Improves interoperability between systems (i.e. devices, platforms, apps, databases) by exchanging data based on their semantics

knowledge base engine

Open-source cognitive engine for AI agents — persistent memory, a first-person journal, a four-layer ethics engine, and a per-user biological clock, over MCP. Apache-2.0.

An event-sourced knowledge runtime for coding agents.

The repository contains an endpoint that can handle SPARQL queries and execute them on the Knowledge Engine

This repository contains the code of a Knowledge Mapper used in the Knowledge Engine

Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.

Generates code for code generators

Self-hosted context engineering engine for AI — MCP server with SQLite, PostgreSQL, or MariaDB

Goal-driven cognitive AI framework built on PetoronHash2 and zkPetoron-Core

AI memory engine exposed as an MCP server

Open-source AI cognitive framework built in Rust for modular reasoning, knowledge exploration, and autonomous intelligence.

Improves interoperability between systems (i.e. devices, platforms, apps, databases) by exchanging data based on their semantics

Quintessences — écosystème d'intelligence environnementale. GSIE : moteur modulaire 14 moteurs, traçable, explicable, offline-first. Spécialisations : GeoSylva (forêt), GSIE-Ignis (incendie), Myhunt (cynégétique), QGISIA (SIG).

Offline Factual Answering Engine — Knowledge, unchained from the cloud. BM25 retrieval, intent classification, 461 curated facts, command center UI.

AI-powered Universal Knowledge Engine — captures unstructured knowledge through conversations and structures it using multi-agent AI

AI-native knowledge base engine (client/server) across the DIKW pyramid: Data → Information → Knowledge → Wisdom. A self-managed server ingests, synthesizes and indexes; knowledge lives on disk as an open, portable Markdown format.

Panzoq is designed to break down information silos. Instead of managing separate tools for document reading, image analysis, and database queries

my pyke exercises 🆒

Enterprise-grade vectorless retrieval platform engineered for deterministic knowledge orchestration, explainable AI search, contextual document intelligence, and scalable enterprise retrieval workflows without vector embeddings.