AI Launch Profile

Codex as an agent provider in GitHub Copilot for JetBrains

GitHub added Codex as an optional public-preview agent provider in GitHub Copilot for JetBrains IDEs and shipped related agentic enhancements including hooks support, richer MCP server management and administrator-configured custom models.

Read official source

At a glance

Launch Snapshot

Company: GitHub
Launch date: July 7, 2026
Launch type: Not classified
Category: AI Agents, AI Coding Tools, AI Developer Tools
Audience: AI Platform Teams, Developers, Engineering Teams, Enterprise IT
Pricing: The announcement lists no separate price for the Codex provider preview. Access follows eligible GitHub Copilot plans, policies, AI-credit rules and any provider-specific conditions documented by GitHub and OpenAI.
Free plan: No
API: No
Open weights/source: No

Launch Context

Use these links to move from this record into the broader Launch Intelligence database.

Launch Intelligence hub Today's launches This week's launches More: AI Agents More: AI Coding Tools More: AI Developer Tools More: AI Platform Teams More: Developers More: Engineering Teams More: Enterprise IT

Verification & Sources

Evidence state: Recheck due
Source links: 6
Freshness: Needs recheck: checked July 28, 2026
Last updated: July 28, 2026

What this evidence state means

Definition: The claim was previously checked, but its review window expired or a material change may have invalidated it.
Required provenance: The prior evidence and check date are retained, together with the expiry or change signal that triggered recheck.
Owner: Kingy freshness queue owner and assigned editorial reviewer
Freshness rule: This is already outside its freshness rule. It must not be presented as current until reviewed against current evidence.
Disputes and corrections: Use “Suggest a correction” on the record. Kingy editorial reviews the cited evidence, records material corrections, and changes or removes the state when it is not supported.

Key source checks

Official site Official docs Pricing Source 3 Source 4 Source 5

Suggest a correction

Kingy AI Take

Provider choice inside JetBrains can reduce tool switching, but Codex, Claude and Copilot modes should not be treated as equivalent harnesses. The release is a public preview and combines provider, model, hooks, permissions and MCP changes. Kingy did not enable the integration, so teams should compare a frozen task pack, inspect approval boundaries and verify which identity and billing path applies before setting a default.

Who it is for

Developers and engineering teams using GitHub Copilot in JetBrains IDEs, especially Business and Enterprise administrators governing preview features, providers, models, permissions and MCP servers.

What feels promising

An in-IDE provider choice, hooks and richer MCP controls can make agent workflows easier to govern without forcing every developer into a separate client.

What feels unproven

Kingy did not test Codex authentication, model parity, tool permissions, hook ordering, MCP isolation, task quality, cancellation, billing attribution, admin-policy enforcement or preview stability.

Source list

Sources

Official site github.blog Source docs.github.com Source docs.github.com Source docs.github.com Source github.com Source docs.github.com