating how your organisation will answer questions from its own knowledge, we would like to hear what you need.