Rag Pipeline Python Packages

navi-sanitize

Deterministic input sanitization for untrusted text — invisible characters, homoglyphs, and encoding tricks, handled before your code sees them. Zero dependencies, no ML. Python 3.12+.

knowledge-rag

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

model-compose

Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.

ragleap-tools

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

simpleaudit

Allows to red-team your AI systems through adversarial probing. It is simple, effective, and requires minimal setup.

ragleap-rag

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

superagentx

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.

toon-llm

Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.

cloudg

Map, graph and audit AWS, Azure and GCP from one CLI. Builds a topology graph, runs Prowler/Checkov/Trivy, tags findings against 28 compliance frameworks, and exports HTML reports, RDF ontologies, RAG chunks and Terraform recreation files.

ragleap-observability

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

embedflow

Zero downtime embedding upgrades

aegis-gateway-core

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

inventio

inventio connects everything: lightweight, fast, simple, accurate. Local retrieval that returns the exact lines.

aegis-gateway-server

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-classification

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-sdk

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-pii

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-residency

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-pack-budgets

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway-cli

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

aegis-gateway

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server

ragleap-graph

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

projectdavid-platform

A single pip installed package will orchestrate a production ready instance of the AI stack in any environment

aegis-gateway-pack-llm-guard

Aegis is an open-source, plugin-first AI gateway framework written in Python. It sits between applications and LLM providers, applying governance rules to every request and response. Demo: https://huggingface.co/spaces/echoness/aegis-server