AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

kai2ser/pefa-rag

AI-powered semantic search across PEFA (Public Expenditure and Financial Accountability) national assessment reports. Next.js + Supabase pgvector + Anthropic Claude.

TypeScript GitHub ↗
★ 0
stars
65
AI relevance
50
solo dev
2
tool sigs

SUMMARY AI summary by gpt-5-mini

PEFA Reports AI is a Next.js application that provides AI-powered semantic search over PEFA (Public Expenditure and Financial Accountability) national assessment reports. It’s intended for analysts, practitioners, and teams who need to find and query content across a curated collection of PEFA reports. Key features: - Semantic search via OpenAI embeddings (text-embedding-3-large) stored in Supabase Postgres with pgvector. - Natural-language responses generated/streamed by Anthropic Claude Sonnet 4. - Shared documents catalogue (CSV → Supabase documents table) scoped to collection_id = "pefa". - Data pipeline: seed overview rows, download public PDFs, parse/chunk/embed, upsert vectors to pefa_chunks. - Deployment: Next.js 16 on Vercel; requires five env vars and a Supabase migration. Includes dev/build/lint scripts and an estimated embedding cost for full ingest.

AI Coding Tools Used

This repository contains config files from these AI coding tools, indicating AI-assisted development.

OpenAI Codex (AGENTS.md) AGENTS.md Claude Code CLAUDE.md

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🧠 LLM providers (2)
Anthropic OpenAI
🗄️ Vector DBs (1)
pgvector
🔢 Embedding models (1)
text-embedding-3
🤖 LLM models (1)
Claude
💾 Databases (1)
Supabase
🌐 Web frameworks (1)
Next.js
☁️ Cloud platforms (1)
Vercel

Language breakdown (by bytes)

CSS
1.2%
PLpgSQL
5.9%
JavaScript
0.8%
TypeScript
92.1%

Owner

Account
kai2ser
Type
User
Followers
1
Company
World Bank

Senior Economist, but with an interest bringing together people, processes and technology for better public sector performance and development outcomes.

Dates

Created on GitHub 2026-05-16
Last push 2026-05-16
First seen here 2026-05-16
Last fetched 2026-05-16 18:11

Similar repos (same language)

Doulor/Clawd-Companion

Claude Code 桌宠伴侣 — 透明桌宠窗口实时显示 Claude Code 的工具调用、会话状态和完成提醒。

TypeScript 5 AI 45
YieldDi/cc-devloop

Claude Code Dev Loop

TypeScript 2 AI 45
ArisRhiannon/vibecheck

Offline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.

TypeScript 2 AI 70
neang-mengseang/LLM-Router

Self-hosted OpenAI-compatible API that routes LLM requests across 14 providers with automatic failover.

TypeScript 2 AI 65
civilization-os/CodeCartographer

Static code intelligence for generating architecture docs, call graphs, business flows, and structured repository maps with optional LLM-powered method understanding.

TypeScript 1 AI 45
nithiin7/repo-chat

A simple and powerful RAG chatbot that can index and intelligently answer questions about your codebase.

TypeScript 1 AI 45
code-by-tiago/Planify

Plataforma de Automação Educacional com IA Repositório oficial de uma aplicação web externa para o ecossistema Planify. O sistema utiliza modelos de linguagem (LLMs) para processar diretrizes pedagógicas, cronogramas estruturados de ensino automatizados e exportar materiais didáticos formatados (PDF/Docs) para educadores.

TypeScript 1 AI 45
boggspa/TaskWraith

Local-first macOS workbench for running and reviewing AI coding agents — multi-provider, with multi-agent ensembles, diff review, and on-device history.

TypeScript 1 AI 100