Preview iCode 0.23.1: pilots open for banks and government teams in air-gapped networks. Book a pilot →
Preview · 0.23.1

Everything a coding agent should do, without leaving your network

iCode reads your code, edits it, runs your tests and reports what really happened. Your administrators decide what it may do, and every step is recorded.

Agent

An agent that proves its work

The engine decides when a job is finished, not the model. iCode runs your tests itself, checks they were not edited to pass, and catches any result the model invented.

  • Ask, Plan and Agent modes, plus modes your teams define
  • Undo a whole run, one step or one file, even without version control
  • Several attempts at a hard fix, keeping the one that passes the most tests
  • Hooks run your own checks before and after each step
task › Fix the failing currency rounding testRead money.ts, money.test.tsAttempt 1: 11 of 12 tests passAttempt 2: 12 of 12 tests passCheck: test files unchangedCheck: every reported output was really printed✓ Done · kept attempt 2 · undo available
Codebase chat

Ask about code you have never cloned

Connect your repositories once. Answers point to the real files and lines, and each source is tied to the roles allowed to see it.

  • Search across every connected repository
  • Credential files, keys and environment files are never indexed
  • People only see answers from repositories they may read
“Where do we validate IBANs?”
payments-core / src/iban/validate.ts : 18match
onboarding-api / Iban.java : 44match
mobile-app / utils/iban.kt : 9match
3 repositories hidden by your rolefiltered
Code Graph

See what a change will touch before you make it

iCode maps how your code fits together: who calls what, which services talk to each other, and which tests cover a path. Answers and plans cover the whole system, not one file.

Impact of changing LedgerClient.post
Direct callers7
Services affected3
Tests that cover it22
Untested callers2 to review
Your models

Any model you host, measured and tuned

iCode talks to any OpenAI-compatible endpoint. Connect a model and iCode measures what it can really do, then sets itself up to match. Drift checks catch a quality drop after a model or settings change.

On your GPUs

The bundled model server starts from weights you copy in, and never downloads anything at run time.

Through your AI gateway

Point iCode at the gateway you already run. Keys stay in the service, never on laptops.

Per role and team

Choose which models each role may use, with budgets and rate limits per team.

Admin console

Everything on. Your admins decide.

Every feature ships switched on. Administrators switch off what they do not want, for one team or for everyone, from a page served by the service itself. Controls your regulator requires can be locked so nobody can change them.

  • Around thirty switches, per tenant
  • Every change recorded, with a reason when a guardrail is weakened
  • Usage per team, model and day
Features · all teams
Codebase chat
Inline completions
Agent runs shell commands
Chat history on laptops
Secret maskingLocked on
Learning

Learns how each person works

Standing preferences and methods that worked become personal skills, reviewed on your own model. Everyone can see, edit, lock or delete what was learned, and nothing leaves your network.

Guardrails

Secrets are masked before anything is stored. Package installs follow your policy: public, internal mirror or blocked.

Security scanning

Built-in checks flag vulnerable dependencies and risky code in what the agent writes, before you keep it.

Audit trail

Every request, tool call and change lands in an audit log you own, ready for your monitoring tools.

See it on your own code

Book a demo, or run a pilot with an evaluation licence in your own network.

Book a demoSee plans