Search

Docs job pack for Tessera: measure Python docstring coverage for public symbols.

Provider LLM client and token/pricing accounting for dacli

Policy-first OpenAI-compatible gateway for regulated workloads

n8n community node for PixelSEO — AI-powered SEO image generation and optimization

Universal LLM API client with Rust-powered polyglot bindings (placeholder release — see https://github.com/xberg-io/liter-llm).

Unified multi-provider LLM caller with automatic fallback

SpendGuard pre-call budget enforcement for n8n AI Agent workflows — drop a sub-node between Chat Model and AI Agent.

Ephemeral remote-runtime provisioning recipes for rag-rat. rag-rat (Rust) spawns a recipe as a subprocess, reads a typed JSONL event stream from its stdout (status/log/ready/error), embeds against the endpoint, then signals teardown.

Detects system prompt leakage using fuzzy string matching (via `rapidfuzz`) to compare the LLM's response against a provided system prompt

An n8n node to create end-to-end encrypted PrivateBin pastes (privatebin.net or self-hosted PrivateBin instances)

The inference boundary layer between your data and outbound AI requests

Analyze and visualize how an LLM picks each next token: probabilities, attention, logit-lens, activations, manifold geometry — CLI + web app.

Self-hosted RAG and semantic search — CLI

Batch processing for LLM APIs - CSV/JSONL in, processed out. With retries, rate limiting, and cost tracking.

Semantic diff for LLM prompts — compare prompt versions like git diff

Voorstel om de chat-+-LLM-functionaliteit uit **Organisatie-Anatomie** los te trekken tot een set herbruikbare bouwstenen, zodat elke app er een AI-assistent in kan hangen door alleen **een handvol dingen** te configureren in plaats van het hele apparaat

Onlist provider for the Vercel AI SDK. Route requests across 40+ AI providers with competitive pricing.

Multi-provider LLM cost observability SDK

PS-50 LLM Interfaces for Cloud-Dog services

Diagnose vector search problems in RAG/LLM systems. Hunt down why retrieval fails — embedding quality, vector search, BM25, reranker analysis.