Search

Semantic-velocity document chunker — cuts where meaning changes, then snaps to real sentence/paragraph boundaries.

Объектное хранилище (ObjectStorage protocol + MinIO adapter + image normalization for Skillery)

MS-RAGS(ALL-IN-ONE) — production-grade RAG framework builder terminal CLI

Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file.

n8n node to read and control Flagsmith feature flags, and trigger workflows on flag changes

n8n community node for Qorami — check an email before your workflow sends it (send / ask a human / block).

Python SDK for observability, tracing, and evaluation of LLM applications

LLM-as-judge linter: enforce code-quality checks deterministic linters can't express, by driving real coding harnesses through oneharness.

A local-first, config-driven LLM router across OpenAI-compatible backends you own.

One OpenAI-compatible endpoint for 15+ free LLM providers. Smart routing, failover, encrypted keys. Run with npx freellm.

Makes a second request to the LLM, asking it if its original response was relevant to the prompt.

Publication-quality LLM architecture diagrams, fact sheets, and diffs from HuggingFace config.json — no weights needed

Uma biblioteca simples para interagir com a IA da Pollinations.

Fails your CI when your LLM app starts making things up — local-first faithfulness regression gate.

Community-editable skills repository

Author's overview by Jesse Vincent

No description available

Official support article explaining Claude Skills

How to enable and use skills

Official announcement from Anthropic