Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
"Best AI agent" means little until you say for what. An agent that writes code, one that books meetings and one that answers support tickets are different products with different buyers. This page ranks them by job, using public usage data (package downloads, editor installs, GitHub activity, releases, attention) that is refreshed every day.
The short version: the leader in each category
The Gid Score (0–100) combines usage, community, attention and momentum on fixed scales; the methodology explains the formula. It is a way to sort products by how much they are actually used and talked about, not a quality grade.
Across all categories
The twelve agents with the highest Gid Score today, whatever they do:
| # | 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 | ||||
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | ||||
| 4 |
n8nn8n |
79 | 107K | down 28.5% | up 4.9% | 211K+167/day | 1.123.982d ago | ||||
| 1 |
LiteLLMBerriAI |
76 | 24.4M | up 5.0% | up 4.6% | 63.5K+61/day | 1.110.1yesterday | ||||
| 5 |
GitHub CopilotGitHub (Microsoft) |
75 | — | — | — | — | — | ||||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | ||||
| 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 | ||||
| 8 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
71 | 3.1M | up 5.8% | down 24.3% | 395K+120/day | 2026.10.332d ago | ||||
| 2 |
LangfuseLangfuse |
69 | 14.7M | down 0.5% | up 33.5% | 37.6K+41/day | 4.82.03d 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.
The full list of 492 tracked agents is on the main ranking.
Best AI agents for coding in the terminal
A terminal agent works inside your repository with the same tools you use: tests, linters, git. It fits any editor and is the easiest kind to script. Most of the largest agents by downloads are here.
| # | 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 | ||||
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.
All terminal coding agents ranked
Best AI agents for coding in an editor
Editor agents show their work as inline diffs, which makes review easier. Extensions keep your current editor; AI-native IDEs replace it. The two largest terminal agents also work inside editors: Claude Code has an official VS Code extension with inline diffs and a JetBrains integration (docs), and OpenAI Codex has an extension for VS Code, Cursor and Windsurf plus Xcode and JetBrains integrations (docs); both are ranked with the terminal agents above.
| # | 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 | ||||
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.
All AI IDEs and editor agents ranked
Best AI agents for delegating coding tasks to the cloud
Cloud agents take a task, work in their own environment and come back with a pull request, so several can run while you do something else. Their output is countable on the GitHub activity page.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 24 |
DevinCognition |
56 | — | — | — | — | — | ||||
| 243 |
JulesGoogle (Google Labs) |
15 | 929 | down 40.6% | down 32.9% | — | — | ||||
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.
All cloud coding agents ranked
Best AI agents for reviewing pull requests
Review agents comment on every pull request, flag bugs and risky changes and often propose fixes. They complement, not replace, a human reviewer.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 30 |
Open Code ReviewAlibaba |
53 | 184K | up 10.4% | up 25.9% | 54.2K+636/day | 1.13.13yesterday | ||||
| 67 |
PR-AgentThe-PR-Agent community (originally Qodo) |
44 | 21.2K | down 18.5% | up 103.9% | 16.4K+63/day | 0.50.013d ago | ||||
| 110 |
SourcerySourcery |
36 | 9,162 | up 65.9%One-day spike | up 34.5% | 1,888+1/day | 1.46.02mo ago | ||||
| 134 |
BitoBito Inc. |
34 | — | — | — | 68 | — | ||||
| 140 |
CodeRabbitCodeRabbit Inc. |
332/4 | — | — | — | — | — | ||||
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.
All AI code review agents ranked
Best AI agents for testing software
Testing agents write end-to-end tests from plain-English descriptions, run them in CI and repair them when the interface changes.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 23 |
MomenticMomentic |
56 | 892K | up 192.3%One-day spike | up 118.0% | — | — | ||||
| 41 |
e2ee2e (formerly TesterArmy) |
50 | 1.3M | up 53.1% | — | 14K+45/day | 0.23.17d ago | ||||
| 78 |
mablmabl Inc. |
41 | 12.1K | down 5.7% | up 12.2% | — | — | ||||
| 159 |
ChecksumChecksum |
302/4 | 15.8K | down 26.0% | up 29.9% | — | — | ||||
| 246 |
KaneAITestMu AI (formerly LambdaTest) |
13 | 1,763 | down 2.2% | up 43.7% | 267 | 0.10.62d 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.
All AI testing and QA agents ranked
Best AI agents for designing interfaces and graphics
Design agents turn a brief into editable screens, prototypes or brand graphics and keep revising them. Several are features inside Figma, Canva or Claude.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 147 |
|
32 | — | — | — | 17.1K+188/day | 0.44.13d ago | ||||
| 171 |
StitchGoogle Labs |
29 | 38.7K | up 3.1% | down 4.0% | 1,857+1/day | 0.1.16mo ago | ||||
| 248 |
PresentonPresenton |
11 | 38 | down 51.3% | down 43.3% | 12K+16/day | 0.5.1015mo ago | ||||
| — |
Canva AICanva, Inc. |
— | — | — | — | — | — | ||||
| — |
Claude DesignAnthropic |
— | — | — | — | — | — | ||||
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.
Best AI agents for getting everyday tasks done
General agents take a goal in plain language ("research this", "fill this spreadsheet", "plan this trip") and use a browser, files and other tools to get there. Interest here moves fast: products can go from nothing to the top of search trends in weeks and fade as quickly.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 8 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
71 | 3.1M | up 5.8% | down 24.3% | 395K+120/day | 2026.10.332d ago | ||||
| 10 |
DeepSeek HarnessDeepSeek |
67 | 658K | down 22.5% | up 59.3% | 284K+685/day | — | ||||
| 13 |
Hermes AgentNous Research |
63 | 88.2K | up 34.8% | — | 265K+293/day | 0.23.24d ago | ||||
| 39 |
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore |
51 | — | — | — | — | — | ||||
| 56 |
Cloudflare OSCloudflare |
46 | — | — | — | 11.8K+10/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.
All general-purpose AI agents ranked
Best AI agents for automating workflows
Workflow tools connect your apps and let an AI step decide what happens next. Choose these when the same process runs many times and you want it visible as a flow, not hidden in a chat.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 4 |
n8nn8n |
79 | 107K | down 28.5% | up 4.9% | 211K+167/day | 1.123.982d ago | ||||
| 14 |
DifyLangGenius |
63 | — | — | — | 161K+80/day | 1.20.02d ago | ||||
| 44 |
AnythingLLMMintplex Labs |
50 | — | — | — | 68.4K+35/day | 1.20.03d ago | ||||
| 50 |
LangflowLangflow (DataStax, an IBM company) |
47 | 13.2K | down 19.0% | up 13.8% | 157K+36/day | 1.13.33d ago | ||||
| 79 |
|
412/4 | — | — | — | 32.6K+19/day | usage-counter11d 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.
All agent builders and workflow automation ranked
Best AI agents for building an app without writing code
App builders turn a description into a working web app with hosting. They suit prototypes and internal tools; for a long-lived product, check how easily you can export the code.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 11 |
LovableLovable |
66 | — | — | — | — | — | ||||
| 19 |
Replit AgentReplit |
60 | — | — | — | — | — | ||||
| 49 |
Bolt.newStackBlitz |
47 | — | — | — | 16.6K+3/day | — | ||||
| 132 |
Base44Wix (Base44) |
34 | 67.5K | up 2.1% | down 1.5% | 125 | 0.3.63d ago | ||||
| 143 |
v0Vercel |
332/4 | — | — | — | — | — | ||||
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.
Best AI agents for working in a browser
Browser agents click, type and read web pages on your behalf. Some are libraries for developers, others are full browsers with an assistant built in.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 16 |
Browser HarnessBrowser Use |
61 | 2.2M | down 0.3% | up 26.5% | 19.2K+19/day | 0.1.132mo ago | ||||
| 17 |
Browser UseBrowser Use |
60 | 2.2M | up 10.9% | down 5.8% | 121K+108/day | 1.0.64d ago | ||||
| 18 |
agent-browserVercel Labs |
60 | 2.5M | up 3.7% | up 29.9% | 52.7K+386/day | 0.43.08d ago | ||||
| 21 |
StagehandBrowserbase |
57 | 2.9M | down 13.3% | up 39.5% | 26.1K+14/day | 3.7.42d ago | ||||
| 76 |
ARTEMISGoogle |
422/4 | — | — | — | 17.7K+66/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.
All browser and computer-use agents ranked
Best AI agents for researching a topic
Research agents plan searches, read papers and web sources and write cited reports. Check the citations before you rely on the conclusions.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 71 |
BettaFish666ghj (community project) |
432/4 | — | — | — | 42.7K+16/day | 3.0.011mo ago | ||||
| 82 |
HorizonSheng Qiang |
412/4 | — | — | — | 14.8K+135/day | — | ||||
| 85 |
Autoresearchkarpathy |
40 | — | — | — | 100K+64/day | — | ||||
| 90 |
DexterVirat Singh |
402/4 | — | — | — | 27.9K+10/day | 1.1.058d ago | ||||
| 151 |
GPT ResearcherAssaf Elovic and contributors |
32 | 8,611 | down 5.1% | down 10.8% | 30.8K+21/day | 3.8.011d 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.
Best AI agents for analysing data
Data agents write and run SQL or Python against your files or warehouse and return charts and summaries. Prefer the ones that show the code they ran.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 142 |
PandasAISinaptik AI |
33 | 8,384 | up 16.1% | up 11.8% | 24K+2/day | 3.0.013mo ago | ||||
| 187 |
HexHex Technologies Inc. |
262/4 | — | — | — | — | — | ||||
| 224 |
WrenAICanner |
21 | — | — | — | 18.3K+29/day | 0.18.010d ago | ||||
| 244 |
|
15 | — | — | — | 2,159+7/day | — | ||||
| — |
Databricks GenieDatabricks |
— | — | — | — | — | — | ||||
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.
All AI data analysis agents ranked
Best AI agents for answering customers
Support agents answer customers in chat and email and hand over to a human when needed. Many are priced per resolved conversation, so compare the unit price, not only the monthly fee. Closed commercial products leave fewer public traces than open-source ones, so their scores rest on less data.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 35 |
RasaRasa |
52 | 43K | down 0.9% | down 31.6% | 21.4K+2/day | 3.6.2122mo ago | ||||
| 38 |
ChatbaseChatbase |
512/4 | 865 | up 1,960% | up 73.5% | — | — | ||||
| 53 |
Chatwoot CaptainChatwoot |
46 | — | — | — | 40.1K+67/day | 4.20.02d ago | ||||
| 57 |
BotpressBotpress |
46 | 24.8K | down 31.3% | up 17.1% | 15K+2/day | 12.30.93y ago | ||||
| 63 |
InkeepInkeep |
45 | 192K | up 15.4% | up 145.3% | 1,501 | 0.68.47mo 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.
All customer support AI agents ranked
Best AI agents for handling phone calls
Voice agents answer and place phone calls. Hosted platforms bundle telephony, speech and a model behind one API and charge per minute; open-source frameworks let you assemble and run the pipeline yourself.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 9 |
ElevenLabs AgentsElevenLabs |
692/4 | 3M | up 4.1% | up 37.8% | — | — | ||||
| 29 |
Retell AIRetell AI |
542/4 | 809K | up 13.0% | up 39.5% | — | — | ||||
| 36 |
LiveKit AgentsLiveKit |
52 | 1.2M | down 3.5% | up 22.4% | 15.3K+14/day | 1.8.132d ago | ||||
| 37 |
VapiVapi, Inc. |
522/4 | 645K | up 1.7% | up 26.3% | — | — | ||||
| 52 |
PipecatDaily |
47 | 391K | up 6.0% | up 40.0% | 17.3K+18/day | 1.16.08d 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.
Best AI agents for finding and contacting prospects
Sales agents research prospects, write outreach and book meetings. Most are closed, sales-led products with few public signals, so treat their order as a rough measure of visibility.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| — |
11x11x AI Inc. |
— | — | — | — | — | — | ||||
| — |
AiSDRAiSDR Inc. |
— | — | — | — | — | — | ||||
| — |
ArtisanArtisan AI Inc. |
— | — | — | — | — | — | ||||
| — |
ClayClay |
— | — | — | — | — | — | ||||
| — |
HubSpot Prospecting AgentHubSpot, Inc. |
— | — | — | — | — | — | ||||
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.
Best AI agents for producing marketing content
Marketing agents plan campaigns and produce on-brand content across channels, usually with a review step before anything is published.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| — |
Adobe GenStudio agentsAdobe Inc. |
— | — | — | — | — | — | ||||
| — |
AirOpsAirOps |
— | 2,371 | up 16.4% | up 22.0% | — | — | ||||
| — |
Copy.aiCopyAI, Inc. (Fullcast) |
— | — | — | — | — | — | ||||
| — |
HubSpot marketing agentsHubSpot, Inc. |
— | — | — | — | — | — | ||||
| — |
JasperJasper AI, Inc. |
— | — | — | — | — | — | ||||
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.
All AI marketing agents ranked
Best AI agents for recruiting and hiring
Recruiting agents source candidates, run first-round screening and schedule interviews. Automated hiring is regulated in several places, so keep a person making the decisions.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| — |
AlexApriora Inc. |
— | — | — | — | — | — | ||||
| — |
ConverzAIConverzAI |
— | — | — | — | — | — | ||||
| — |
|
— | — | — | — | 5,300+36/day | 1.15.02d ago | ||||
| — |
Eightfold AI InterviewerEightfold AI |
— | — | — | — | — | — | ||||
| — |
JuiceboxJuicebox |
— | — | — | — | — | — | ||||
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.
All AI HR and recruiting agents ranked
Best AI agents for finance and accounting work
Finance agents analyse filings and deal documents or run accounting workflows such as bookkeeping and close. Nothing here is investment advice.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| — |
BasisBasis |
— | — | — | — | — | — | ||||
| — |
FinRobotAI4Finance Foundation |
— | 152 | down 7.9% | down 22.1% | 8,449+7/day | 0.1.04mo ago | ||||
| — |
HebbiaHebbia |
— | — | — | — | — | — | ||||
| — |
Ramp agentsRamp |
— | — | — | — | — | — | ||||
| — |
RilletRillet |
— | — | — | — | — | — | ||||
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.
All AI finance and accounting agents ranked
Best AI agents for legal work
Legal agents research, draft and review contracts under a lawyer's supervision. Every citation still needs checking.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| — |
Clio WorkClio |
— | — | — | — | — | — | ||||
| — |
CoCounsel LegalThomson Reuters |
— | — | — | — | — | — | ||||
| — |
EvenUpEvenUp Inc. |
— | — | — | — | — | — | ||||
| — |
HarveyCounsel AI Corporation |
— | — | — | — | — | — | ||||
| — |
LegoraLegora |
— | — | — | — | — | — | ||||
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.
Best AI agents for investigating production incidents
AI SRE agents start investigating when an alert fires, correlate telemetry and recent changes and propose a root cause.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 177 |
OpenSRETracer |
28 | 63 | up 28.6% | up 138.4% | 12.9K+10/day | 0.1.2026.11.19yesterday | ||||
| 205 |
HolmesGPTRobusta (CNCF Sandbox) |
24 | 4,364 | down 23.7% | up 62.1% | 3,929+9/day | 0.46.016d ago | ||||
| 238 |
K8sGPTK8sGPT (CNCF Sandbox) |
15 | — | — | — | 8,339+3/day | 0.4.4130d ago | ||||
| — |
Bits AI SREDatadog |
— | — | — | — | — | — | ||||
| — |
ClericCleric |
— | — | — | — | — | — | ||||
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.
All AI SRE and DevOps agents ranked
Best AI agents for security testing and alert triage
Security agents run authorised penetration tests or triage security alerts like a SOC analyst. Only point them at systems you are allowed to test.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 51 |
|
472/4 | — | — | — | 10.1K+1,118/day | 0.6.09d ago | ||||
| 84 |
StrixStrix |
40 | 11.2K | up 11.5% | up 24.3% | 76.6K+224/day | 1.7.110d ago | ||||
| 94 |
Codex SecurityOpenAI |
392/4 | — | — | — | 14.1K+314/day | 0.10.12d ago | ||||
| 162 |
PentAGIVXControl |
29 | — | — | — | 34.6K+90/day | 2.2.046d ago | ||||
| 231 |
CAI (Cybersecurity AI)Alias Robotics |
20 | 878 | up 34.5% | up 25.1% | 9,867+2/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.
Best AI agents for building your own agent
Frameworks and SDKs are for developers building their own agents. Download numbers here are large because they include every app and CI pipeline that installs them.
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | ||||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | ||||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | ||||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | ||||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d 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.
All agent frameworks and SDKs ranked
Free and open-source options
Many of the agents above can be used without paying the vendor: either the code is open source and you bring your own model key, or there is a free tier. Ranked lists:
- Open-source AI agents
- Free AI coding agents
- Open-source coding agents
- Local AI coding agents that run with Ollama, LM Studio or llama.cpp
"Free" agents still cost something when they call a paid model, so check which models an agent supports and whether you can run a local one.
By task
Agents for specific jobs, each listed only where its own documentation describes that use: Excel and spreadsheets · research · presentations · email · building websites · data analysis · code review · web scraping · testing and QA · marketing · SEO · job search · personal assistant
By company
The big platforms each ship several agents, and their line-ups change often. Side-by-side overviews with status and pricing: Google · Microsoft and GitHub · OpenAI · Anthropic · Amazon and AWS
How to choose
- Start from the job, not from the leaderboard. Pick the category that matches what you want done.
- Shortlist two or three from the top of that category. Wide use and a recent release mean the product is maintained and that problems you hit have been hit before.
- Check the price model. A flat subscription with a quota, pay-per-token with your own key, or pay-per-result (common in support) behave very differently at scale.
- Try them on a real task from your own work with a clear definition of done, and compare the results you would actually have to check.
- Start with tight permissions. Let the agent propose and ask before it acts, and widen that as you learn where it is reliable.
For coding specifically, see the detailed guide: best AI coding agents. New to the topic? Start with what an AI agent is.
What these rankings cannot tell you
Usage numbers show what people choose, not how well an agent will do your particular task. Downloads include automated installs, closed products leave fewer public traces than open-source ones, and a score is our own formula, not a measurement of quality. Use the rankings to build a shortlist, and let a trial decide. Every number on this page is collected from public sources described on the sources page.
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 | ||||
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | ||||
| 4 |
n8nn8n |
79 | 107K | down 28.5% | up 4.9% | 211K+167/day | 1.123.982d ago | ||||
| 5 |
|
75 | — | — | — | — | — | ||||
| 6 |
CursorAnysphere (owned by SpaceX) |
73 | — | — | — | 33.3K+4/day | — | ||||
| 8 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
71 | 3.1M | up 5.8% | down 24.3% | 395K+120/day | 2026.10.332d ago | ||||
| 11 | 66 | — | — | — | — | — | |||||
| 17 |
Browser UseBrowser Use |
60 | 2.2M | up 10.9% | down 5.8% | 121K+108/day | 1.0.64d ago | ||||
| 24 |
DevinCognition |
56 | — | — | — | — | — | ||||
| 39 |
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore |
51 | — | — | — | — | — | ||||
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.