Deploy Claude agents to production. Your server, your sandbox, your VPC. Self-host or let us manage.
The Claude Agent SDK isn't just an API client — it's a full agent runtime. Teams are ripping out LangChain, custom harnesses, and hand-rolled tool systems and replacing them with a CLAUDE.md and the SDK.
The punchline: If Claude Code is your agent runtime, you still need production infrastructure around it. That's Ash.
The agent reads and writes files as working memory. Persistent, searchable, diff-able. No vector DB needed.
Skills are markdown prompts that compose naturally. No JSON schema, no serialization overhead.
Plain markdown in your repo. Version-controlled with git. Reviewed in PRs. No proprietary config.
Model Context Protocol gives agents access to databases, APIs, and services through a standard interface.
Hosted platforms charge you a premium to run agents on their infrastructure. With Ash, you run everything on your own cloud—your AWS credits, your VPC, your rules.
Run on your existing AWS, GCP, or Azure accounts. No markup on compute. Use reserved instances, spot pricing, and existing commitments.
Agent conversations, tool outputs, and session data stay in your infrastructure. Meet compliance requirements without trusting a third party.
Inspect, audit, extend, and modify the runtime. No black boxes. Fork it, patch it, contribute back. Open source under BSL.
Your MCP servers run inside your VPC alongside your agents. No need to expose databases, APIs, or internal tools over the public internet.
Your agents run on standard infrastructure. Switch clouds, go multi-region, or run on-prem. If we disappear tomorrow, your agents keep running.
Third-party managed
Your infrastructure
Hosted agent platforms create a new dependency you don't need. You already have cloud infrastructure. You already have security policies. Ash works with what you have—not instead of it.
CLAUDE.md # System prompt
.claude/
settings.json # Tool permissions
skills/
search-docs/SKILL.md # Reusable workflow
escalate/SKILL.md # Reusable workflow
.mcp.json # MCP servers
setup.sh # Init scriptMarkdown, JSON, and bash. That's it.
DB schema, state machine, checkpoint/restore, forking
Backpressure, reconnection, heartbeats, fan-out
Process isolation, warm cache, idle sweep, cleanup
Routing, auth, validation, error handling, docs
OAuth, key rotation, per-session scoping
Event logging, tracing, debugging, metrics
Before you write a single line of agent logic
Building agents is product work. Building agent infrastructure is a distraction.
Get production-ready infrastructure with AshRuntime infrastructure that handles the hard parts, plus observability to keep them running well. Self-host the runtime, optionally connect Ash Cloud for dashboards and monitoring.
Database-backed session storage out of the box. Conversation history, session state, metadata—all persisted automatically with PostgreSQL or SQLite.
# Persistence is built in — just start with Postgres
$ ash start --database-url postgresql://localhost/ash
✓ Server running on :4100
✓ Connected to PostgreSQL
# Or use SQLite by default (zero config)
$ ash start
✓ Using SQLite at ~/.ash/ash.db
# Sessions, messages, metadata — all persisted
# Survives restarts automaticallyDatabase-backed session storage out of the box. Conversation history, session state, metadata—all persisted automatically with PostgreSQL or SQLite.
Real-time Server-Sent Events with backpressure, reconnection, and multi-client fan-out. No more building streaming infrastructure from scratch.
Auto-generated REST endpoints for sessions, messages, and agent management. Auth middleware, validation, error handling—all included.
Resume interrupted sessions or fork them for exploration. Branch conversation history like git branches—built into the SDK.
Interactive debugger for every agent session. See the full conversation, tool calls, reasoning steps, and errors—all in one timeline.
Watch agent sessions in real-time as events stream in via SSE. Perfect for development and debugging active sessions.
Install the CLI, write a CLAUDE.md system prompt, run ash start. You get a REST API, SSE streaming, session persistence, and sandboxed execution. Self-host anywhere Docker runs.
Overhead Per Message
To Production
Open Source Runtime
Events / Minute
Write your agent logic. Ash handles the production infrastructure. Optionally connect Ash Cloud for dashboards and real-time monitoring.
Create a folder with a CLAUDE.md system prompt. Add tool permissions and MCP servers as needed. That's your entire agent.
Run ash start anywhere — your laptop, a VM, ECS, Kubernetes. You get a REST API, SSE streaming, session persistence, and sandboxed execution. Your cloud, your credits.
Every session emits structured telemetry automatically. Debug with Run Inspector, monitor with Live Tail. Connect Ash Cloud for dashboards, or pipe events to your own stack.
Every session automatically emits structured events. Stream via SSE during development, or connect Ash Cloud for production monitoring.
99.6% of latency is the Claude API — not Ash. Running on your own infra means zero network hops to a third-party platform.
Ash overhead per message (p50)
Target was <5ms. We hit 0.41ms.
The Ash Runtime is open source and runs on your infrastructure at no cost. Ash Cloud adds dashboards, real-time monitoring, and team collaboration.
Open source, run anywhere
forever
Dashboards + monitoring
to start
Security, compliance & scale
Self-host in 5 minutes. Free and open source, forever.