AI Meets Your Data Layer
AI that queries your databases natively, with the same auth and permissions as the user.
AI That Lives Next to Your Data
Adam sits alongside your database endpoints as siblings in the same system, querying your data natively, governed by the same permissions as the user.
ADAM queries all your data natively via MCP. No glue code. No separate systems. One unified access layer.
Provider-Agnostic AI
OpenAI, Anthropic, Ollama, OpenRouter — one API, swap providers without changing code. Self-host with Ollama for air-gapped deployments.
RBAC-Scoped Querying
AI queries your databases via MCP tool calling, constrained by user permissions. No privilege escalation — the AI has exactly the same access as the user.
Custom Skills & Templates
Give your AI domain expertise with runtime-loadable skills. Version prompts, swap templates mid-conversation, no redeployment needed.
Your AI. Your Databases. One Platform.
Other products give you an LLM gateway or a database proxy. Eden gives you both — and because they share the same system, capabilities emerge that neither can offer alone.
Multi-Provider LLM Access
Four LLM providers normalized through a single abstraction layer. Swap providers without changing a line of code.
- OpenAI, Anthropic, Ollama, OpenRouter
- Streaming & tool calling
- Custom base URL support
Database Proxying & Pooling
Redis, PostgreSQL, and more register as endpoints in the same system alongside your AI models.
- Connection pooling
- Zero-config switching
- Same API surface
Shared Auth & RBAC
One identity system for AI and database access. AI operates under the exact same permissions as the requesting user.
- No privilege escalation
- Organization-scoped credentials
- Permission-verified on every request
Custom Templates & Skills
Define prompt templates stored in memory and toggle domain expertise on or off without redeployment.
- Versioned prompts
- Runtime-loadable skills
- Swap templates mid-conversation
Provider-Agnostic AI Access
One API, every model. Zero vendor lock-in.
| Provider | Default Model | Streaming | Tool Calling |
|---|---|---|---|
| OpenAI | gpt-5.2 | ||
| Anthropic | claude-sonnet-4-5 | ||
| Ollama | llama3.2 | ||
| OpenRouter | moonshotai/kimi-k2 |
Your AI, Your Permissions. Query Anything You're Allowed To.
Because the LLM and database endpoints live in the same system, AI-powered database querying isn't a bolt-on integration — it's a natural consequence of the architecture.
How MCP Tool Calling Works
User sends chat request with database endpoint references
Eden connects to each endpoint's MCP server and discovers tools
Tool definitions sent to LLM alongside the conversation
LLM decides whether to call tools based on context
Eden verifies RBAC: does this user have access?
Tool result fed back into conversation (max 12 iterations)
Same permissions as the user. Always.
RBAC-Scoped AI Access
The AI operates under the exact same permissions as the requesting user. No privilege escalation — because the AI is authenticated through the same identity system.
- Read-only if user is read-only
- Invisible endpoints stay invisible
- Same identity system for AI and data
Natural Language Queries
Ask questions about your data in plain English. AI queries your databases directly through MCP, constrained by your RBAC permissions.
- No SQL required
- Context-aware responses
- Multi-database support
MCP Tool Orchestration
Up to 12 tool passes per turn. AI discovers available tools, calls databases mid-conversation, and feeds results back into the conversation.
- Paginated tool discovery
- Namespaced identifiers
- Cached tool snapshots
Tool Execution Metrics
Every tool call is instrumented with OpenTelemetry. Track attempts, failures, and latency per tool and per server.
- Attempt & failure counters
- Latency histograms
- Per-tool observability
Your Database Talks. Eden Listens.
Zero-instrumentation analytics that sits in the proxy layer. No code changes, no agents to deploy, no SDK to integrate. Enable a feature flag and insights start flowing.
Automatic Anti-Pattern Detection
Eden watches your traffic and identifies performance anti-patterns in real time at two levels: per-connection burst analysis and per-endpoint aggregate analysis.
- N+1 query detection
- Hot key concentration
- Unbounded range warnings
PII Exposure Alerts
Real-time detection of personally identifiable information flowing through your data layer. 9 PII types detected with automatic redaction before storage.
- SSN & credit card detection
- API key & password scanning
- Email, phone, IP detection
13-Rule Recommendation Engine
Not just metrics, but actionable recommendations with confidence scoring, severity classification, and estimated monthly cost savings.
- Pattern & context rules
- Confidence-scored output
- Cost savings estimates
Real-Time Streaming Analytics
SSE-powered real-time monitoring with per-endpoint snapshots every 15 seconds. Anomaly transitions emit immediately.
- Zero-overhead when unused
- Anomaly-only filtering
- 64-event broadcast buffer
Detected Anti-Patterns
Automatically flagged with confidence scores and actionable recommendations.
N+1 Queries
5 repeated commands
Hot Keys
10 accesses per key
KEYS Command
Any occurrence
Unbounded Range
Any occurrence
Large Responses
> 64 KB
High Fanout
100+ keys avg
High Error Rate
> 10% rate
Missing TTLs
> 80% no TTL
AI in Your Terminal. Connected to Your Data.
Eden Chat is a TUI-based chat application that brings all of Eden's AI capabilities into an interactive experience. Because it runs inside Eden, it can query your databases natively.
Features
- Multi-provider support — Anthropic, OpenAI, Ollama, OpenRouter
- Auto-endpoint discovery from your Eden deployment
- Database querying via MCP with same RBAC as your user account
- Real-time streaming with token-by-token rendering
- Conversation persistence with sequence tracking
- Skill system — toggle domain expertise on/off
- Tool approval gates for safe AI execution
- Model override — switch models mid-conversation
Built-in Tools
eden_curl
Make authenticated API calls to Eden service from within AI conversation
load_skill
Dynamically load and enable a skill at runtime
show_form
Display interactive forms dynamically within the terminal
Sign in to try Eden Chat directly in your browser — connected to your real data with your real permissions.
Ready to Connect AI to Your Data?
Join forward-thinking companies using ADAM to unify their AI and database infrastructure. Same auth. Same RBAC. Same API.