Sovereign Ai Python Packages

vaara

Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.

memry

European memory system for AI agents with focus on compression and weighted information

vibey-engine

Open-source orchestrator for AI coding agents: a spec interview, unattended builds on local (Ollama) or paid agents, human-gated review, and an append-only PostgreSQL ledger so a crashed agent's work is picked up, not lost.

skillware

A Python framework for modular, self-contained skill management for machines.

mcp-tracking

Sovereign task tracking for LLM agents (suivi souverain): local-first, self-hosted, on-prem MCP server, HTTP API and Textual TUI for long-running tasks, no cloud

atomadic

Python SDK for the Atomadic sovereign MCP. Authenticate with a signed Ed25519 entitlement key, call 78 entitlement-gated tools at mcp.atomadic.tech. Tools execute deterministically — no LLM in the hot path. pip install atomadic.

cloakmcp

CloakMCP — local-first, deterministic sanitizer for secrets before LLMs

dryade-plugins-sdk

Pure-Protocol Python SDK for authoring Dryade plugins. MIT-licensed, zero core imports, hash-conformant with the Dryade plugin contract v4.

annona

Annona — the sovereign execution kernel for AI agents. Decides where each step runs, enforces it, and records it.

sarvam-cli-app

A CLI / AI Coding Assistant for Sarvam.ai... This could well be India's 2nd Independently developped Sovereign CLI based AI Coding Assistant.....

agdr-mantle

Sovereign Post-Quantum Fortification for AgDR Records. A three-tier lineage (Core, Implementation, Fortification) for 0.62µs Atomic Kernel Inferences. Published by the Genesis Glass Foundation. Canonical Source: aiccountability-source/AgDR-Mantle

lyra-assistant

Sovereign, local-first voice DevOps assistant (assistant vocal souverain): Ollama LLM, Whisper STT, Piper TTS and MCP tools for KVM, backups and smart home

tapirus

The 100% Safe-Rust Embedded Quad-Model AI Database & Cognitive Memory Engine (SQL, Vectors, GraphRAG, Documents)

krypton-app

Open-source orchestrator for AI coding agents: a spec interview, unattended builds on local (Ollama) or paid agents, human-gated review, and an append-only PostgreSQL ledger so a crashed agent's work is picked up, not lost.

incdai

Public protocol, SDK and widget for incdai — sovereign decentralized AI by INCPRITECH.

runwitness

Independent deployment evidence for AI systems

helix-hamiltonian

A first-principles Hamiltonian framework realizing the 'Knot-in-Time' ontology. Unifies topological physics, general relativity, and sovereign AI governance.

flyto-mlx

Flyto MLX — Apple Silicon LLM server with audio chat / DFlash / Chinese model presets. Fork of @jundot/oMLX.

sovereign-ai-stack

Experimental local-first AI prototype with NLI grounding and audit logging

sutra-sdk

Sovereign AI Initiative for Open Autonomous Cognitive Companion

sovereign-sdk-ledger

Local-first AI WAF, compliance gate, and cryptographic provenance engine for agentic workflows. Intercepts payloads, slashes token spend via Prose-Tax minimization, and mints tamper-evident audit chains on local silicon.

sovereign-sdk-edge

Local-first AI WAF, compliance gate, and cryptographic provenance engine for agentic workflows. Intercepts payloads, slashes token spend via Prose-Tax minimization, and mints tamper-evident audit chains on local silicon.

sovereign-sdk-core

Local-first AI WAF, compliance gate, and cryptographic provenance engine for agentic workflows. Intercepts payloads, slashes token spend via Prose-Tax minimization, and mints tamper-evident audit chains on local silicon.

sovereign-sdk-fastapi

Local-first AI WAF, compliance gate, and cryptographic provenance engine for agentic workflows. Intercepts payloads, slashes token spend via Prose-Tax minimization, and mints tamper-evident audit chains on local silicon.