What did Hlido score juanjuandog/FinSight-AI?

juanjuandog/FinSight-AI scored 82/100 (STEADY) in Hlido's independent, hands-on review.

How much does juanjuandog/FinSight-AI cost?

Hlido recorded the pricing model as: Open source. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

juanjuandog/FinSight-AI

Name: juanjuandog/FinSight-AI review
Item: juanjuandog/FinSight-AI
Rating: 82
Author: Hlido Editor

Research · tested 2026-09-24 · by the Hlido desk, not the vendor

In short: An open-source, infrastructure-heavy AI equity-research agent — evidence-grounded reports, pgvector RAG, resilient workflows — that is more a reference architecture for building agents than a turnkey product.

9 PASS · 1 FAIL of 10 public-surface claims

Visit juanjuandog/FinSight-AI → scorecard.json

Quick answer

juanjuandog/FinSight-AI scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-24). STEADY reflects a substantial, well-architected, MIT-licensed project with documented install, CI, and recent activity, whose evidence-tracing and RAG-evaluation focus is genuinely above the category norm. Pricing: Open source (free entry point documented).

Hlido Editor · 2026-09-24

FinSight AI turns filings, financial reports, research notes, and market data into source-grounded answers and versioned research reports, and it is refreshingly upfront that its point is the infrastructure around an AI agent, not just the model call. The stack shows it: Spring Boot backend, PostgreSQL + pgvector for RAG, Redis with Lua single-flight to deduplicate concurrent work, RabbitMQ for workflow orchestration, plus evidence tracing and a RAG-evaluation harness. For a developer studying how to build a resilient, evaluable research agent — with proper caching, deduplication, versioning, and evidence traceability — this is a genuinely instructive, MIT-licensed reference. As a product for a non-technical equity researcher, it is not that: it is a self-hosted, backend-heavy application you must stand up and operate, and it needs your own data feeds and model keys. The evidence-tracing and RAG-eval focus is the standout, because it treats "can you trust this report?" as a first-class engineering concern rather than a disclaimer. Hlido assessed the repo and its public surface, not a live research run, so report quality itself is unverified here.

Why STEADY

STEADY reflects a substantial, well-architected, MIT-licensed project with documented install, CI, and recent activity, whose evidence-tracing and RAG-evaluation focus is genuinely above the category norm. Not higher because this is a repo-health + public-surface assessment (medium confidence) — Hlido did not run a live research workflow — and it is a self-hosted reference architecture, not a turnkey product, which limits who can actually use it.

Public-surface checklist

PASS Repo reachable (required) — GH API 200 for juanjuandog/FinSight-AI
PASS Readme present (required) — README length 20218
PASS License present (required) — MIT
PASS Install documented (required) — install/usage section found in README
PASS Active 12mo (required) — last push 51d ago
FAIL Releases present — no releases
PASS Community traction — 1123 stars
PASS Ci or tests — 1 workflow file(s)
PASS Recent commit 90d — last push 51d ago
PASS Agent consumable — CLI install line in README

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-3e4b95c49b6ededc-github-com). Our own captures — not vendor marketing material.

juanjuandog/FinSight-AI — run screenshot 1 (home.png) — home.png

What it does well

Treats trust as engineering: evidence tracing and a built-in RAG-evaluation harness, not just an AI disclaimer
Serious resilience architecture — Redis Lua single-flight, RabbitMQ workflows, versioned reports
pgvector RAG on PostgreSQL keeps the stack conventional and self-hostable
MIT-licensed and openly documented — a strong learning reference for building research agents
Runnable institutional-research console that exposes the workflow, cache, and evidence trace

What it fails at

Backend-heavy and self-hosted — significant setup and operational burden, not a turnkey product
Requires the user to supply data feeds and model keys
Report quality is unverified here; Hlido assessed the repo, not a live equity-research run
Targeted at developers, not the equity researchers who are the end audience of the output
No hosted demo to evaluate output quality before standing up the whole stack

Red flags

Financial research output must not be treated as investment advice; the project is a tool/reference, and report accuracy was not verified by Hlido at this evidence tier.

Best for

Developers learning how to build a resilient, evaluable, evidence-grounded RAG research agent
Fintech/research engineering teams wanting a self-hostable reference architecture to adapt
Anyone who needs versioned reports with an auditable evidence trail
Teams that value RAG evaluation being built in rather than bolted on

Not recommended for

Non-technical equity researchers wanting a ready-to-use product
Teams without the appetite to run Spring Boot + PostgreSQL + Redis + RabbitMQ
Buyers who need investment-grade output quality independently validated before adoption
Anyone expecting bundled market-data feeds (bring your own)

Pricing & access

ModelOpen source
Free entry pointYes — a free tier or open-source edition is documented

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.

Related agents

Agent relevance

API

Agentic-Commerce Readiness 29/100 · SURFACE-ONLY

Independent readiness for agent delegation & transaction. How it’s scored · check live

A self-hosted Spring Boot backend with a research console; integration is via standing up the service and its APIs. No MCP server or CLI advertised. More a system to run than a component to embed.

Agent-friendly score: 5/10

Evidence

Public repository reachable with substantive README — source (2026-09-24) verified
Product description: "AI equity research agent with resilient workflows, Redis Lua single-flight, pgvector RAG, versioned reports, evidence tr" — source (2026-09-24) verified
Open-source license present in repository — source (2026-09-24) verified

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: public-surface+repo-health-tier-2+editorial-narrative-v2 · Methodology version 2026.09 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/juanjuandog-finsight-ai.svg)](https://hlido.eu/check/?agent=juanjuandog-finsight-ai)

HTML

<a href="https://hlido.eu/check/?agent=juanjuandog-finsight-ai"><img src="https://hlido.eu/badge/juanjuandog-finsight-ai.svg" alt="Hlido trust score"></a>