# Powabase

> Postgres, RAG, and agents. One backend.

Every project gets its own Postgres, storage, auth, realtime, and an agent runtime. Documents extract, embed, and index on upload. Agents call tools over HTTP or MCP. Self-host it or use ours.

> Full site text for ingestion: https://powabase.ai/llms-full.txt

## What it is

Powabase is an all-in-one development platform for AI-native applications.
Each project gets a fully isolated stack: Postgres + pgvector, GoTrue auth,
object storage, realtime, plus an Agent Runtime, RAG Pipeline, and Workflow
engine.

## Capabilities

### Backend (BaaS)
- Per-project Postgres with Row Level Security and pgvector for vector search.
- GoTrue authentication (email, OAuth, magic links, MFA).
- S3-compatible object storage with signed URLs and CDN.
- Realtime subscriptions over WebSockets (postgres_changes + broadcast channels).
- Direct PostgREST access to your public schema for app data.

### RAG (Retrieval)
- Document ingestion: PDFs, DOCX, images (with OCR), and URLs.
- VLM OCR scoring 91% on OlmOCR-Bench.
- Full RAG pipeline scoring 98.7% on FinanceBench.
- Four indexing strategies: ChunkEmbed, PageIndex (hierarchical tree),
  GraphIndex (entity + cross-reference enrichment), Doc2JSON (structured
  field extraction).
- Four retrieval methods: vector search (pgvector), full-text (BM25),
  hybrid (RRF fusion), tree search (LLM reasoning over PageIndex).
- Cross-encoder reranking (Cohere, Jina, Voyage, others).

### Agents
- ReAct loop with multi-step tool calling and streaming SSE.
- Sessions persist multi-turn state, including reasoning traces and
  retrieved context per turn.
- Hooks and approval flow for human-in-the-loop tool calls.
- Multi-agent orchestrations: a coordinator delegates to specialised
  entity agents and synthesises their replies.

### Tools
- Built-in: db query/write, HTTP request, code execute, storage read/write,
  web search, web scrape.
- Custom tools via HTTP endpoints with JSON Schema input definitions.
- MCP server integrations for runtime tool discovery.

### Workflows
- DAG-based automation with blocks: triggers, conditions, agent calls,
  HTTP, code execution, platform_api, response.
- Visual builder + REST API. Deployed workflows expose an HTTP endpoint
  with webhook, cron, and interval triggers.
- Natural-language Copilot generates and edits workflow graphs from
  plain-English descriptions.

### LLM providers
OpenAI, Anthropic, Google, Mistral, and open-source models via OpenRouter.
Bring your own keys; keys are stored per-project, encrypted at rest. BYOK is
optional — you can also skip keys and pay for inference from your Powabase credits.

### Hosting & deployment options
Powabase offers two deployment models:
- **Powabase Cloud** — fully managed at app.powabase.ai.
- **Self-hosted (open source)** — Powabase is open source under Apache-2.0 at
  https://github.com/powabase-ai/powabase. Run the full single-project stack on
  your own infrastructure with one `docker compose up`. Enterprise adds a
  commercially-licensed, supported edition with SLAs, a Kubernetes Helm chart,
  and private managed hosting (https://powabase.ai/pricing#enterprise).

## Pricing

Powabase uses usage-based pricing, not per-seat. Each monthly plan converts its
fee into a pool of credits you spend on actual usage — compute hours, per-call
actions, active users, and storage — and unused credits roll over month to month.
Paid plans add prepaid credits and progressively cheaper unit rates; underneath
every plan is the same pay-as-you-go meter.

Plans:

- **Free** — $0. All platform features. Pay-as-you-go on usage with no
  monthly minimum and no commitment. $10 in free credits on sign-up.
  Free projects run on Sandbox compute only.
- **Self Serve** — $25 / month. $25 in monthly credits to spend on
  compute hours, per-call costs, MAU overages, and storage. Pick any compute
  tier (Sandbox through Foundry). Up to 25% cheaper per-call costs and 15%
  cheaper per-hour compute vs. Free. Email support.
- **Scale** — $300 / month. $300 in monthly credits. Up to 50% cheaper
  per-call costs and 20% cheaper per-hour compute vs. Free. Lowest
  overage rates. Priority live support.
- **Enterprise** — Custom. Managed on Powabase Cloud or private hosting
  in your AWS / GCP / Azure / on-prem environment. $500 in platform
  credits to start. SOC 2, DPA, MSA, regional residency, SSO, RBAC,
  audit logs, BYO KMS / IdP, air-gapped supported, dedicated solutions
  engineer.

See https://powabase.ai/pricing for the live pricing matrix.

## Project isolation

Each Powabase project is a dedicated stack with its own resources and
backups. There is no shared vector DB, no noisy neighbours, and no
cross-tenant traffic. The control plane manages routing and authentication;
the data plane is isolated per project.

## Integrations — coding agents & vibe-coding platforms

Powabase connects to the AI coding tools you already use. Coding agents
(Claude Code, Codex, Antigravity, OpenCode, Replit) install the Powabase
Agent Skill — `npx skills add powabase-ai/agent-skills` — and build a full
backend from a prompt. Browser-based vibe-coding platforms (Replit, Lovable,
v0, Base44, Bolt.new) connect over the REST API using the Connect dialog's
Project URL + Service Role (Secret) Key (server-side only; the Anon key is the
client-side, RLS-respecting key). A third option is the auth-connection guide
at https://docs.powabase.ai/guides/auth-connection. MCP support is coming soon.
Per-tool connector pages with quick starts and example prompts live at
https://powabase.ai/integrations.

## Blog

Recent writing from the Powabase team (full text at https://powabase.ai/llms-full.txt):

- [Enterprise AI Workflow Automation: The Most Common Use Cases](https://powabase.ai/blog/enterprise-ai-workflow-automation-the-most-common-use-cases/) — Fri Jul 24 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Explore the most common enterprise AI workflow automation use cases across customer service, finance, HR, IT, and supply chain — plus ROI and implementation tips.
- [Why Vibe Coding Platforms Need a Robust BaaS](https://powabase.ai/blog/why-vibe-coding-platforms-need-a-robust-baas/) — Thu Jul 23 2026 00:00:00 GMT+0000 (Coordinated Universal Time). BaaS for vibe coding isn't optional—it's essential. Discover why vibe coding platforms need a solid backend foundation to scale, sync, and succeed.
- [Backend as a Service: Beat the AI Cleanup Economy](https://powabase.ai/blog/backend-as-a-service-beat-the-ai-cleanup-economy/) — Thu Jul 23 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Agencies pay $200–400/hr to fix unreviewed AI code. See how an agent-native backend as a service ships correct schemas, RLS, and migrations — and how to sell managed hosting.
- [What Regulated Enterprise AI Buyers Really Care About](https://powabase.ai/blog/what-regulated-enterprise-ai-buyers-really-care-about/) — Tue Jul 21 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Regulated enterprise AI buyers weigh compliance, data sovereignty, auditability, and lock-in over raw model accuracy. Here's what they evaluate—and the red flags to avoid.
- [Custom AI Deployment in Enterprises: A Practical Guide](https://powabase.ai/blog/custom-ai-deployment-in-enterprises-a-practical-guide/) — Thu Jul 16 2026 00:00:00 GMT+0000 (Coordinated Universal Time). A practical guide to custom AI deployment for enterprises: fine-tuning vs RAG, on-premise vs cloud vs sovereign, security, compliance, and LLMOps.
- [Unified BaaS vs. Compose-Your-Own Stack: Head-to-Head](https://powabase.ai/blog/unified-baas-vs-compose-your-own-stack-head-to-head/) — Wed Jul 15 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Unified BaaS vs compose-your-own stack — which wins for your project? We compare cost, flexibility, and speed so you can choose with confidence.
- [Token Efficiency: How to Design Efficient AI Systems](https://powabase.ai/blog/token-efficiency-how-to-design-efficient-ai-systems/) — Wed Jul 15 2026 00:00:00 GMT+0000 (Coordinated Universal Time). A step-by-step guide to token efficiency: measure usage, tighten prompts, add caching, route models, and cut LLM costs while keeping AI systems fast.
- [Build vs Buy Enterprise AI: A Decision Framework](https://powabase.ai/blog/build-vs-buy-enterprise-ai-a-decision-framework/) — Tue Jul 14 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Build vs buy enterprise AI? Use this framework to weigh custom AI workflows against off-the-shelf platforms on cost, lock-in, compliance, and orchestration.
- [LangChain Alternative in 2026: The Production RAG Stack](https://powabase.ai/blog/langchain-alternative-in-2026-the-production-rag-stack/) — Wed Jul 08 2026 00:00:00 GMT+0000 (Coordinated Universal Time). A production RAG audit says you don't need LangChain in 2026. The LangChain alternative: native SDK + Postgres/pgvector + a thin router you don't build yourself.
- [Backend for AI Apps: Why Vibe-Coded Apps Need a Governed BaaS](https://powabase.ai/blog/backend-for-ai-apps-why-vibe-coded-apps-need-a-governed-baas/) — Wed Jul 08 2026 00:00:00 GMT+0000 (Coordinated Universal Time). 93% of teams hit an AI infra incident last year. See why a backend for AI apps needs tenant isolation, RLS, and validation as governed BaaS primitives.
- [Postgres MCP Server Comparison: Why 2–10 Tool Servers Fail Coding Agents](https://powabase.ai/blog/postgres-mcp-server-comparison-why-2-10-tool-servers-fail-coding-agents/) — Wed Jul 01 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Our Postgres MCP server comparison reveals why 2–10 tool servers break coding agents—and what to look for in a solution that actually works.
- [Backend for Claude Code: Why Supabase Keeps Breaking (and What Agent-Native Fixes)](https://powabase.ai/blog/backend-for-claude-code-why-supabase-keeps-breaking-and-what-agent-native-fixes/) — Wed Jul 01 2026 00:00:00 GMT+0000 (Coordinated Universal Time). Using Supabase as your backend for Claude Code? Learn why it keeps breaking and which agent-native alternatives actually hold up under AI-driven workloads.

## Key pages

- [Full text for LLMs](https://powabase.ai/llms-full.txt) — every section of the site concatenated for ingestion
- [Home](https://powabase.ai/)
- [Integrations](https://powabase.ai/integrations) — connect Claude Code, Codex, Antigravity, OpenCode, Replit, Lovable, v0, Base44, and Bolt.new
- [Blog](https://powabase.ai/blog/) — engineering and product writing from the Powabase team
- [Pricing](https://powabase.ai/pricing)
- [Free MVP](https://powabase.ai/free-mvp/) — plan-gated program where Powabase's forward-deployed engineers build a working MVP for customers committing to an annual Scale or Enterprise plan. $500 in platform credit on selection.
- [Docs](https://docs.powabase.ai/concepts/platform-overview)
- [Privacy Policy](https://powabase.ai/privacy)
- [Terms of Service](https://powabase.ai/terms)

## Contact

- Discord community: https://discord.gg/k8W2A9KRtc
- Schedule a demo: https://calendly.com/hello-powabase/powabase-demo
- Apply for Free MVP build: https://calendly.com/hello-powabase/free-mvp
- App: https://app.powabase.ai
- Privacy / legal: hello@powabase.ai

## Crawler note

All major AI search and indexing crawlers are explicitly allowed via
robots.txt. https://powabase.ai/sitemap.xml lists every public route. Pages are
fully prerendered as static HTML — no JavaScript required for content.

_Generated from https://powabase.ai._