Agent Atlas / Coding agents

google-gemini/gemini-cli

A terminal-first coding agent whose public source exposes tool scheduling, hooks, policy, context assembly, extensions, and specialized workers.

Coding agent CLI Full dossier Reported + sourced Reviewed July 21, 2026

Intended operator

Developers operating an agent in a terminal or through an integrating client.

Primary surfaces

terminal client / built-in tools / MCP and extensions

Tracked repository

google-gemini/gemini-cli

Teaching mechanism

Hooks can add context or stop work before execution

BeforeAgent and related hook boundaries let the runtime attach delimited context or block a run before the next agent step.

Evidence limitA documented hook boundary does not establish that every extension is safe or that every client exposes the added context.

Inspect the source

System Map

Eight inspection boundaries

Model boundary

The CLI assembles provider requests and tool declarations around the selected Gemini or compatible model path.

Context and memory

Workspace files, conversation state, settings, hooks, and extension context can shape the model-visible request.

Tools and execution

Built-in file, shell, web, and MCP tools pass through scheduler and policy code.

Permissions and isolation

Approval modes, policy checks, trusted folders, and sandbox options separate a proposal from an allowed effect.

Sessions and recovery

Session and tool lifecycle state support resumption, cancellation, and visible failure handling.

Delegation

Specialized subagents receive focused prompts, tool scopes, and independent context before returning results.

Human control

Terminal status, approval, command, and issue-maintenance surfaces keep operator decisions in the loop.

Evidence surface

Public commits, tests, tool events, scheduler behavior, and issue-maintenance receipts expose runtime pressure.

Learn Through This Project

8 lessons

Chapter 1 Before the First Model Request Chapter 2 The Invisible Prompt Chapter 3 Tool Calls: Contract, Authorization, Execution Chapter 4 Loops, Workflows, and Recovery Chapter 5 Delegation Is a Distributed System Chapter 7 The Approval Trap Chapter 8 The Human Control Loop Chapter 9 Trust Must Make Its Case

Compare Its Boundaries

8 labs

Comparison labTool Contracts Comparison labGoverned Memory Comparison labDelegation Receipts Comparison labApproval Boundaries Comparison labHuman Workbench Comparison labSessions And Recovery Comparison labEvidence And Evaluation Comparison labMaturity Signals

Latest Reporting

8 articles

Gemini CLI’s Caretaker Has Permission to Read, Not to Act

July 18, 2026 — Gemini CLI’s new issue-triage worker gives its model a read-only repository view, then keeps labels, comments, retries, and escalation in a separate validated program. google-gemini/gemini-cli

Gemini CLI Explains the Missing Privacy Switch

July 11, 2026 — The /privacy screen now says when a consumer data-control does not apply to an account, instead of making Workspace and enterprise users decode a raw OAuth or tier error. google-gemini/gemini-cli

Gemini CLI Turns Issue Triage Into A Caretaker Worker

July 8, 2026 — Gemini CLI added a caretaker triage worker and GitHub egress handler, moving issue sorting toward an agent-run workflow with locks, retries, labels, comments, and human handoff states. google-gemini/gemini-cli

Agent Safety Gates Catch Edge Cases

June 27, 2026 — Gemini CLI, OpenClaw, and Hermes all turned ordinary boundary mistakes into explicit control failures. google-gemini/gemini-cli, openclaw/openclaw, NousResearch/hermes-agent

Google Antigravity After the Transition

June 23, 2026 — The public record after the June 4 transition points to Antigravity as the packaged migration and operator surface, while Gemini CLI still carries open implementation repair. google-antigravity/antigravity-cli, google-gemini/gemini-cli

Agent Tools Get Back-Pressure Surfaces

June 22, 2026 — Fresh Gemini CLI and OpenWork patches show agent products turning hangs, publish failures, voice quotas, and provider outages into explicit runtime behavior. google-gemini/gemini-cli, different-ai/openwork, google-antigravity/antigravity-cli

Ramón Medrano Llamas Let Gemini CLI Breathe

June 22, 2026 — A Gemini CLI contributor fixed a scheduler starvation path by changing how parallel tool waves yield back to the event loop. google-gemini/gemini-cli

Agent Tools Are Moving Safety Into Boundaries

June 16, 2026 — Gemini CLI, LangChain, and Codex landed fresh patches that put agent safety in filesystem checks, type gates, pending-tool waits, and permission-path parsing. google-gemini/gemini-cli, langchain-ai/langchain, openai/codex

Primary Sources

Google Gemini CLI repository

Primary public implementation and documentation source.

Open Questions

Can every injected context and policy result be reconstructed from the operator-facing session record?

Evidence state describes what this Atlas profile can support today. It is not a product score and it is not evidence that uninspected capabilities are absent.