AI Agents
Pre-built agents you can install, inspect, and run. Every agent declares what it does, what it needs, and how it behaves — in a single, standardized manifest.
What is an AgentNode Agent?
An AgentNode agent is a self-describing AI agent packaged with a standardized manifest. Unlike traditional AI agents that hide their behavior in code, AgentNode agents declare everything upfront: their goal, behavior, tool access, permissions, and limits.
This means you can inspect before you install. You know exactly what the agent does, which tools it uses, what API keys it needs, and what permissions it requires — before running a single line of code.
Agents are composable. They use AgentNode tool packs as building blocks — a research agent might combine web search, page extraction, and document summarization, all installed from the registry.
Each agent is automatically verified by AgentNode before listing: installed, imported, and smoke-tested in a sandbox. You see the verification score, tier, and any issues upfront.
Agent Tiers
Agents are classified by what they need to run. This tells you at a glance how much trust and configuration is required.
LLM Only
Pure reasoning agents. They use your LLM to think, write, and plan — no external tools or API calls needed.
Examples: Blog writer, newsletter, project planner, report generator
LLM + Tools
Agents that combine LLM reasoning with AgentNode tool packs. They search the web, extract documents, analyze data, and more.
Examples: Deep research, code review, competitive intel, fact checker
LLM + Credentials
Agents that connect to external services using API keys or OAuth. They interact with your CRM, cloud provider, email, or databases.
Examples: CRM enrichment, cloud cost analysis, email triage, deployment
How It Works
Install
One command. The agent and all its dependencies are downloaded, verified, and installed locally.
agentnode install deep-research-agent
Configure
Each agent declares what it needs: API keys, permissions, tool access. You see everything upfront — no hidden behavior.
result = run_tool("deep-research-agent",
goal="Compare React vs Vue in 2026")Run
Agents run locally on your machine with declared isolation. They orchestrate tool calls, handle errors, and return structured results.
print(result["report"]) print(result["sources"])
Why AgentNode Agents?
Standardized Manifest
Every agent declares its goal, behavior, permissions, tool access, and limits in a single agentnode.yaml. No guessing what an agent does or needs.
Verified Before You Install
Each agent is automatically installed, imported, and smoke-tested by AgentNode before listing. You see the verification score and tier upfront.
Transparent Behavior
The agent's behavior description, tool access, system prompt, and permission levels are all visible on the package page. Nothing is hidden.
Any LLM Provider
Agents work with any LLM provider — OpenAI, Anthropic, Gemini, or OpenRouter. The agent uses the same model that invokes it, auto-detected from your API key.
Declared Permissions
Network access, filesystem access, code execution — every permission level is declared in the manifest and shown before installation.
Composable
Agents use AgentNode tool packs as building blocks. A research agent combines web search, page extraction, and summarization — all from the registry.
Available Agents
View allAcademic Research Agent
Search academic papers on arXiv and Google Scholar, extract citations, and produce a literature review.
API Design Agent
Generate an OpenAPI specification from requirements, validate it, and produce API documentation.
Blog Writer Agent
Research a topic and write an SEO-optimized blog post with proper structure, keywords, and meta description.
CI/CD Agent
Set up and manage CI/CD pipelines: configure builds, run tests, build containers, and deploy.
Cloud Cost Agent
Analyze cloud infrastructure costs across AWS/Azure, identify waste, and recommend optimization strategies.
Code Review Agent
Perform comprehensive code review: lint, security audit, refactoring suggestions, and best practices check.
Competitive Intelligence Agent
Analyze competitors by scraping their web presence, monitoring news, and producing a competitive analysis report.
Contract Review Agent
Analyze legal contracts, flag risky clauses, compare against templates, and suggest amendments.
CRM Enrichment Agent
Enrich CRM contacts with public web data: company info, social profiles, recent news, and role details.
CSV Analyst Agent
Upload a CSV, detect patterns and anomalies, generate visualizations, and produce an analysis report.
Data Pipeline Agent
Build and run a data pipeline: load from CSV/JSON, clean and transform, then output to a target format.
Deep Research Agent
Conduct deep multi-source research on any topic, synthesize findings from web and documents into a structured report.
Dependency Audit Agent
Scan project dependencies for known vulnerabilities, outdated versions, license issues, and leaked secrets.
Deployment Agent
Orchestrate application deployments: build, test, push images, deploy to cloud, verify health, and notify the team.
Email Triage Agent
Prioritize incoming emails, draft responses for routine messages, and create tasks from action items.
Fact Check Agent
Verify claims against multiple web sources and produce a fact-check verdict with supporting evidence.
Log Investigator Agent
Parse log files, identify errors and anomalies, correlate events, and produce an incident report.
Meeting Prep Agent
Prepare for meetings by researching attendees, summarizing relevant docs, and generating an agenda with talking points.
News Digest Agent
Aggregate news from multiple sources on a topic, summarize key stories, and optionally translate for multilingual digests.
Newsletter Agent
Curate top stories on a topic, summarize them, and draft a ready-to-send newsletter email.
Project Planner Agent
Break down a project goal into user stories, tasks, and milestones with time estimates.
Report Generator Agent
Transform raw data (CSV, JSON) into a formatted report with charts, tables, and executive summary.
Security Scanner Agent
Run a comprehensive security scan on a codebase: SAST, dependency vulnerabilities, secret detection, and compliance check.
SEO Research Agent
Audit a website's SEO by analyzing content, keywords, meta tags, and competitor rankings.
Social Media Agent
Create platform-optimized social media posts with copy, hashtags, and image suggestions from a topic or URL.
Spreadsheet Auditor Agent
Audit Excel/CSV spreadsheets for errors, duplicates, formula issues, and data inconsistencies.
SQL Report Agent
Answer natural language questions about a database by generating SQL queries, executing them, and visualizing results.
Technical Documentation Agent
Generate API documentation and developer guides from source code, including examples and type signatures.
Test Writer Agent
Analyze source code and generate comprehensive test suites with unit tests, edge cases, and mocks.
Website Monitor Agent
Monitor websites for content changes, downtime, and visual regressions, and send alerts via Slack or email.
Build Your Own Agent
Create an agent with a standardized manifest, publish it to the registry, and let others install and run it. The manifest format is open and documented.