Search

Extract skills from job postings and resumes — 32K-skill gazetteer + MiniLM embeddings + MLP context classifier (73% F1, trained on 491K samples). ONNX Runtime, no torch.

Thin benchmark runner for OpenAI-compatible chat completion endpoints.

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.

n8n community node for receiving Saweria donation webhook notifications

LangChain adapter for AgentKit Stellar

Any HuggingFace model. Local. Multi-modal. Served over an OpenAI-compatible API.

Drop-in, self-hosted analytics engine backed by Convex. Tracks sessions, interactions, and errors with a single machine/session identity model.

Manually switch between multiple Claude Code accounts by swapping local credentials.

A Django storage field that works everywhere. One import. Any backend. Zero plumbing.

RAG evaluation library for Indian languages (Hindi, Marathi)

AI-powered git diff analysis and code review with RAG context

n8n community node for rendering videos using your self-hosted Remotion server. Supports multiple images with Ken Burns effects, text overlays with alignment, multi-track audio, dynamic input from upstream nodes, and Auto Collect mode that detects images/

Early-stage toolkit for building AI, ML, and LLM workflows.

LLM/AI Prompt Manager Library

GraphSearch: a GraphQL API server for Retrieval-Augmented Generation (RAG) over your documents

Universal Loop Engineering System — iterative AI execution for any LLM provider with tool support

Login to ChatGPT with email:password, get access token + cookies

Circuit SDK inference — OpenAI-compatible client for the decentralized DLLM mesh, paid per call in CIRC (x402).

Circuit SDK — batteries-included meta-package re-exporting @circuit-llm/{core,x402,inference,data,wallet}.