Skip to main content
Xcapit

Xcapit Labs

7 products built from real client engagements

Bonum, Privacy, Shelter, ArgenTor, AiSec, OrchestAI, xNinja: the SaaS layer we built by solving real client problems first, then turning them into product. Same engineers, same standards, same ISO 27001.

OrchestAI multi-LLM orchestration platform with signed audit chain and on-premise deployment

OrchestAI

OrchestAI is Xcapit's enterprise platform for multi-LLM orchestration with governance. Route requests across Claude, GPT, Gemini, and Ollama with cost-optimized strategies, signed HMAC-SHA256 audit chains for tamper-evident compliance, versioned agent catalogs with promotion gates, and full on-premise deployment. Data never leaves your datacenter.

Key Features

  • Multi-LLM routing (Claude, GPT, Gemini, Ollama)
  • HMAC-SHA256 signed audit chain
  • On-premise deployment (Docker/K8s)
Multi-LLM
LLM Router
HMAC
Audit Chain
On-Prem
Deployment
AI
Versioned Agents
Technology Stack
PythonFastAPINext.jsPostgreSQLChromaDBDockerKubernetes
XNinja automated pentest platform — AI agents orchestrating a multi-tool scanning engine

XNinja

XNinja is a multi-agent SaaS platform for automated penetration testing for enterprises and SMEs. AI agents orchestrate a multi-phase DAG engine — 8 default tools such as Nmap, Nuclei and TestSSL, plus a 77-integration catalog — and map findings to 10 compliance frameworks, from ISO 27001, NIS2 and BSI IT-Grundschutz to GDPR, TISAX and SOC 2.

Key Features

  • Automated Penetration Testing
  • 5 Compliance Frameworks
  • Multi-Tenant Architecture
10
Compliance Frameworks
77
Integration Wrappers
PDF/DOCX
PDF/DOCX Reports
AI
AI Agents
Technology Stack
AngularDjangoPostgreSQLpgvectorCeleryNmapNucleiRedis
Bonum closed-loop digital wallet — Company, Employee, and Local Business ecosystem

Bonum

Bonum is a closed-loop digital wallet SaaS platform for corporate benefits. Companies distribute non-remunerative benefits digitally, employees pay via QR at affiliated local businesses, and the community benefits from a virtuous economic cycle. The platform provides full traceability, saves 80% of administrative time, and delivers 35% more effective value to employees.

Key Features

  • QR payments at local businesses
  • SaaS admin panel with analytics
  • Multi-tenant architecture
5
Implementations
10K
Town population
35%
More purchasing power
80%
Time saved
Technology Stack
React NativeNode.jsTypeScriptPostgreSQLCloud SaaS
Shelter programmable aid distribution — Treasury to Smart Contract to Beneficiaries to Mobile Money

Shelter

Shelter is Xcapit's own product for distributing aid and subsidies end to end: batch registration from phone numbers, rules in smart contracts, stablecoins to a non-custodial SMS wallet, and use at merchants or cash-out via M-Pesa, all auditable. Backed by UNICEF Venture Fund and Stellar Development Foundation, a Digital Public Good, with pilots in 3 countries, 319 beneficiaries, 100% completion and on-chain settlement in under 2 minutes.

Key Features

  • Configurable disbursement rules
  • Multi-chain smart contracts (EVM)
  • Real-time tracking & traceability
319
Beneficiaries reached
3
Countries
<2min
Settlement time
100%
Completion rate
Technology Stack
SolidityEVMCeloReact NativeNode.jsTypeScriptPostgreSQL
Xcapit Privacy dashboard

Privacy

Xcapit Privacy is a platform for machine learning on data that remains encrypted at all times. Using Fully Homomorphic Encryption (CKKS scheme), organizations can collaboratively train AI models — for fraud detection, medical research, risk analysis — without ever exposing their sensitive data. Not even the platform can see it.

Key Features

  • 256-bit FHE encryption
  • Blockchain governance (Arbitrum)
  • 15+ ML algorithms on encrypted data
559+
Automated tests
15+
ML algorithms
256-bit
FHE security
42
Dashboard pages
Technology Stack
TenSEALCKKS FHEFastAPIArbitrumReactPostgreSQLDocker
ArgenTor multi-agent AI orchestration with WASM sandbox and MCP protocol

ArgenTor

ArgenTor is an intelligent multi-agent AI framework built entirely in Rust. ReAct reasoning, code intelligence with AST analysis for 4 languages, precise diffs, 25+ rule code review, automated TDD, and autonomous dev teams with 8 workflows. Cost-aware model routing across 14 LLM providers, A2A protocol, WASM sandbox, and ISO 27001/42001 compliance. 14 crates, 1514 tests, and 85K+ lines of code.

Key Features

  • WASM-sandboxed plugin execution
  • Centralized MCP protocol proxy
  • Human-in-the-loop approval workflows
14
Modular crates
1514
Passing tests
8
Communication channels
4
Compliance standards
Technology Stack
RustTokioWASMwasmtimeMCP ProtocolDocker
AiSec AI agent security analysis with 35 specialized agents

AiSec

AiSec is an AI agent security analysis framework with 35 specialized agents that scan, detect, and auto-remediate vulnerabilities across AI systems. Featuring Docker-sandboxed execution, AI-CVSS scoring, policy-as-code governance, and SARIF/CI integration. Validated through the OpenClaw audit where it found 63 findings — 4.2x more than traditional scanners.

Key Features

  • 35 specialized security agents
  • Docker-sandboxed execution
  • Auto-remediation engine
35
Security agents
250+
Vulnerability detectors
8
Compliance frameworks
4min
Average scan time
Technology Stack
PythonDjangoDockerKubernetesFalcoeBPFSARIF