State of CLI Coding Agents, Mid-2026arcbjornthoughtbook<br>RSS Feed

Saturday, July 4, 2026<br>State of CLI Coding Agents, Mid-2026<br>The terminal was an unlikely winner. In 2024 the bet was on IDEs — Copilot already lived in the editor, Cursor was climbing, and "agent" still meant chat with shell access bolted on. By mid-2026 the serious usage ran from CI, SSH, and machines with no GUI at all. Scriptable, boring, and the model never fights something else for the window manager.

35 actively maintained CLI coding agents as of July 3, 2026. Crowded field.

Skip to feature by feature comparison · Skip to conclusions

Short history<br>The 1st wave arrived in 2023, before anyone called these things agents. gptme (March 2023) let a model run shell commands from the terminal. Aider (mid-2023) built AI pair programming around git, with atomic commits as the unit of change. Open Interpreter (July 2023) generalized the idea to controlling the whole computer. All 3 survive — gptme as a daemon, Aider as a pair programmer, Open Interpreter as a general computer controller.

Anthropic's Claude Code research preview in February 2025 set the shape: agentic loop, file and shell tools, project memory file, permission prompts, plan mode, hooks, subagents. Everyone else cloned it. OpenAI shipped Codex CLI in April 2025 (later rewritten in Rust). Google followed with Gemini CLI in June 2025 and an aggressive free tier. By the 2nd half of 2025 the releases piled up in one quarter — Cursor, Amp, Augment, Factory, Charm, and 12 open-source teams.

Teams that standardized on Gemini CLI in 2025 still have configs from last fall. December 2025 is when the standards people showed up: the Linux Foundation formed the Agentic AI Foundation (AAIF), anchored by Anthropic's Model Context Protocol, OpenAI's AGENTS.md convention, and Block's Goose agent, with backing from Google, Microsoft, AWS, Cloudflare, and Bloomberg. The same month, Sourcegraph spun its agent out as the independent Amp Inc., Mistral entered with Vibe and the Devstral 2 models, and Codebuff open-sourced its multi-agent harness.

The 1st half of 2026 was messier. Copilot CLI hit GA in February. Cline shipped CLI 2.0 and peeled off an open SDK. Kilo CLI reached 1.0. Junie went from beta to GA in June. Google stole the headline at I/O in May: Antigravity CLI launched, and Gemini CLI got a kill date — June 18 for free and consumer-plan users. Grok Build landed late May. Moonshot replaced its earlier CLI with Kimi Code in June.

Models kept pace. DeepSeek V4 under MIT in April. GLM-5.2 and Kimi K2.7 Code in June, pulling open weights to within a few points of frontier terminal scores. The free tiers started dying around the same time: Qwen Code's hosted tier in April, Amp Free waitlisted, Gemini's consumer path gone by summer.

Model labs<br>Lab agents come from the model vendors — harness and model in one box, usually on a subscription line item already there.

Agent<br>Maintainer<br>Debut<br>Source<br>Models<br>Access<br>Known for

Claude Code<br>Anthropic<br>Feb 2025<br>Closed<br>Claude only<br>Pro/Max plans or API<br>The category template; deepest orchestration features

Codex CLI<br>OpenAI<br>Apr 2025<br>Apache-2.0, 95k stars<br>OpenAI Codex models<br>ChatGPT plans or API<br>Rust core, OS-level sandboxing, cloud handoff

Gemini CLI<br>Google<br>Jun 2025<br>Apache-2.0, 106k stars<br>Gemini<br>API key / enterprise only after Jun 18, 2026<br>Consumer access retired in favor of Antigravity CLI

Antigravity CLI<br>Google<br>May 2026<br>Closed<br>Gemini 3.5 plus selected third-party models<br>Free public preview<br>Shares one harness with the Antigravity 2.0 desktop app

Grok Build<br>xAI<br>May 2026<br>Closed<br>grok-build (256K context)<br>SuperGrok 30/mo,XPremium+30/mo, X Premium+ 30/mo,XPremium+40/mo, or API<br>Up to 8 parallel subagents in isolated git worktrees

Mistral Vibe<br>Mistral AI<br>Dec 2025<br>Apache-2.0, 4.6k stars<br>Mistral (Medium 3.5, Devstral 2); open weights<br>Free CLI; Mistral plans/API<br>European option; remote async agents; ACP

Kimi Code CLI<br>Moonshot AI<br>Jun 2026<br>MIT, 3k stars<br>Kimi K2.7 Code<br>Kimi plans or low-cost API<br>Built-in coder/explore/plan subagents; ACP

Qwen Code<br>Alibaba (Qwen)<br>Jul 2025<br>Apache-2.0, 26k stars<br>Qwen3-Coder or any endpoint<br>BYOK; paid plans (free hosted tier ended Apr 2026)<br>Gemini CLI fork tuned for Qwen's open-weight coders

Claude Code still sets the vocabulary — agent teams, hooks, skills, the lot. Experimental agent teams (multiple sessions messaging each other) remain ahead of the pack. The trade is total model lock-in. As of June 2026, headless and SDK usage bill from a separate credit pool. Terminal-Bench 2.0 in early July had Anthropic's newest models on top. The bundled pitch is a co-trained model plus harness, and the leaderboard backs it.

Codex CLI is the strongest counterweight, and it had a busy spring. It's open source, OS-sandboxed, rides ChatGPT's subscriber base, and runs GPT-5.5 as its current frontier default. Through the 1st half of 2026 it picked up persistent Goals with token budgets, thread-level delegation to subagents, a plugin marketplace,...