Every feature, in depth
Simmetric Chat is a batteries-included AI knowledge-base platform. Explore each pillar below.
Hybrid RAG & agent core
The retrieval and reasoning engine at the heart of Simmetric Chat. Every answer is grounded, cited, and reproducible — from ingestion to streaming response.
- Vector search over LanceDB (local) or Qdrant/pgvector/Chroma (config choice, not license-gated)
- PostgreSQL tsvector FTS fused with vector via RRF (k=60)
- Deterministic tiebreaker: score DESC → documentId ASC → chunkIndex ASC
- Automatic FTS-only fallback on embedding-model mismatch (Guard D-01)
- Recursive chunking: 1000 chars, 200 overlap, paragraph-aware
- Xenova all-MiniLM-L6-v2 (384-dim, on-device) or OpenAI text-embedding-3-small
- ReAct orchestrator with plan mode, watchdog & unknown-tool circuit breaker
- Built-in skills: rag_search, workspace_memory, document_temp_process, wiki_query, wiki_write
- Server-side OCR: pdfjs-dist + Ollama vision model (glm-ocr) with approve/reject
- Synthesis: 5-pass entity → summary → BM25 → LLM decision → overview, PHI-gated
Hybrid RAG (RRF)
Vector search (LanceDB default, or Qdrant/pgvector/Chroma) fused with PostgreSQL FTS via Reciprocal Rank Fusion, k=60. Deterministic tiebreaker, per-chunk citations, semantic+keyword tags.
ReAct Agent Orchestrator
Single-call ReAct loop with plan mode, watchdog (wallclock, token, context, loop detection), unknown-tool circuit breaker, and progressive DLP flush via buffered replay.
Multi-LLM with 20 presets
Ollama, OpenAI, Anthropic, OpenRouter, Gemini, plus 20 provider presets (DeepSeek, Mistral, Qwen, xAI and more). Per-chat model resolution, 3-tier graceful fallback, Cmd+K quick-switch palette.
Document ingestion
PDF, DOCX, XLSX, PPTX, MD, CSV, TXT and YouTube transcripts. Recursive chunking (1000 chars, 200 overlap). Xenova local embeddings by default, OpenAI optional.
OCR via Ollama vision
Server-side OCR pipeline: pdfjs-dist renders pages, an Ollama vision model (glm-ocr by default) extracts text. Approve/reject workflow with quality and credibility scoring.
Archives & Wiki
Multi-page markdown knowledge bases with wikilinks. Dedicated agent skills wiki_query (FTS + BFS traversal, depth 3) and wiki_write (preview, dry-run, SSE edit events).
Synthesis pipeline
5-pass entity extraction → summary → BM25 candidate search → LLM decision (CREATE/UPDATE/SKIP/FLAG_CONTRADICTION) → overview. PHI gate blocks non-local egress when required.
Multi-instance scaling
Horizontally scalable behind a load balancer: Redis-backed rate limits, JWT revocation, SSE fan-out relay and distributed locks. pg-boss queue with 8 cron schedulers — no extra infrastructure.
Security & access control
31 permissions across 13 menu sections. IDOR-safe by design. Encrypted, rotation-safe backups with a full inventory of destinations.
- Fine-grained RBAC with workspace + project access grants
- IDOR prevention middleware and constant-time secret comparison
- DLP filter redacts 6 PII classes (email, credit card, SSN, sk-, AKIA, PEM)
- AES-256-GCM data-at-rest encryption with rotation-safe legacy key chain
- Scheduled encrypted backups (Enterprise): Local, S3, S3-compatible, Dropbox, Drive, FTP, SFTP, Email
- Path-traversal guard, streaming SHA-256 checksum, safety backup pre-restore
- JWT + bcrypt auth, sk- API keys, session expiry configurable
- Per-user concurrency and token budgets with graceful degradation
- Full air-gap: Ollama + Xenova + LanceDB, zero outbound traffic
RBAC — 31 permissions
Fine-grained role-based access across 13 menu sections, workspace and project access grants, IDOR-safe middleware, and constant-time secret comparison.
DLP filter
Six PII classes redacted inline: email, credit card, SSN, sk- API keys, AWS AKIA keys, PEM private keys. Applied to both input and output streams behind DLP_ENABLED.
Encrypted backups
Enterprise-gated: scheduled or on-demand AES-256-GCM backups with rotation-safe keys. Unlimited destinations (Local, S3, Dropbox, Drive, FTP, SFTP, Email), retention and point-in-time restore.
Air-gap by design
Ollama LLM + on-device embeddings + LanceDB vectors run fully offline. Package boundaries enforce HTTP-only server↔collector communication for split deployments.
HMAC API keys
sk--prefixed API keys verified with a dedicated HMAC-SHA256 secret (API_KEY_HMAC_SECRET), decoupled from JWT and encryption key rotation.
Integrations
Embed AI where your users already are. Extend the agent with the tools you already own — MCP in both directions.
- Preact IIFE widget in a sandboxed iframe (no allow-same-origin, no top-navigation)
- Per-widget dynamic CORS allowlist and SRI-friendly loader script
- Isolated anonymous sessions (256-bit token, 24h); rate limiting, lead capture and layered workspace access (Enterprise tier)
- MCP Marketplace: curated catalog with verification tiers & health status
- Install MCP servers workspace-scoped, pin per chat via ChatMCPPin
- Expose rag_search and workspace_memory as an MCP server for Cursor / Claude Desktop
- SSE streaming with token, status, citations, plan, wiki_edit and done events
- Cmd+K quick-switch palette and Cmd+Shift+M side-by-side model comparison
Embeddable widget
Preact IIFE in a sandboxed iframe (no allow-same-origin). Isolated anonymous sessions, per-widget CORS allowlist, rate-limited sessions and lead capture. Widget creation is an Enterprise-tier feature.
MCP Marketplace
Curated catalog with verification tiers and health checks. Install workspace-scoped connections, pin per chat via ChatMCPPin, or expose your RAG as an MCP server to IDEs.
SSE chat streaming
Real-time token, status, citations, plan, wiki_edit, and done events over @microsoft/fetch-event-source. Slash /model, Cmd+K palette, Cmd+Shift+M side-by-side comparison.
Bidirectional MCP
Connect external MCP servers as agent skills, or start the server-side MCP endpoint to expose rag_search and workspace_memory to Cursor, Claude Desktop, and other clients.
Webhooks + Web Push
Outbound events signed with HMAC-SHA256 and VAPID Web Push for real-time browser notifications on chat completions and system events. Always-on in Community.
Enterprise
Everything a regulated team needs: SSO, immutable audit logs, white-label, custom agents, priority support — 11 license flags; commodity features always-on in Community (EPA-02).
- SSO via SAML and OIDC
- Immutable audit log with signed webhook dispatch
- Token usage analytics: daily, by model, top users
- HMAC-SHA256 outbound webhooks and VAPID Web Push notifications
- White-label branding across app, widget, and emails
- Custom agents, per-chat model overrides, unlimited MCP connections
- Unlimited backup destinations (Community limit: 1)
- i18n across 8 languages with automated parity checks in CI
Analytics & audit
Token usage dashboards: per day, per model, per user. Event log with webhook dispatch. Immutable INSERT-only audit trail (Enterprise) for compliance evidence.
Enterprise license
Community (AGPL-3.0) vs Enterprise: 11 license flags with commodity features always-on. SSO, SCIM, white-label, unlimited widgets and workspaces — graceful degradation without a key.
i18n — 8 languages
English, Italian, Russian, German, French, Spanish, Chinese and Portuguese. Automated parity checks enforce translation completeness in CI.