Cognipeer Console
Self-hosted AI infrastructure with OpenAI-compatible API, provider routing & resiliency, vector orchestration, files pipeline, guardrails, tracing & observability, and project-level resource management.
Key Features
Enables existing clients to operate as a seamless drop-in replacement, supporting chat, embeddings, streaming, and tool calling.
Routes requests across model providers with built-in fallback handling and health-based routing strategies.
Manages multiple vector databases through a unified control layer, including index lifecycle and operational workflows.
Supports document uploads with optional Markdown conversion, preparing content for RAG-ready ingestion pipelines.
Evaluate content against configurable safety policies with input and output filtering for production AI deployments.
Tracks agent executions, tool calls, and LLM requests with integrated platform-level visibility.
Organise resources, models, and API keys into isolated projects with independent configuration and usage tracking.
Architecture
A fully self-hosted AI gateway built on Next.js 15 with a modular provider system.
Next.js 15 App Router
API routes and dashboard built on Next.js 15 with TypeScript and Mantine v7 UI.
MongoDB with Abstraction Layer
Database abstraction layer that supports future provider changes. Clean separation between storage and application logic.
JWT + Middleware
Edge-compatible JWT auth (jose library). Middleware injects context and enforces feature access on every request.
Provider Registry
Contract-driven provider system with auto-registration. Supports vector, model, and custom domains with form schema rendering.
Quick Start
# Clone and run git clone https://github.com/Cognipeer/cgate.git cd cgate npm install cp .env.example .env.local # Configure MongoDB URI and JWT secret in .env.local npm run dev # Console is now running at http://localhost:3000 # API available at http://localhost:3000/api/client/v1
Cognipeer Console vs Alternatives
| Product | Primary Role | Self-Hosted | Open Source | OpenAI Compatible | Routing / Fallback | Rate Limiting | Caching | Guardrails | Tracing | Vector Ops |
|---|---|---|---|---|---|---|---|---|---|---|
Cognipeer Console | AI Gateway + Control Plane | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
LiteLLM | AI Gateway | ✓ | ✓ | ✓ | ✓ | ✓ | △ | ✕ | △ | △ |
Helicone | Gateway + Observability | ✓ | ✓ | ✓ | △ | △ | △ | ✕ | ✓ | ✕ |
Portkey | Managed AI Gateway | △ | △ | ✓ | ✓ | ✓ | ✓ | ✕ | ✓ | △ |
Cloudflare AI Gateway | Edge AI Gateway | ✕ | ✕ | ✓ | ✓ | ✓ | ✓ | ✕ | ✓ | ✕ |
Kong AI Gateway | Enterprise API Gateway | ✓ | △ | ✓ | ✓ | ✓ | ✓ | ✕ | △ | △ |
Envoy AI Gateway | Kubernetes-native Gateway | ✓ | ✓ | △ | ✓ | ✓ | △ | ✕ | △ | △ |
Langfuse | LLM Observability Platform | ✓ | ✓ | ✕ | ✕ | ✕ | ✕ | ✓ | ✓ | △ |