Now in early access

The AI infrastructure
platform
for builders.

Train models, deploy agents, manage infrastructure, and ship AI products — from one unified platform. Zero to production in under 5 minutes.

< 50msp99 latency
5 minzero to prod
99.9%uptime SLA
2,847req/s peak throughput
< 50msp99 inference latency
99.9%platform uptime
5 minzero to production
6unified products
deployments per day
2,847req/s peak throughput
< 50msp99 inference latency
99.9%platform uptime
5 minzero to production
6unified products
deployments per day

See it in action.

Real infrastructure, real agents, real results — running right now.

01

AI Platform

vLLM-based inference with full fine-tuning pipelines and sub-50ms p99 latency.

inference throughput2,847 req/s
< 50ms
p99
99.9%
uptime
vLLM
engine
02

Agent Console

Autonomous agents with tiered memory, MCP tool use, and full task observability.

Indexing knowledge baserunning
Deploy api-service@2.1.0done
Generating proto stubsrunning
Running eval suitequeued
03

Knowledge Engine

Hybrid BM25 + vector search, web crawling, and multi-source document ingestion.

hybrid BM25 + vector search...
api-service proto spec
proto
0.97
deploy runbook v3.md
docs
0.91
agent memory schema
schema
0.88
01

AI Platform

vLLM-based inference with full fine-tuning pipelines, model evaluation, and sub-50ms p99 latency at scale.

inference throughput2,847 req/s
< 50ms
p99
99.9%
uptime
vLLM
engine
02

Agents

Autonomous agents with tiered persistent memory — short-term context, long-term pgvector, and shared team memory.

Indexing knowledge baserunning
Deploy api-service@2.1.0done
Generating proto stubsrunning
Running eval suitequeued
03

Knowledge Engine

Hybrid BM25 + vector search with web crawling, multi-source ingestion, and real-time auto-sync from your codebase.

hybrid BM25 + vector search...
api-service proto spec
proto
0.97
deploy runbook v3.md
docs
0.91
agent memory schema
schema
0.88
04

Dev Center

Service catalog, Helm/K8s deployments, secrets management, and auto-generated API docs from proto contracts.

22s
zero to deployed
Deployments
05

Infrastructure

EKS orchestration, Pulumi IaC, and full-stack observability with Grafana, Prometheus, and Loki built-in.

EKS
Orchestration
Pulumi
IaC
Grafana
Observability
Prometheus
Metrics
06

App Builder

Ship AI-powered interfaces with drag-and-drop components wired directly to your Riven backend and agents.

Component palette · 42 blocks
ChatUIchat-interface
DataTableagent-output
MetricCardlive-stats

From code to production in minutes

01

Init and scaffold

Run riven init, then riven service new to scaffold a gRPC service with proto contracts, types, and docs auto-generated.

02

Publish and deploy

Run riven publish to build and push to ECR, then riven dev-center to roll out via Helm. No YAML, no ops.

03

Observe and iterate

Full-stack observability via Grafana and Prometheus. Run riven doctor to diagnose issues. Agents can write and deploy the next version.

A system that compounds
with every cycle

Every service you deploy auto-generates proto contracts. Every contract generates docs and types. Every doc is indexed into the Knowledge Engine. Every agent has MCP access to that knowledge — and writes the code that deploys the next service.

Code → Protobuf contracts
Proto → Auto-generated docs
Docs → Knowledge graph
Agents → Write more code
Code
Proto
Docs
Graph
MCP
Agents

The humans behind Riven

A small, focused team building the infrastructure layer we always wished existed. Fully remote.

Join our team
GH
Gal Hindi
Founder & CTO
Gal Hindi
Founder & CTO

Software engineer, architect, and ML engineer. Built Riven from the ground up — from the proto-first service mesh to the vLLM inference layer. Obsessed with eliminating the glue code between AI tools.

Formerly at linkedin.com/in/gal-hindi
OP
Orel Perez
Software Engineer
Orel Perez
Software Engineer

Full-stack engineer helping shape the Riven platform and product experience. Focused on making the developer experience feel effortless — from CLI to dashboard.

Formerly at linkedin.com/in/orelperez

Latest from the lab

View all

Pay for a seat. Meter the work.

A seat covers the platform. Agents bill on what they actually consume — tokens and sandbox-hours. No surprises.

Free

For individuals exploring autonomous dev.

$0
  • Up to 3 seats
  • Full CLI access
  • Dev Center (1 service)
  • Community support
  • Shared infrastructure
Included monthly
1M agent tokens / mo
3 sandbox-hours / mo
Hard cap — no overage
Most Popular

Team

For teams shipping with agents that execute.

$99/seat/mo
billed annually
  • Up to 25 seats
  • Unlimited projects
  • Agent deployments
  • SSO / SAML
  • Knowledge Engine
  • Email support
Included monthly
15M agent tokens / seat
30 sandbox-hours / seat
then $12 / 1M tokens · $0.35 / sandbox-hr

Pro

For orgs running agents at scale.

$199/seat/mo
billed annually
  • Up to 100 seats
  • Everything in Team
  • SSO + SCIM
  • Role-based access (OpenFGA)
  • Knowledge graph + context lake
  • Priority support · 99.8% SLA
Included monthly
50M agent tokens / seat
80 sandbox-hours / seat
then $9 / 1M tokens · $0.28 / sandbox-hr

Enterprise

Committed volume, dedicated infra, full security.

Custom
  • Unlimited seats
  • VPC-isolated / BYOC
  • SAML · SCIM · directory sync
  • SOC 2 · DPA · 99.95% SLA
  • Named solutions engineer
Included monthly
Committed token volume
Dedicated machine pools
Volume pricing from $6 / 1M tokens

Stay ahead of the curve

Engineering deep-dives, AI infra insights, and product updates — straight to your inbox. No noise.

Browse the blog

Unsubscribe any time. No spam, ever.