Coming soonAccounts and the planned features are not open yet.See what is planned
Agent tooling startup
AgentsUse builds the tools AI agents use.
We are building APIs, MCP servers, and SDKs for agent runtimes. The work starts from a simple observation: a model can only act through the tools it is given, and those tools need contracts, permissions, and operating limits that hold up outside a demo.
24 tools · 19 MCP servers · 6 frameworks · 4 stacks · 37 guides · 9 harness patterns
Market map
The tool layer, organized by job
- Browser AutomationBrowser drivers and agent layers for opening pages, reading content, and acting through a real browser engine.7 verified tools
- Web Data and Document ExtractionFetchers and converters that turn web pages and documents into structured input for an agent or model.4 verified tools
- Search and Retrieval APIsSearch indexes and content APIs that let an agent find, rank, and read web information.3 verified tools
- Code Execution SandboxesIsolated environments where agents can run code, install packages, and keep state without touching your machine.1 verified tool
- Tool Integration PlatformsPlatforms that give agents authenticated access to apps and APIs through one integration layer.3 verified tools
- Agent Observability and EvaluationTracing, logging, and evaluation platforms for reviewing agent behavior, cost, and output quality.4 verified tools
- Agent MemoryMemory layers that let agents remember users, facts, and prior work across sessions.2 verified tools
- APIs, MCP servers, and SDKs that give agents a defined way to search, read, compute, and act.
- Through a harness that validates calls, gates consequential actions, budgets results, and records the run.
- It maps the tool layer agents use today, with setup, limits, and sources builders can check.
Live today
Live today- Public market map: source-checked tools, MCP servers, frameworks, stacks, and guides.
- Browser workspace: saved stacks, JSON and CSV export, and a watchlist on your device.
- Production harness checklist: 24 checks for validation, gates, retries, logs, and scope.
Coming soon
Coming soon- Catalog API: verified records and check dates as structured data.
- Accounts and change alerts: account sync and alerts for watched entries. Not built yet.
- Vendor listings: planned paid offers for vendors. Not open for purchase. Readers always pay $0.
Tool profiles
What a useful profile has to answer
Purpose, setup, operating limits, maintenance signals, and alternatives, each traced to a primary source.
Showing 24 of 24 tools, in alphabetical order. Nothing paid changes this order.
Actions runtime for AI agents with authorized tool calling, managed OAuth and tokens, a prebuilt MCP tool catalog, and an open-source MCP framework.
Tool Integration PlatformsFreemiumOpen sourceArcade CloudVPC on EnterpriseChecked 2026-10-29
Active observability and evaluation platform for agents, from production tracing to experiments and scoring in one system.
Observability and EvaluationFreemiumNot open sourcecloudhybridChecked 2026-10-29
An independent search index exposed as APIs for web, news, images, video, places, and LLM-ready context for agent grounding.
Search and Retrieval APIsFreemiumNot open sourcecloudAPIChecked 2026-10-29
An open-source Python library that lets an LLM agent open pages, click, type, and fill forms from a plain task description.
Browser AutomationOpen sourceOpen sourceSelf-hosted libraryHosted cloud (optional)Checked 2026-10-29
A cloud platform that gives agents browsers to drive, plus search, fetch, and a runtime for running them.
Browser AutomationUsage basedNot open sourcecloudChecked 2026-10-29
Tool platform for AI agents with pre-authenticated toolkits, per-user sessions, managed authentication, triggers, and a sandboxed workbench across a large app catalog.
Tool Integration PlatformsFreemiumOpen sourceManaged cloudHosted MCP endpoint per sessionChecked 2026-10-29
An open-source Python crawler that turns any website into clean, LLM-ready markdown for agents and RAG pipelines.
Web Data and Document ExtractionOpen sourceOpen sourceSelf-hosted libraryDocker serverChecked 2026-10-29
Isolated Linux sandboxes in the cloud for running code written by AI agents, with Python and JavaScript SDKs and a separate code interpreter SDK.
Code Execution and SandboxesUsage basedOpen sourceManaged cloudSelf-hosted runtimeChecked 2026-10-29
A search API for AI: natural-language queries over an index built for agents, with content returned in model-ready shapes.
Search and Retrieval APIsFreemiumNot open sourcecloudAPIChecked 2026-10-29
A web data API that searches, scrapes, and crawls sites into clean markdown and structured output for AI agents.
Web Data and Document ExtractionFreemiumOpen sourceHosted APISelf-hosted (open source)Checked 2026-10-29
Open source AI gateway and LLM observability platform with one-line integration to monitor, evaluate, and route requests.
Observability and EvaluationFreemiumOpen sourcecloudself-hostedChecked 2026-10-29
A hosted API that converts any URL into LLM-friendly markdown by adding a prefix, with web search through the same pattern.
Web Data and Document ExtractionFreemiumOpen sourceHosted APISelf-hosted DockerChecked 2026-10-29
Open source LLM engineering platform for tracing, prompt management, evaluation, and debugging of AI applications.
Observability and EvaluationFreemiumOpen sourcecloudself-hostedChecked 2026-10-29
Agent and LLM observability platform from LangChain for tracing, monitoring, and evaluating applications in production.
Observability and EvaluationFreemiumNot open sourcecloudbring-your-own-cloudChecked 2026-10-29
A lightweight Python utility that converts files and Office documents into markdown for LLMs and text pipelines.
Web Data and Document ExtractionOpen sourceOpen sourceSelf-hosted libraryCommand lineChecked 2026-10-29
Memory layer for AI agents that persists user, session, and agent context across conversations for personalized applications.
Agent MemoryFreemiumOpen sourcelibraryself-hostedChecked 2026-10-29
A browser automation framework that drives Chromium, Firefox, and WebKit with a single API for tests, scripts, and AI agents.
Browser AutomationOpen sourceOpen sourceSelf-hosted libraryLocal browserChecked 2026-10-29
A JavaScript library that controls Chrome and Firefox through a high-level API for automation, scraping, and testing.
Browser AutomationOpen sourceOpen sourceSelf-hosted libraryLocal browserChecked 2026-10-29
The long-running open-source WebDriver standard for driving real browsers, now adding WebDriver BiDi for event-driven control.
Browser AutomationOpen sourceOpen sourceself_hostedChecked 2026-10-29
A browser agent SDK with act, observe, and extract calls for interacting with sites and pulling structured data.
Browser AutomationOpen sourceOpen sourceSelf-hosted libraryHosted cloud (optional)Checked 2026-10-29
An open-source browser API for AI agents and apps: a batteries-included browser sandbox you can self-host or run as Steel Cloud.
Browser AutomationOpen sourceOpen sourcecloudself_hostedChecked 2026-10-29
A web access API built for AI agents: search, extract, map, crawl, and research endpoints behind one key.
Search and Retrieval APIsFreemiumNot open sourcecloudAPIChecked 2026-10-29
AI workers and a tool platform that connect agents to many services and MCP servers, so repetitive tasks can be delegated in plain language or built with an SDK.
Tool Integration PlatformsUsage basedNot open sourceManaged cloudPrivate cloud on BusinessChecked 2026-10-29
Managed agent memory platform that builds temporal context graphs from conversations and business data for governed retrieval.
Agent MemoryFreemiumNot open sourcecloudcloud-byokChecked 2026-10-29
Compare up to 3
Tick Compare beside two or three tools above. Every recorded characteristic appears here side by side, and you can click a column header to sort the rows.
MCP servers
Connection details before you paste a config
Transport, runtime, placeholder configuration, environment variables, exposed tools, and security scope.
stdio / sse
Playwright MCP Server
Microsoft MCP server that automates a real browser through Playwright from accessibility snapshots, without a vision model.
Checked 2026-10-29
stdio
Filesystem MCP Server
Node.js MCP server for file operations scoped to explicitly allowed directories.
Checked 2026-11-03
streamable-http / stdio
GitHub MCP Server
Official GitHub MCP server that connects AI tools to repositories, issues, pull requests, Actions, and code analysis on GitHub.
Checked 2026-10-29
streamable-http
Context7 MCP Server
Context7 MCP server that injects current, version-specific documentation and code examples into the model prompt.
Checked 2026-11-03
The Harness
A tool call needs an operating layer.
The harness sits between a model and its tools. It checks arguments before execution, holds consequential calls for approval, sets timeouts and retry bounds, controls how much of a result re-enters context, and leaves a record a reviewer can read. AgentsUse publishes nine patterns for that layer, three long-form guides, and notes inside selected profiles.
The AgentsUse framework is in the works, not shipped. Request early access
- Argument validation before executionMalformed arguments execute and fail downstream, or the model burns turns guessing the format you wanted.
- Permission gating and human approvalThe agent sends, deletes, or spends before anyone reviews the actual call.
- Context budgeting for tool resultsOne oversized result evicts the instructions and constraints the model still needs.
- Error recovery and bounded retriesA transient failure ends the run, or a permanent failure gets retried until latency and cost spin out of control.
Frameworks
Frameworks, read through their tool behavior
Scope, setup, MCP support, and compatibility records that link to the evidence behind each pairing.
Framework
LangChain
Agent framework for Python and TypeScript that standardizes model, tool, and retrieval interfaces so teams can swap providers without rewriting the agent loop.
Checked 2026-10-29
Framework
LangGraph
Low-level Python orchestration runtime for long-running, stateful agents that need durable execution, explicit state, and human review points.
Checked 2026-10-29
Framework
CrewAI
Python framework for role-based multi-agent work, pairing autonomous Crews with event-driven Flows for controlled production workflows.
Checked 2026-10-29
Framework
LlamaIndex
Python framework for ingestion, indexing, and retrieval that grounds agents and LLM applications in private data.
Checked 2026-10-29
Framework
Haystack
Python orchestration framework for production LLM applications built from explicit, modular pipelines and agents.
Checked 2026-10-29
Framework
Microsoft Agent Framework
Microsoft's open-source framework for building, orchestrating, and deploying AI agents and multi-agent workflows in Python, .NET, and Go, built as the direct successor to AutoGen and Semantic Kernel.
Checked 2026-10-29
Reference stacks
Workflows with the control points left in
A defined job, the components that do it, the order they run in, and the points where a person approves or intervenes.
Web research and briefing
Research Briefing Stack
Reference workflow for cited briefs: Tavily handles discovery and extraction, LangGraph runs a stateful planning loop, Langfuse records traces for review. Drawn from the AgentsUse catalog as a composition pattern.
3 verified components
Browser QA and regression checking
Browser QA Stack
Reference workflow for browser regression work: Playwright runs deterministic checks, the Playwright MCP server supports agent-led failure investigation with artifacts.
3 verified components
Turning websites and documents into agent-ready data
Web Data Pipeline Stack
Reference workflow for building an agent-ready corpus: Crawl4AI extracts pages, MarkItDown normalizes documents, Mem0 retains durable facts, LangSmith traces consumption back to inputs.
4 verified components
Coding assistance with project context
Coding Assistant Stack
Reference workflow for scoped coding assistance: Filesystem and Git provide repository access, Context7 supplies current library documentation, Sequential Thinking structures multi-step analysis.
4 verified components
Guides
Operating judgment for agent work
Delegation, permissions, failure handling, evaluation, cost, and handoff, written for the person who owns the result.
Guide
10 Tasks AI Agents Handle Well (and 5 to Keep in Your Hands)
Where AI agents earn their keep in 2026 and where they still fall short. A decision grid for delegating checkable, low-cost work and keeping judgment, money, and public commitments in human hands.
2026-09-26
Guide
Comparing AI Agent Frameworks
Framework marketing converges on the same claims. The dimensions that matter for choosing: control, observability, tooling, deployment, cost, and team fit, plus a 30-day evaluation plan and the build-versus-buy math.
2026-09-29
Guide
A Checklist Before Letting an AI Agent Touch Real Work
Twelve checks before an agent touches customers, money, or public communication. Covers least-privilege access, written instructions and limits, trial runs, action logs, and rollback, calibrated by risk tier.
2026-09-26
Guide
Agent Security Risks You Must Handle
Agents read untrusted content, run code, and call APIs with your credentials. The risks that materialize in production, from prompt injection to credential leakage, and the layered mitigations that contain them.
2026-09-29
Guide
How to Choose an AI Agent for a Specific Task
A job-first framework for choosing an agent for one specific task. Write the job down, score candidates on five criteria, run a same-task test on your own inputs, and cost the winner before it touches real work.
2026-10-04
Guide
When Not to Use AI Agents
Knowing when not to deploy an agent is a core operating skill. Where agents are overkill, where they are dangerous, the hidden costs of defaulting to them, and what to use instead.
2026-09-29
AgentsUse is building the tool layer AI agents run on. The catalog stays public because it is the map we build from: what agents can call today, where the contracts are thin, and where a better tool should exist.
Know a tool, server, or framework the map is missing? Suggest it for review. Submissions enter a queue and are never published automatically.