Search

A thin, opinionated, local-first structured-output + logging layer over LiteLLM

Ontomesh — the ontology mesh for GraphRAG. Mine ontologies from logs, validate with SHACL, ship a hybrid retriever.

Local CLI and desktop checker for repairing structured LLM outputs against lightweight schemas

Uma biblioteca leve para interagir com a API nativa do Windows usando ctypes.

Lightweight and extensible memory layer for LLMs

Record linkage with dense blocking using text embeddings and LLM matching

A package for computing the CosinorAge from raw accelerometer data.

Out-of-tree vLLM KVConnector for SemBlend semantic KV donor discovery

Fully automatic censorship removal for language models

Python SDK for the Vector Gateway service (embeddings and vector search)

A fast, safe macOS CLI tool to reclaim disk space

Generic async LLM gateway with concurrency, retries, and JSON helpers

Context compression sidecar for LLM applications. Reduce token costs 3-5x before calling any AI API.

Unified Claude Code plugin — semantic memory, rule enforcement, neuro-symbolic logic, and project search

Unified supply-chain security suite — scanner, sandbox, LLM defense, and orchestration

Drop-in replacement for `claude -p` that runs through mngr create/message/transcript

Typing stubs for Ragged

Intelligent CLI tool router and LLM orchestrator wrapper (Placeholder).

Declarative LLM workflow orchestration with DAG-based parallel execution, safe conditional branching, and built-in cost tracking

Toroidal semantic graph retrieval for measurable multi-hop RAG trade-offs.