PLATFORM / Coding Agents

Govern coding agents on developer machines

Claude Code, Cursor, and Codex work with real repos and systems — give them brokered, revocable access instead of raw keys.

Get a demoExplore the workflow ↓
01 / IDENTITY02 / POLICY03 / AUDIT
FABRIQ / RIPPLEIDENTITY · PERMISSIONS · VISIBILITY
Keep the developer in the loop.FABRIQ / CONNECT
01 / THE CONTEXT

Developer machines,
without the loose keys.

Coding agents read repos, call APIs, and ship changes — powered by whatever credentials live on the laptop.

AUTHORITY
agent
∩
person
RESOLVED PER REQUEST
02 / IN PRACTICE

Keep the developer in the loop.

ONE SESSION · ALEX@ACME · CODING AGENTIllustrative · coding-agent acting for a Developer
  1. alex
    Open a pull request for the retry fix.
  2. broker
    github.open_pr · acme/checkout #481

    Opened through Alex’s own GitHub connection. The laptop never held a provider key — the credential was attached server-side for this one call.

    Brokered
  3. alex
    Pull in the payments service for context.
  4. broker
    github.read · acme/payments-core

    Alex has no access to that repository, so the agent working for him has none either. Refused at the broker; GitHub was never called.

    Refused
  5. alex
    Ship it to production.
  6. broker
    deploy.release · production

    A named human approver has to say yes first. The session stays open and nothing ships while the request waits.

    Held
  7. alex
    Fine — I’ll take the deploy myself.

Illustrative session · the developer sees every verdict as it happens, and each one lands on the same audit trail.

03 / WHAT CHANGES

Control, in the details.

ON THE DEVELOPER’S MACHINE
$ coding-agent --connect fabriqopening sign-in…signed in as alex@acmesession open · tools from your own connections

No provider key is stored here. Credentials stay in the vault and are injected server-side at call time.

IN THE CONSOLE
  • alex@acmeclaude-codeopen
  • priya@acmecursoropen
  • sam@acmecodexclosed

Illustrative sessions. Every broker session is attributed to the developer who started it.

01

Admins enable each coding agent.

Claude Code, Cursor, and Codex are switched on per org — an agent nobody enabled cannot open a session.

02

A broker instead of raw keys.

Copy-paste config; provider credentials stay in the vault and are injected server-side at call time.

03

Sessions visible live.

Every active broker session shows in the console, attributed to the developer who started it.

04

A kill switch at the org, not the keyring.

Switch the coding agent off and no laptop can establish a session again — nothing to rotate, nothing to chase down.

05

Bounded by the developer’s own access.

The agent works through that person’s connections, so it can’t reach a system they haven’t connected themselves.

06

Every call on the same audit trail.

Developer, agent, tool, verdict, timestamp — the same ledger as the rest of the fleet.

ORGANIZATION CONTROL

One switch. Every developer session.

💻 DEVELOPER LAPTOP
Claude Code raw keys · unattributed
🔑 ~/.envghp_live…
⚙ .mcp.json3 direct endpoints
◉ sessioninvisible
AGENTIC FABRIQ
MCP broker · session auth · audit
GitHub
prod API
Slack
THREE LAYERS. ONE DECISION.

The boundary travels with the work.

Explore the context attached to every request.

What is this agent allowed to do?

coding-agent has a defined purpose and a bounded set of tools.

QUESTIONS

A closer look.

Which coding agents are supported?+

Claude Code, Cursor, and Codex through the local broker — plus anything MCP-compatible on the same governed endpoint.

Can we cut an agent off quickly?+

Switch the agent off for the organization. From that moment no laptop can establish a session, and because the broker re-authenticates rather than holding a standing key, its automatic reconnect is refused too. Revoking a developer’s live session from the console closes out what is already open.

Does this slow developers down?+

No — setup is a copy-paste config and one sign-in. After that the agent works exactly as before, just through a governed endpoint instead of raw keys.

Do developers paste API keys anywhere?+

No. Sign-in is an OAuth login — a device code flow for headless machines — and provider credentials stay in the vault, injected server-side at call time. Nothing a developer holds locally can reach a provider on its own.

What can a coding agent reach?+

The tools the developer has connected, through the org’s hub. It inherits that person’s access rather than carrying standing credentials of its own — so offboarding the developer offboards their agent with them.

Can we see who is running agents right now?+

Yes — live broker sessions are visible in the console as they happen, each one attributed to the developer who started it.

YOUR NEXT CHAPTER

Give your agents
room to move.

See Fabriq in action
Integration HubInternal AgentsPermissions & Scopes