@sperax/tool-research-intel

VC research intelligence from a16z, Paradigm, Messari, Delphi Digital and more — trend radar, industry outlooks, and actionable thesis analysis

Research Intel is an agent tool from SperaxOS, packaged headless so you can call it from any agent framework. It ships two things: the manifest — a JSON-Schema function definition a model can call — and the executor that runs the call against the real API.

There is no UI layer and no framework lock-in. It works anywhere TypeScript runs.

Install

npm install @sperax/tool-research-intel

Usage

Call it directly

import { researchIntelExecutor } from '@sperax/tool-research-intel';

const result = await researchIntelExecutor.invoke('getLatestReports', {"limit":1,"source":"<source>"}, {
  messageId: 'msg-1',
});

console.log(result.content); // prose summary written for the model to read
console.log(result.state);   // typed data payload for your own UI

Give it to a model

import Anthropic from '@anthropic-ai/sdk';
import { ResearchIntelManifest, researchIntelExecutor } from '@sperax/tool-research-intel';

const client = new Anthropic();

const response = await client.messages.create({
  model: 'claude-opus-4-8',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Ask something this tool can answer' }],
  tools: ResearchIntelManifest.api.map((api) => ({
    name: api.name,
    description: api.description,
    input_schema: api.parameters,
  })),
});

for (const block of response.content) {
  if (block.type !== 'tool_use') continue;
  const result = await researchIntelExecutor.invoke(block.name, block.input, { messageId: response.id });
  console.log(result.content);
}

ResearchIntelManifest.api is already in JSON-Schema form, so it maps onto any tool-calling API — Anthropic, OpenAI, the Vercel AI SDK, or an MCP server — without translation.

Every executor returns a BuiltinToolResult — { success, content, state }. content is prose written for the model to read; state is the typed data payload for your own code. Executors never throw: a failed call comes back as { success: false, content: '<reason>' }, so a network blip degrades the answer instead of crashing the agent loop.

Configuration — required

This tool needs a backend you control. It will not work on a bare npm install alone.

The upstream API requires a secret key. That key is deliberately not bundled here — shipping it in an npm package would leak it to every consumer. Instead the executor calls a SperaxOS /webapi/* route, which holds the key server-side and injects it. That route is session-authenticated, so the public deployment at https://chat.sperax.io (the default origin) answers 401 to anonymous callers.

To use this tool you need one of:

• a SperaxOS deployment of your own, or
• any HTTP endpoint that implements the same request shape and supplies the key.

Point the package at it before importing the tool — the URL is resolved once, when the module first loads:

SPERAX_API_BASE_URL=https://my-speraxos.example.com

or in code:

import { configureSperaxApi } from '@sperax/agent-tools-core';

configureSperaxApi({ baseUrl: 'https://my-speraxos.example.com' });

// import the tool only after configuring, so the path resolves against your origin
const { researchIntelExecutor } = await import('@sperax/tool-research-intel');

Inside a browser that already serves those routes at its own origin, requests stay same-origin and no configuration is needed.

If you want a tool that runs with zero setup, use one of the standalone tools — those call public APIs directly and need no key, no origin, and no backend.

Tool identifier

sperax-research-intel

API reference

getLatestReports

Fetch the latest research reports from top VC firms and crypto research organizations. Optionally filter by source firm (a16z, paradigm, messari, delphi, galaxy, pantera, electric-capital, variant, multicoin) or topic tag (defi, infrastructure, ai, gaming, social, regulation, scaling, privacy, identity, rwa).

| Parameter | Type | Required | Description | | --- | --- | --- | --- | | limit | number | no | Maximum number of reports to return (default: 10) | | source | string | no | Filter by publishing firm: a16z, paradigm, messari, delphi, galaxy, pantera, electric-capital, variant, multicoin | | topic | string | no | Filter by topic tag: defi, infrastructure, ai, gaming, social, regulation, scaling, privacy, identity, rwa |

searchResearch

Search across all indexed VC research by keyword, technology, or thesis. Returns matching reports with key takeaways and source attribution.

| Parameter | Type | Required | Description | | --- | --- | --- | --- | | limit | number | no | Max results (default: 10) | | query | string | yes | Search query — topic, technology name, or thesis (e.g. "account abstraction", "AI agents", "intent-based architecture") | | source | string | no | Optionally restrict search to a specific firm |

getTrendRadar

Get the trend radar — a bird's-eye view of emerging technologies and themes across all VC research. Each trend includes a confidence score (0-100), maturity stage (emerging/growing/mainstream/declining), mention count across firms, and time horizon (near-term/mid-term/long-term).

| Parameter | Type | Required | Description | | --- | --- | --- | --- | | category | string | no | Filter by category: defi, infrastructure, ai, gaming, social, regulation, scaling, privacy | | horizon | string | no | Filter by time horizon: near-term (<1yr), mid-term (1-3yr), long-term (3-5yr+) | | limit | number | no | Max trends to return (default: 20) |

getOutlook

Get a structured industry outlook with predictions organized by category. Each prediction includes confidence level and supporting evidence. Choose a time horizon: 1yr (near-term tactical), 3yr (mid-term strategic), or 5yr (long-term visionary).

| Parameter | Type | Required | Description | | --- | --- | --- | --- | | category | string | no | Focus on a specific category: infrastructure, defi, consumer, regulation, ai-crypto, identity, scaling | | horizon | string | no | Time horizon: 1yr, 3yr, or 5yr (default: 1yr) |

getThesisSummary

Deep-dive into a specific firm's thesis or report. Returns the full summary, key takeaways, actionable insights for builders, and relevance analysis for the SperaxOS ecosystem.

| Parameter | Type | Required | Description | | --- | --- | --- | --- | | report | string | no | Specific report title or URL (optional — if omitted, uses the firm's most recent major report) | | source | string | yes | Which firm's thesis to summarize (e.g. "a16z", "paradigm", "messari") |

Types

Shared types come from @sperax/agent-tools-core: BuiltinToolManifest, BuiltinToolResult, BuiltinToolContext, and the BaseExecutor class every tool executor extends.

Related

• @sperax/agent-tools-core — the tool contract
• All SperaxOS agent tools — tool-research-intel is one of many
• SperaxOS — the agent workspace these tools were built for

License

Apache-2.0