Cloud coding agent
Run a coding agent in the cloud.
A coding agent is only as useful as the environment running it. plori gives each agent an isolated environment: a shell with git and dev tools, a Workspace that keeps working copies with saved versions, and time to finish the build after you close the tab.
Sign in with Google to start.
A real dev loop.
§01- Clones and keeps repos
- Working copies live in the agent's Workspace files, so follow-up asks skip the setup and pick up where the agent left off.
- Installs its own toolchain
- Node, Go, Python, whatever the repo needs. Tools installed under /workspace stay with the Workspace files. Installs elsewhere, including system locations, do not carry over to the next run.
- Runs builds and tests
- Long compiles and suites run as background jobs instead of timing out a chat turn.
- Asks before risky actions
- Credentials and risky commands go through built-in human-in-the-loop: the run pauses, you approve or supply the secret (masked), it resumes.
- Remembers your conventions
- Memory notes carry your stack, style, and standing constraints into every turn.
- Works over MCP
- Hand work to it from Claude, your IDE, or CI via the MCP server, then poll the run or get the reply in-thread.
Where it fits next to your IDE.
§02An IDE assistant is at its best in the tight loop: you watching, it editing. If that is the whole job, you do not need plori. A hosted coding agent covers the other half, the part that does not need you present: the long test run, the overnight refactor, the "check CI in the morning and fix what broke" run you set tonight via scheduled runs.
Because plori speaks MCP in both directions, the two compose: your IDE agent can delegate to your plori agent, and your plori agent can be steered from anywhere. Start one at plori.ai/agent and hand it a repo.
Questions, answered.
§03What can a cloud coding agent actually do?
Everything that fits in a shell: clone repositories, read and edit code, install toolchains, run builds and test suites, use git, and write up what it did. On plori it does this in a Workspace, so the repo it cloned Monday is still in the Workspace files Friday.
How does it authenticate to GitHub or other services?
It asks you. When a command needs a credential, plori's human-in-the-loop flow pauses the run and requests the value from you with a masked input, so secrets are redacted from the visible history and never guessed by the model.
What happens on long builds or test runs?
They become background jobs instead of hanging the conversation. The job keeps running until it exits, the agent stops it, or a deadline the agent set passes. In a Workspace run, the job also stops when the run ends. The agent can watch the job and post the result in the same thread.
Which models does it code with?
You do not choose one. The Plori Router picks the model from a pool shared by every plan. We choose the pool for quality per dollar and change it as models are released and repriced, so we don't list it here. Each run's usage shows what it cost. Bring your own OpenRouter or provider key to code with a specific model, including frontier models. That usage bills your provider directly instead of drawing credits.
Can I drive it from my IDE or from another agent?
Yes. plori's MCP server lets any MCP client create a Workspace, hand its agent a task, poll the result, and answer its questions. Your IDE assistant can delegate a long refactor to a plori agent and pick up the result when it lands.
Is my code isolated?
Yes. Each agent runs in its own isolated virtual machine, and no other account can reach your code. Deleting the Workspace erases its files and history in a background cleanup.