Compare

Devin is a factory you rent. engrams is one you own.

Devin and Factory run the agent, the machines, and your credentials on their platform. engrams runs the agent you choose, in microVMs in your cloud, with the source code in your hands.

engramsDevin (Cognition)Factory (Droids)
Who runs itYou, in your own cloud account or on your own hardwareCognition; on Enterprise, a single-tenant VPC that Cognition managesFactory; on-premise and air-gapped options on Enterprise contracts
Source codeOpen source. Read it, change it, and run every lineProprietaryProprietary
The agentClaude Code, Codex, or your own harness, mounted by the host at boot; never baked into your imageDevin, Cognition's agentDroids, Factory's agent
ModelsWhatever your harness calls, on your own provider keys or model routerFrom Cognition's model listFrom Factory's model list
Where the work runsA Firecracker microVM per session, on your KVM nodesA vendor-managed cloud machine per sessionVendor-managed cloud machines, or your machine through the CLI
Your environmentAny Linux image with /bin/sh, built with docker build; warmed once and snapshottedSet up inside the vendor's machine configurationSet up inside the vendor's environment configuration
CredentialsBrokered: the egress proxy inserts each key outside the VM, and the agent never sees itStored on the vendor's platformStored on the vendor's platform
AutomationsWorkflows you edit as a graph, started by a schedule, a pull request, Slack, Linear, or a webhookTasks from Slack, Linear, GitHub, and the APITasks from Slack, Linear, the IDE, and the CLI
Where people workDashboard, Slack threads, GitHub pull request review, CLI, APIWeb app, desktop app, CLI, Slack, LinearCLI, IDE, web app, Slack, Linear
What you payNo license fee. You pay your cloud provider and your model providerPer-seat plans with usage quotasPer-seat plans with usage limits

Vendor details are from their public product and pricing pages as of October 2026. Plans change; check with each vendor.

Sec. 1Other options

Where else teams look.

"Self-hosted" means different things. For most products below, the vendor keeps the control plane: the agent loop, the session record, and often the transcripts. Only the execution runs on your machines. engrams runs all of it in your account: the orchestration, the database, the VMs, and the snapshots.

Who runs whatWhere the work runsPick it when
OpenHandsOpen source agent and runtime; the hosted cloud, or self-hosted on Teams and Enterprise plansDocker containersYou want the OpenHands agent itself, and container isolation is enough
Claude Code self-hosted environmentsAnthropic runs the control plane and stores transcripts; runners on your hosts do the work (Team and Enterprise, beta)Your hosts; isolation is yours to set upYou use only Claude and accept a control plane at Anthropic
Cursor self-hosted cloud agentsCursor runs the agent loop and inference; your workers run commands and edits (team pools on Enterprise)Your machines or Kubernetes podsYour team works in Cursor and accepts a control plane at Cursor
OpenAI Codex cloudOpenAI runs everythingOpenAI-hosted environmentsYou pay for ChatGPT, and hosted execution is acceptable
E2BA sandbox SDK, not an agent product; open source infrastructure, or E2B runs it in your accountFirecracker microVMsYou are building your own agent product and need only the sandbox layer
Modal SandboxesModal runs everythinggVisor containers or VMs, with GPUsYou want serverless sandboxes with GPUs and no infrastructure to run

From each vendor's public docs and pricing pages as of October 2026. Plans change; check with each vendor.

Sec. 2When to pick the others

Pick the other thing when it fits.

If you do not want to run infrastructure, a hosted product is the right call. Devin and Factory give you an agent in minutes and handle the machines and billing. engrams asks you for a Kubernetes cluster with a KVM node pool, a Postgres, a bucket, and someone to run them.

If you want one vendor's agent and models, tuned together and supported by that vendor, buy that vendor's product. engrams runs the agents you bring and does not ship a model of its own.

If your hosts cannot run KVM, engrams has no production mode for you. It does not run sessions as containers.