An agent runtime, not agent hosting.
Deploy autonomous agents that run for months, wake on events, remember what happened, call tools with scoped credentials, pause for human approval, and report what every run cost. Memory, triggers, retries, secrets, and cost tracking come with the platform — you do not rebuild them per project.
Bring your framework. Push once.
Deploy the agent you already wrote — or one you have not started yet. Darwa runs the process continuously instead of invoking a function and killing it.
agent: invoice-recovery
runtime: python3.12
entry: agents/recovery.py
triggers:
- webhook: stripe/invoice.payment_failed
- schedule: "0 9 * * 1-5"
memory:
long_term: true
namespace: billing
approvals:
- when: amount > 1000
notify: slack#finance
tools: [stripe, gmail, postgres]Agents that wake up on their own.
Events and schedules are part of the runtime. You do not stand up a queue, a cron container, and a webhook receiver to get an agent to start working.
retries
approvals
secrets
tracing
Missed windows are recorded rather than silently skipped, and a schedule that overlaps its own previous run either queues or is dropped — your choice, per schedule.
Approvals are a first-class step: the run genuinely pauses, keeps its state, and continues where it stopped once a human decides.
Four kinds of memory, none of which you have to build.
Most teams reimplement the same storage layer for every agent. Here it is part of the runtime, addressable from your code with one client.
The current task, tool results, and intermediate reasoning — scoped to one execution and discarded when it ends.
Facts, preferences, and outcomes persisted across runs, retrievable by key or semantic search.
Every turn kept with its tool calls and token counts, replayable for debugging or audit.
A namespace several agents read and write, so a research agent's findings are available to the writer.
from darwa import memory
# long-term, namespaced, survives restarts and versions
profile = memory.get("customer:cus_9F21")
memory.set("customer:cus_9F21", {**profile, "last_outcome": "recovered"})
# semantic recall across everything this agent has learned
similar = memory.search("payment failures resolved by card update", k=5)Connect once, scope tightly, never paste a key into code.
Credentials live in the platform, are injected at run time, and are granted per tool and per agent. An agent that only needs to read Postgres cannot write to it.
CPU and memory tell you nothing about an agent.
What matters is what it decided, which tools it called, how long the model took, and what the run cost. That is what the dashboard shows.
Deploy the tool, not the tutorial.
Each of these normally means a container, a database, a volume, a reverse proxy, certificates, and a backup job. Press one button and every piece is provisioned and wired together.
Self-hosted workflow automation with 400+ nodes.
Chat interface for local and hosted models.
Documents in, private RAG assistant out.
Start from a working agent, not an empty file.
Each template ships with its triggers, tools, memory namespace, and approval rules already declared — then it is yours to edit in your own repository.
Reads your docs and past tickets, answers in your voice, escalates when confidence drops.
Qualifies inbound leads, enriches them, and books meetings on a real calendar.
Runs on a schedule, gathers sources, cites them, and files a summary.
Drafts from a brief, checks facts against your sources, waits for approval before publishing.
Opens pull requests against your repository, runs the test suite, reports what it changed.
Watches metrics and logs, investigates anomalies, pages a human with a cause.
Not shipped yet.
Listed so you can plan around it. Everything above works without any of this.
You pay for runtime. Model tokens stay at cost.
Agent hours are billed like any other always-on service. Model usage is passed through at provider price — Darwa makes money on the runtime, not on a markup you cannot see.
Enough to run a real scheduled agent and watch it work.
- 1 agent, 100 runs/day
- Shared CPU, 512 MB
- Short-term + conversation memory
- 3 connected tools
- 7-day trace retention
- Bring your own model key
For agents doing work someone depends on.
- Unlimited agents
- Long-term + shared memory
- All triggers and schedules
- Human approval steps
- Unlimited tools, scoped per agent
- 90-day traces, cost attribution
- Model tokens at provider cost
For agents touching regulated or customer data.
- Dedicated runtime and GPU options
- Private networking + peering
- SSO, audit logs, SOC 2
- Data residency per region
- Unlimited trace retention
- Named engineer
Deploy one agent and read its first trace.
Push the agent you already have, or start from a template. Memory, triggers, secrets, and cost tracking are already there.