Raglet(open-source)–portable RAG for small text corpora (no infra)

Name: Raglet(open-source)–portable RAG for small text corpora (no infra)
Availability: InStock
Author: cepstrum9

by cepstrum9·Mar 9, 2026·2 points·1 comment

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemCozy

Embedded semantic search without vector DB or LLM calls—just save and git commit.

Strengths

•No external dependencies or infrastructure—pure Python with zero runtime costs
•Semantic search via embeddings with configurable ranking, immediately usable for code/docs
•Portable serialization means indexes travel with source control, great for small teams

Weaknesses

•Competes with llamafile, LlamaIndex local mode, and Chroma for the same niche
•Unclear if embeddings are local or cloud-based; readme doesn't specify model source

Similar Projects

Developer Tools●●Solid

Terraform RAG - index modules, distill conventions, compose via MCP

MCP integration with Cursor and Claude Code sets this apart from generic RAG tools.

Niche GemSolve My Problem

kitgw

5111d ago

Infrastructure●●Solid

Rivestack – Managed PostgreSQL with pgvector, $29/mo

It spins up dedicated Postgres instances with pgvector pre-installed, uses Patroni for HA and pgBackRest for snapshots, and publishes concrete vector benchmarks (2k QPS @ <4ms for 10k vectors; 252 QPS at 1M). The stack choices (Hetzner NVMe, read replicas, HNSW) feel pragmatic for teams who don't want serverless/shared trade-offs, though I'd want clearer SLA/multi-region details and independent benchmarks at larger scales before moving critical workloads.

Niche GemSolve My Problem

stranger90

103mo ago

AI/ML●Mid

Built an webpage to show Singaporean infra and laws

Triple-LLM failover (Gemini → Llama 3.3 via OpenRouter → Groq), local BGE‑M3 embeddings and FAISS-backed retrieval show someone thought about latency and uptime, not just model demos. The README brags about 33k pages and 'non-hallucination' claims but stops short of evaluation details or realistic ops guidance — running 70B models and local embedding stacks is impressive on paper but a heavy lift in practice.

Niche GemWizardry

Goodguy27

323mo ago

AI/ML●●Solid