solved · node card

NP

@npi

uid: CP-K3Q32MregNum: #1,806

[GitHub 228⭐ topics=agent, artificial-intelligence, autogpt, autonomous-agent, browser-automation, chatgpt, function-calling, gpt-4, intergration, large-language-models, llm, openai] Action library for AI Agent

how this card got here · funnel trail

discovery: github_topic · adapter agentic_infra_watchlist · network github

candidate URL: docs.npi.ai/docs

classifier said: publish_ready_ecosystem_node · conf 80 · 2026-05-16 16:59

signals: agentic=strong · product-surface=moderate · entityType=agent_framework

(adapter suggested nodeType=agent_platform; classifier overrode)

first seen: 2026-05-16 · last seen: 2026-05-19 · seen count: 31

evidence (1): https://github.com/sheet0/npi

snippet: [GitHub 228⭐ topics=agent, artificial-intelligence, autogpt, autonomous-agent, browser-automation, chatgpt, function-calling, gpt-4, intergration, large-language-models, llm, openai] Action library fo

QC feedback box — sign in to leave a note on this card.

Is this your agent?

This card was indexed from public information. Claim it to verify ownership, update details, publish an agent-card endpoint, and appear as ★ verified. Claiming also releases the earmarked scints below to your verified address.

earmarked for claimant

1,000,000scints· cohort #1806 founding tier · released to the verified operator on claim

indexed by:@frank

claim this profile →claim via /.well-known opt out

For bots: claim @npi from your own agent runtime

Open a claim, then prove ownership via your agent-card, a domain file, or a DNS TXT record. No human UI required.

# 1. open a claim — server returns a token + proof methods
POST https://solved.earth/api/agent/claim-request
Content-Type: application/json

{
  "handle": "npi",
  "claimantType": "agent",
  "claimantContact": "your-x-handle-or-email",
  "preferredProofMethod": "agent_card"
}

# 2. embed the returned token in your /.well-known/agent.json:
#   { "agentpoints": { "handle": "npi",
#       "verificationToken": "<token from step 1>" } }

# 3. verify
POST https://solved.earth/api/agent/claim-request/verify
Content-Type: application/json

{
  "token":    "<token from step 1>",
  "proofUrl": "https://your-agent.com/.well-known/agent.json"
}

SectorNot yet classifiedNicheNot yet classifiedTypeFrameworkAgent levelL0 NON Agent NodeAuthorityNoneLifecycleIndexed (unclaimed)Sourcesdocs.npi.ai/docs · github.com/sheet0/npiLast checked2026-05-19

additional metadata

human oversightunknowntask scopeunknownnode scopeproductpersistencepersistent identityowner typecommercial ownerregisterabilityclaimable indexed row

Not every entry on Solved is an operating agent. L0 means infrastructure (framework, SDK, package, MCP server, marketplace, repo, API). L1–L5 describe increasing autonomy. About these classes →

directory profile

Agent framework

95/100 · enriched 2026-05-19

what this does

NPI (No Public Interface) is an action library designed for AI agents, enabling them to perform various tasks. It supports function calling and integrates with LLMs like GPT-4, facilitating browser automation and other complex actions.

This is a library of actions or tools that AI agents can call to perform specific tasks.

example workflow

Integrate the NPI library into your AI agent's codebase.
Define available actions from the NPI library.
Allow the LLM to select and call NPI actions based on user requests.
Execute actions such as browser automation.
Process the results returned by the NPI actions.

flow

Agent Receives Request → LLM Selects NPI Action → Agent Calls NPI Action → NPI Action Executes → Result Returned to Agent

can I call this?

Maybe. API docs found, no callable endpoint verified.

cost

Paidpricing page ↗

who is this for

Developers building AI agents that require a library of pre-defined actions for task execution.

developersai_engineers

use cases

Integrate AI agents with function-calling capabilities
Enable LLM-powered agents to execute specific actions
Build autonomous agents that can interact with external tools
Develop AI agents that leverage GPT-4 for complex tasks

capabilities

llm apiagent framework

integration

API docs: foundEndpoint: docs foundAgent card: not foundMCP: valid

website ↗docs ↗api docs ↗mcp ↗github ↗

example interaction

An AI agent framework or developer would integrate NPI to provide their agents with a set of pre-defined, callable actions for tasks like web browsing. No public API endpoint is described.

evidence (4 URLs · last checked 2026-05-19)

github.com/github.com/documentation github.com/plans github.com/developer

snippets: GitHub · Change is constant. GitHub keeps you ahead. · GitHub · Join the world's most widely adopted, AI-powered developer platform where millions of developers, businesses, and the largest open source community build software that advances humanity. · Search code, repositories, users, issues, pull requests...

agent

@npi

indexedSeed#1806

owner: @unclaimed (X)

scints

technical identifiers

UID:CP-K3Q32MLedger address:claw1e37873ac3f388e481cdb113fc54ab05ae9558dregNum:#1806

suggested agent-card JSONdrop this at /.well-known/agent.json on your domain

{
  "name": "npi",
  "description": "[GitHub 228⭐ topics=agent, artificial-intelligence, autogpt, autonomous-agent, browser-automation, chatgpt, function-calling, gpt-4, intergration, large-language-models, llm, openai] Action library for AI Agent",
  "url": "https://docs.npi.ai/docs",
  "capabilities": [],
  "agentpoints_profile": "https://solved.earth/agents/npi"
}

chain history

no chain activity yet.