Best AI Coding Agents in 2026: Ranked by Usage, Benchmarks and Price
The AI coding agents developers use most, with live download and install numbers, benchmark results, entry prices and a way to choose between terminal, IDE and cloud agents.
The short version
There is no single best coding agent, because "best" depends on where you work. What can be said with numbers, as of Nov 20, 2026:
- Most downloaded: OpenAI Codex with 26.6M package downloads in the last week; Claude Code with 18.9M package downloads in the last week; Pi with 6.4M package downloads in the last week.
- Most installed in VS Code: GitHub Copilot (79.4M), Claude Code (30.6M), OpenAI Codex (16.9M).
-
Growing fastest: Momentic (+118% in 30 days), PR-Agent (+104% in 30 days), Kimi Code (+93% in 30 days).
-
Benchmarks: on Terminal-Bench 4.1, the best listed runs are 62.1% for Codex and 65.8% for Claude Code, which is inside each other's margin of error. See benchmarks.
Downloads count every install, including CI and automatic updates, so read them as activity and direction, not as a head count.
The live ranking
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
Claude CodeAnthropic |
88 | 18.9M | up 15.1% | up 15.5% | 156K+136/day | 2.1.328yesterday | ||||
| 2 |
OpenAI CodexOpenAI |
84 | 26.6M | up 2.4% | up 7.4% | 136K+144/day | 0.168.07d ago | ||||
| 3 |
OpenCodeAnomaly (SST team) |
80 | 3.9M | up 15.4% | up 28.7% | 228K+266/day | 2.3.22d ago | ||||
| 5 |
GitHub CopilotGitHub (Microsoft) |
75 | — | — | — | — | — | ||||
| 6 |
CursorAnysphere (owned by SpaceX) |
73 | — | — | — | 33.3K+4/day | — | ||||
| 7 |
PiEarendil Inc. (created by Mario Zechner) |
73 | 6.4M | up 1.6% | up 36.3% | 123K+193/day | 1.5.210d ago | ||||
| 12 |
ZedZed Industries |
64 | — | — | — | 95.3K+89/day | 1.29.22d ago | ||||
| 15 |
Gemini CLIGoogle |
62 | 495K | up 16.9% | up 6.8% | 109K+35/day | 0.69.0yesterday | ||||
| 20 |
ClineCline Bot Inc. |
58 | 84.3K | down 8.7% | up 14.9% | 71.8K+38/day | 4.1.2625d ago | ||||
| 22 |
GitHub Copilot CLIGitHub (Microsoft) |
56 | 1.7M | down 8.3% | up 8.3% | 11.4K+6/day | 1.0.1142d ago | ||||
| 23 |
MomenticMomentic |
56 | 892K | up 192.3%One-day spike | up 118.0% | — | — | ||||
| 24 |
DevinCognition |
56 | — | — | — | — | — | ||||
Live table, updated daily (figures as of Nov 20, 2026); numbers in the text are as of the dates given there. "#" is the rank among products of the same kind by Gid Score, our 0-100 composite of adoption, community, attention and momentum (how it is calculated); a dash means no public data.
The full table, with every tracked product, is on the coding agents page.
First decide the shape: terminal, editor or cloud
Most of the choice is made by how you want to work, before any product comparison.
Terminal agents
A command-line agent runs inside your repository, uses the same tools you do (tests, linters, git) and works with any editor. It is the easiest kind to script and to run in CI. Choose this if you are comfortable in a shell and want the agent to fit into your existing workflow.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
Claude CodeAnthropic |
88 | 18.9M | up 15.1% | up 15.5% | 156K+136/day | 2.1.328yesterday | ||||
| 2 |
OpenAI CodexOpenAI |
84 | 26.6M | up 2.4% | up 7.4% | 136K+144/day | 0.168.07d ago | ||||
| 3 |
OpenCodeAnomaly (SST team) |
80 | 3.9M | up 15.4% | up 28.7% | 228K+266/day | 2.3.22d ago | ||||
| 7 |
PiEarendil Inc. (created by Mario Zechner) |
73 | 6.4M | up 1.6% | up 36.3% | 123K+193/day | 1.5.210d ago | ||||
| 15 |
Gemini CLIGoogle |
62 | 495K | up 16.9% | up 6.8% | 109K+35/day | 0.69.0yesterday | ||||
| 20 |
ClineCline Bot Inc. |
58 | 84.3K | down 8.7% | up 14.9% | 71.8K+38/day | 4.1.2625d ago | ||||
Live table, updated daily (figures as of Nov 20, 2026); numbers in the text are as of the dates given there. "#" is the rank among products of the same kind by Gid Score, our 0-100 composite of adoption, community, attention and momentum (how it is calculated); a dash means no public data.
AI IDEs and editor extensions
Here the agent lives in the editor, with inline diffs and visual review. It is easier to follow what changed and to step in. Choose this if you review by reading diffs and want the agent and the code side by side. Extensions keep your current editor; AI-native IDEs replace it.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 5 |
GitHub CopilotGitHub (Microsoft) |
75 | — | — | — | — | — | ||||
| 6 |
CursorAnysphere (owned by SpaceX) |
73 | — | — | — | 33.3K+4/day | — | ||||
| 12 |
ZedZed Industries |
64 | — | — | — | 95.3K+89/day | 1.29.22d ago | ||||
| 25 |
Google AntigravityGoogle |
55 | — | — | — | — | — | ||||
| 26 |
WarpWarp |
55 | — | — | — | 66.1K+15/day | 0.2026.06.03.…5mo ago | ||||
| 42 |
KiroAmazon Web Services |
50 | — | — | — | 4,484+4/day | — | ||||
Live table, updated daily (figures as of Nov 20, 2026); numbers in the text are as of the dates given there. "#" is the rank among products of the same kind by Gid Score, our 0-100 composite of adoption, community, attention and momentum (how it is calculated); a dash means no public data.
Cloud agents
A cloud agent takes a task, works in its own remote environment and returns a pull request. Several can run in parallel while you do something else. Choose this for well-specified tasks that do not need your local setup. Their output is countable: the GitHub activity page tracks how many pull requests each one opens and what share is merged.
Many products now span more than one shape. Claude Code and Codex, for example, each have a terminal agent, an editor extension and a cloud mode, so picking one of them does not lock you into one way of working.
What it costs
Entry prices for individual plans, as listed on each vendor's pricing page and checked on the date shown on the agent's page:
| Agent | Entry price | What the listed plans cover |
|---|---|---|
| Claude Code | $20/mo | Claude Code is included in Pro ($17/month annual or $20/month monthly), Max ($100/month), and Ultra ($200/month) plans. The Free plan does not include Claude Code.... |
| OpenAI Codex | Free + $8/mo | Included in ChatGPT plans: Free $0, Go $8/month, Plus $20/month, Pro from $100/month ($100, $200 or $500 tiers), Business $20/user/month billed annually ($25... |
| OpenCode | Free + $10/mo | OpenCode is free and open source, with free models under a daily request limit. Paid plans: OpenCode Go ($10/month) and Go Plus ($40/month) with monthly usage limits... |
| GitHub Copilot | Free + $10/mo | Free plan with 2,000 completions per month, limited chat and agent usage. Pro $10/mo with $15 total monthly credits ($10 base + $5 flex), Pro+ $39/mo with $70 total... |
| Cursor | Free + $8/mo | Free tier with limited AI usage; Plus $8/mo, Premium $30/mo, Super $100/mo, Ultra $200/mo for individuals with tiered usage pools; Teams $30+/user/mo with pooled... |
| Pi | Free (OSS) | Free and MIT-licensed; costs are those of the chosen model provider. Pi Durable (experimental) is also free per the 1.0 announcement. |
| Zed | Free + $10/mo | Personal $0 (the editor, free; unlimited use with your own API keys or external agents such as Claude Agent and Codex CLI); Pro $10/mo (Zed-hosted models, unlimited... |
| Gemini CLI | API usage or license | As of 2026-06-18 the free Code Assist for individuals tier and Google AI Pro/Ultra access ended; Gemini CLI continues with paid Gemini/Vertex API keys (pay as you go)... |
| Cline | Free + $9.99/mo | The open-source extension and CLI are free for individuals; you pay only for model inference (BYOK or the usage-billed Cline provider). ClinePass is a subscription... |
| GitHub Copilot CLI | Free + $10/mo | GitHub Copilot offers Free ($0, 2,000 completions/month with limited agent usage), Pro ($10/month with $15 monthly credits), Pro+ ($39/month with $70 monthly credits... |
| Momentic | Free + $500/mo | Free plan with $50 monthly usage included. Scale plan at $500/month with $500 monthly usage, ability to add funds from $50, and device testing features. Enterprise... |
| Devin | $20/mo | Devin Cloud access starts with Pro at $20/mo (the Free plan covers desktop agents only); Max $200/mo; Teams $80/mo plus $40/mo per full dev seat (up to 200 users);... |
| Google Antigravity | Free + $30/mo | Individual use is free with unlimited Tab completions and Command requests plus basic weekly rate limits. Paid tiers Google AI Pro and Google AI Ultra offer flexible... |
| Warp | Free + $20/mo | Free $0 (bring your own inference, limited cloud agents); Build $18/mo billed annually or $20/mo monthly ($20 of agent usage a month at API rates); Max $180/mo billed... |
Two cost models hide behind those numbers:
- Subscription with limits. A flat monthly price that includes a quota of model usage. Predictable, and usually the better deal for daily use, until you hit the quota.
- Bring your own key. The agent is free or cheap, and you pay the model provider per token. Cheaper for occasional use, open-ended for heavy use. Most open-source agents work this way.
If you want to start without paying a vendor, see free AI coding agents. To keep code on your own machine, see local AI coding agents, which run with a model served by Ollama, LM Studio or llama.cpp.
Open source or commercial
Open-source agents let you choose the model, audit what the tool does with your code and keep working if the vendor changes course. That last point has mattered recently: within the past year several popular agents were discontinued, archived or folded into other products. Commercial agents are typically tuned for one vendor's models and bundle the model cost, which tends to mean less setup.
Ranked list: open-source coding agents.
How to choose in practice
- Pick the shape (terminal, editor, cloud) that matches how you already work.
- Shortlist two or three from the top of that table. High usage and a recent release are good signs that an agent is maintained and that problems you hit will have been hit before.
- Check the model terms. Which models can it use, can you bring a key, and what happens when the quota runs out?
- Run the same real task through each. Use a task from your own backlog with a clear definition of done, such as a bug with a failing test. Compare the diff you would have to review, not the demo.
- Start with tight permissions. Let the agent read and propose, approve edits and commands yourself, and loosen that as you learn where it is reliable.
What these numbers cannot tell you
Usage shows what developers choose; it does not measure the quality of the code an agent writes on your codebase. Benchmarks measure quality on a fixed task set, which may not look like your work, and only for agents someone submitted. Treat both as a way to build a shortlist, and let a trial on your own code make the decision. The methodology explains how every figure on this page is collected.
Looking for agents that do something other than code? See the best AI agents in every category.
Agents mentioned in this guide
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
Claude CodeAnthropic |
88 | 18.9M | up 15.1% | up 15.5% | 156K+136/day | 2.1.328yesterday | ||||
| 2 |
OpenAI CodexOpenAI |
84 | 26.6M | up 2.4% | up 7.4% | 136K+144/day | 0.168.07d ago | ||||
| 3 |
OpenCodeAnomaly (SST team) |
80 | 3.9M | up 15.4% | up 28.7% | 228K+266/day | 2.3.22d ago | ||||
| 5 |
|
75 | — | — | — | — | — | ||||
| 6 |
CursorAnysphere (owned by SpaceX) |
73 | — | — | — | 33.3K+4/day | — | ||||
| 20 |
ClineCline Bot Inc. |
58 | 84.3K | down 8.7% | up 14.9% | 71.8K+38/day | 4.1.2625d ago | ||||
| 24 |
DevinCognition |
56 | — | — | — | — | — | ||||
| 25 |
Google AntigravityGoogle |
55 | — | — | — | — | — | ||||
Live table, updated daily (figures as of Nov 20, 2026); numbers in the text above are as of the dates given there. "#" is the rank among products of the same kind by Gid Score, our 0-100 composite of adoption, community, attention and momentum (how it is calculated); a dash means no public data.
Sorted by rank. Promo marks an official promotion the maker runs right now (a discount, free access or credits); open it for the details on Deals.