flowbit Agents
BetaCoding agents
Hand a task to an agent that reads your repository, plans the change, edits the files and runs your tests. You review the diff and decide what stays.
Currently in beta. We're still building this, and access is limited.
bashrun-task.sh
RunningCompleted in 24sses_7f3a91
RunningCompleted- Session started
build00:00:00 - Read
src/routes/*.ts00:00:02 - Edit approved
src/routes/login.ts00:00:09 - Ran
npm test00:00:21 - Completed and closed00:00:24
- Model
- Sonnet 5
- Context
- Full repo
- Agent
- build
- Approvals
- Ask first
- Session
- ses_7f3a91 · 24s
Setup guides
Choose where your agent runs
The same agent, permissions and sessions, wherever you write code.
- Available
Agentic Terminal
A full-screen agent in your shell. Run it in any repository, or in a cloud workspace with nothing to install.
- Preview
Agentic IDE
A fast native editor with the agent built in, beside your files, diffs and terminal.
- Preview
Agentic Extension
Bring the agent into the editor you already use, with the same approvals and sessions.
Agent session
Every session starts with the whole repo in view.
The agent attaches to your workspace with your model, your project context, and a safe approval policy already set, so the first thing you type can be the task itself.
Defaults shown. Models, approval rules and agents can be changed per project or per session.
Agent session~/app
Running- Model
- Sonnet 5Switch provider any time
- Context
- Full repoFiles, git history and LSP
- Agent
- buildTab switches to plan
- Approvals
- Ask firstBefore edits and commands
- Status
- RunningWorking in ~/app
- Session
- 42 minResumable at any time
Capabilities
An engineer in the terminal, not a chat window
The agent works where your code already lives. It uses your tools and your tests, and it stops to ask you before anything important.
Agentic by default
Give it a goal instead of a prompt. It breaks the task into steps and works through them until it is done.
Understands your repo
It reads files, searches symbols and follows imports with language-server awareness, so its changes match your patterns.
Plan before it builds
A read-only plan agent explores and proposes. Hand the plan to the build agent when you agree with it.
Runs your toolchain
It installs dependencies, runs builds and tests, and reads the failures. MCP servers add any other tool it needs.
You stay in control
Edits and shell commands wait for your approval unless you allow them. Every change can be undone.
Bring any model
Use frontier models from any major provider, or a local model, and switch between them in the middle of a session.
Commands
One command to start. Plain language after that.
The agent is a single command in any repository. Everything else is a sentence describing what you want done.
cloud-user@agents~/app · bash
# Open any repository and start the agentcd ~/appagent# Or hand it one task and let it run to the endagent run "explain how requests reach the database"# Pick up where you left off yesterdayagent --continueDocumentation
Read the docsCLI
Start sessions, run one-off tasks, resume and share work from any shell.
MCP servers
Connect tools and data sources the agent can call, under your permission rules.
Models
Enable providers for your organization and pick a default per project.
Prompts
Start from a prompt
Most tasks that take an afternoon of reading, editing and re-running tests fit in one sentence. Copy one and make it yours.
Build features
Describe the behavior you want. The agent finds where it belongs, writes it, and wires it up end to end.
agent run "add CSV export to reports"Fix bugs
Point it at a failing test or an error message. It reproduces the problem, finds the cause, and proves the fix.
agent run "fix the failing auth test"Understand a codebase
Ask how something works in plan mode and get an answer that cites the actual files, without any edits.
agent run --plan "how does billing work?"Refactor safely
Rename, move and restructure code across many files, with the test suite run after each step.
agent run "move date helpers to lib/date"Write tests
Cover untested modules with tests that follow your existing conventions and pass on the first run.
agent run "cover utils/price.ts with tests"Review changes
Have the agent read your diff before you push. It flags bugs, missed edge cases and inconsistencies.
agent run --plan "review my git diff"
How it works
From request to reviewed change in four steps.
There is no new editor to learn and no copying code out of a chat window. The agent works in your repository, and you keep the final decision.
- Select a step to pin it.
agent~/app
Step 1/4Safety
Autonomy with guardrails
The agent can change code and run commands, so it is limited the same way you would limit a new teammate. It needs permission to act, its changes can be reversed, and there is a record of what it did.
Permission prompts
File edits and shell commands ask first by default. You can allow specific commands per project, such as your test runner, and keep everything else gated.
edit · bash: askRead-only planning
The plan agent cannot edit files. Use it on unfamiliar or sensitive code to understand the work before anything changes.
plan agentReversible changes
Every run is recorded as one change set. agent undo restores the files exactly as they were before the run.
agent undoIsolated workspaces
In the cloud, the agent runs inside your own workspace container. It can reach only the projects and resources that you can reach.
containerYour models, your keys
Use your organization's provider accounts or a local model. Provider keys are stored as secrets and are never written into the repository.
BYOKFull transcript
Every prompt, tool call and command is saved in the session history, so you can see exactly how a change was made.
transcript
Matched rule
Reading the repository is allowed
Tool calls in this session
Select a call to see how it was handled.
FAQ
Frequently asked questions
Put coding agents to work on flowbit.
Open a session in any project and hand the agent its first task in under a minute.
Works with any model provider · You approve every change
Security & compliance
flowbit runs on independently audited security, privacy and cloud controls — so your apps and data meet the standards your customers expect.
