The Agents Index · Research
Research & Analysis
Data-driven reports on the AI agents and the agentic stack, what each tool does, what it costs, and whether it actually ships in production.
Explore this section
Type
69 pieces in the library below
On this page
Latest reportBuyer's guide
How Developers Should Choose a Coding Agent
Learn how coding agents differ in workflow, model choice, control, deployment, and cost, and what to check before choosing one.
Read the report01 The full library
Data report
In a browser: a census of 149 listings
124 of 149 listings answer yes for “In a browser”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
GPT models: a census of 149 listings
105 of 149 listings answer yes for “GPT models”. Counted from our own datasheet, with the query that reproduces every figure.
Buyer's guide
Which Coding Agents Have a Terminal CLI?
Learn which coding agents run from a command line, which only expose terminal features through an editor or browser, and what that means for choosing one.
Comparison
OpenCode vs Claude Code: Which Should You Pick?
Compare OpenCode and Claude Code on model choice, pricing, workflows, and limits to find the better fit for your coding work.
Data report
Cost per task: a census of 149 listings
116 of 149 listings answer yes for “Cost per task”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Getting your data out: a census of 149 listings
31 of 149 listings answer yes for “Getting your data out”. Counted from our own datasheet, with the query that reproduces every figure.
Buyer's guide
What This Week’s Agents Are Built to Do
A guide to this week’s additions, the work each one handles, who it suits, and the pricing published by its vendor.
Data report
Audit log: a census of 149 listings
28 of 149 listings answer yes for “Audit log”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Single sign-on: a census of 149 listings
14 of 149 listings answer yes for “Single sign-on”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Data residency: a census of 149 listings
35 of 149 listings answer yes for “Data residency”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Runs unattended: a census of 149 listings
99 of 149 listings answer yes for “Runs unattended”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Claude models: a census of 149 listings
88 of 149 listings answer yes for “Claude models”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Ships it: a census of 149 listings
18 of 149 listings answer yes for “Ships it”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Multi-agent: a census of 149 listings
83 of 149 listings answer yes for “Multi-agent”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
API access: a census of 149 listings
84 of 149 listings answer yes for “API access”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Free to use: a census of 149 listings
86 of 149 listings answer yes for “Free to use”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Pooled budget: a census of 149 listings
67 of 149 listings answer yes for “Pooled budget”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Done-for-you service: a census of 149 listings
14 of 149 listings answer yes for “Done-for-you service”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Writes code: a census of 149 listings
52 of 149 listings answer yes for “Writes code”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
On the command line: a census of 149 listings
67 of 149 listings answer yes for “On the command line”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Certifications: a census of 149 listings
63 of 149 listings answer yes for “Certifications”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Model choice: a census of 149 listings
74 of 149 listings answer yes for “Model choice”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
MCP server: a census of 149 listings
71 of 149 listings answer yes for “MCP server”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Seat model: a census of 148 listings
48 of 148 listings answer yes for “Seat model”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Whole-codebase work: a census of 149 listings
14 of 149 listings answer yes for “Whole-codebase work”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Opt out of training: a census of 149 listings
72 of 149 listings answer yes for “Opt out of training”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Admin controls: a census of 149 listings
60 of 149 listings answer yes for “Admin controls”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Open models: a census of 149 listings
53 of 149 listings answer yes for “Open models”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Agent permissions: a census of 149 listings
68 of 149 listings answer yes for “Agent permissions”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Debugs and fixes: a census of 149 listings
35 of 149 listings answer yes for “Debugs and fixes”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Writes tests: a census of 149 listings
20 of 149 listings answer yes for “Writes tests”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Bring your own key: a census of 149 listings
56 of 149 listings answer yes for “Bring your own key”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Reviews code: a census of 149 listings
26 of 149 listings answer yes for “Reviews code”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
In your pipeline: a census of 149 listings
28 of 149 listings answer yes for “In your pipeline”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Open source: a census of 149 listings
30 of 149 listings answer yes for “Open source”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
Self-hosted: a census of 149 listings
34 of 149 listings answer yes for “Self-hosted”. Counted from our own datasheet, with the query that reproduces every figure.
Data report
In your editor: a census of 149 listings
31 of 149 listings answer yes for “In your editor”. Counted from our own datasheet, with the query that reproduces every figure.
Comparison
Which AI Support Agents Skip the Sales Call? 4 of 9
We checked all 9 support agents in our index for self-serve access. Four publish a price and a signup page; the other five start with a sales call.
Comparison
25 AI Coding Agents Compared: Pricing and API Access
A field-by-field comparison of all 25 coding agents in our directory, split by pricing model and whether each one exposes a public API.
Comparison
Which of 14 AI Agent Frameworks Locks You to One Model?
We checked model-provider support across our 14 indexed agent frameworks. Only the Claude Agent SDK locks you to a single model vendor by design.
Data report
Which AI Agents Are Free to Start? 60 of 94
We read the published pricing tiers of the 94 classified AI agents in our index on 27 August 2026. 60 offer an ongoing free tier and 34 do not.
Data report
Research or Data Agent? 6 of 11 Return Structured Data
Our Research & data agents category holds 11 tools. Re-verified 26 August 2026: 6 return structured, machine-readable output as a named feature; 5 return prose.
Data report
Which AI Agents Have a Public API? 72 of the 81 We Could Confirm
We checked all 94 AI agents in our index for a public API on 22 August 2026. 72 of the 81 we could determine offer one, and 34 of the 35 you can self-host.
Data report
AI Agent Entry Prices: 40 of 92 Publish One, and the Median Is $20
We read the pricing table of all 92 tools in our index on 18 August 2026. 40 publish an exact flat monthly price in dollars, and the median is $20 a month.
Data report
CLI, Web App or Library? An Interface Census of 93 AI Agents
We recorded the primary interface of 93 of the 94 AI agents in our index on 20 August 2026. All 14 library-first tools self-host; 4 of 37 web apps do.
Data report
AI Agent Pricing Models: 21 of 93 Tools Bill by Usage
We classified the pricing meter on 93 of the 94 AI agents published in our index on 26 August 2026. 21 bill by usage, 15 of them voice or support agents.
Data report
How Many AI Agent Tools Publish a Full Price List? 30 of 92
We read all the pricing tiers recorded for the 93 tools in our index on 25 August 2026. 30 publish a figure for every tier, and 8 publish no price anywhere.
Buyer's guide
AI Agents for Sales & Marketing: What the 7 in Our Index Actually Do
The 7 sales and marketing agents we index split three ways: outbound, inbound, and the account-data layer underneath. Only 2 let you start without a sales call.
Buyer's guide
GitHub Copilot's Coding Agent: Three Surfaces, Three Defaults
Copilot's coding agent is the cloud one: you assign it an issue, it opens a pull request. It is not agent mode in VS Code, and it does not ask before it acts.
Data report
Which Coding Agents Run Commands Without Asking? 21 Tools, Checked
Cursor auto-applies edits but asks before commands. Codex CLI and OpenCode run both by default. We checked all 21 coding agents in our index against their own docs.
Data report
Which AI Agent Frameworks Support A2A? 12, Verified
A2A lets agents on different frameworks talk to each other. We checked all 12 frameworks in our index: 4 ship it natively, 3 as an add-on, 4 don't support it yet.
Data report
Does Your Coding Agent Train on Your Code? 21 Tools, Checked
SOC 2 confirms an audit was passed, not whether your code trains a model. We checked the default training policy, tier by tier, for 21 coding agents in our index.
Buyer's guide
Why AI Support-Agent 'Resolution Rate' Claims Aren't Comparable
Seven AI support agents in our index report success on different metrics: resolution, containment, deflection, accuracy. Here's what each one measures, and hides.
Buyer's guide
What 'Multi-Agent' Actually Means: Six Shapes, 36 Tools
36 of the 95 listings in The Agents Index carried our multi-agent tag on 28 August 2026. We sorted the sourced facts into six different shapes.
Data report
Terminal-Bench 2.1: How Our Indexed Coding Agents Actually Score
Stanford/Laude Institute's independent Terminal-Bench results, matched against the coding agents in our index: accuracy, model pairing and cost, not vendor claims.
Data report
GitHub Star Velocity: 30 Open-Source AI Agents Measured 7 Days Apart
Stars for 32 trackable open-source AI agents in our index, counted 2026-08-18 and 2026-08-25. OpenAI Codex CLI gained 11,317 stars in 7 days.
Data report
Which AI Agents Can You Self-Host? A Census of 94 Tools
Of the 94 AI agents in our index, 42 can run on infrastructure you control and 52 are cloud-only. Support and sales agents offer zero self-hosting.
Market analysis
Are AI Coding Agents & Frameworks Actually Open Source?
We read the license behind every AI agent in our index. All 94 product listings now have a determined answer, and 33 are open source in some form.
Statistics
Which AI Agents Won't Tell You What LLM Powers Them?
We checked all 93 AI agents in our index for the LLM underneath. Of the 92 we could classify, 23 name no model at all, and it tracks how the tool is sold.
Buyer's guide
How Much Do AI Agents Actually Cost? A Pricing FAQ
Intercom Fin, n8n, Clay, Lindy and LangChain each price agents differently: per resolution, per credit, per seat. What each one actually charges.
Market analysis
What Is MCP, and Which AI Agents Mention It?
We searched each listing's own attributes, key features and integrations for the text "MCP" on 27 August 2026: 70 of 94 mention it, 24 do not.
Market analysis
9 AI agent tools that changed how they charge in 2026
Nine 2026 pricing-change case studies, with verified old and new terms and what they mean for buyers of “free,” “bundled,” or “unlimited” plans.
Market analysis
Who owns the AI agent you're building on? A 2025–2026 field guide
Six tools in our index changed hands or raised historic rounds in nine months. What happened, what it already broke, and how to judge the risk before you adopt.
Statistics
AI Agent Statistics 2026: Adoption, Production, and Trust
Sourced 2026 statistics on AI agent adoption, production and developer trust, from Gartner, McKinsey, LangChain and Stack Overflow, plus our own 94-tool index.
Market analysis
AI voice agent funding vs. real growth: the 2026 gap
Vapi, Retell AI, Bland AI, ElevenLabs and Cartesia raised very different amounts. The one that raised the least reports the fastest, most profitable growth.
Tutorial
Using LangChain tools inside CrewAI agents: a working guide
CrewAI and LangChain are usually pitched as rivals. Their own docs disagree: the verified, working pattern for wrapping a LangChain tool for a CrewAI agent.
Data report
The State of AI Agents 2026: A Census of 93 Researched Tools
License, API, deployment and price for all 93 AI agents in our index, measured 26 August 2026. 33 are open source, and every self-host-only tool is one of them.
Comparison
Terminal AI coding agents: open, portable, or locked in?
We verified the license, model portability and pricing of six terminal AI coding agents: Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode and Goose.
Methodology
How The Agents Index researches AI agents
Our method for deciding what an AI agent actually does, what it costs, and whether it ships: sourced, quality-gated, and re-checked on a schedule.
No posts match that type.