Persistent institutional shared memory as observable middleware for collaborative AI agents
Multi-agent orchestration plugin for Claude Code — 10 specialized agents, persistent Brain memory, quality gates, continuous QA, wave-based parallel execution, and mechanical enforcement hooks
Persistent, governed memory for chat clients, IDEs, & agents. Share memory across clients without losing scope, provenance, or auditability.
Institutional memory for AI coding agents. Scars, wins, and patterns that persist across sessions. MCP server for Claude Code, Cursor, OpenClaw...
Cross-model shared memory for AI agents. One canon every model reads. Free OSS via pipx install memee. memee.eu hosts the Team edition with shared scope, SSO, audit log.
Build one shared, permission-aware, auditable AI memory for an entire organization. A vendor-neutral blueprint you hand to a coding agent: 13 pillars, 70 decision forks, an M0-M15 build order. The org-scale sibling of RAG-OS and an alternative to Glean, Dust, M365 Copilot, Letta, and Zep.
AI tools write code fast, but they have zero memory of your team's history. mergelore sits in your CI pipeline and surfaces past architectural decisions, reversed patterns, and constraint violations before they ship again. No new infrastructure required, just add it to your workflow.
KRONOS is a multi-agent system on the GitHub Actions platform that gives your codebase institutional memory. It captures every architectural decision your team makes — from both code reviews AND the actual diffs — predicts failures before code is written
Self-hosted company memory — ask why, get receipts. SQLite, BM25, MCP. Slack, Jira, GitHub, email, Teams, Linear.
Working papers on responsibility infrastructure, AI governance, authority, evidence, and accountable AI-assisted work.
This repository documents realities that surface only after scale,authority,and commitment eliminate reversibility—where decisions ossify into structure, costs compound beyond instrumentation, failures persist without incident,accountability diffuses,and systems continue operating long after meaningful correction has become structurally impossible.
Institutional memory engine for AI agents — compiled Rust MCP server with adapters for Hermes, CrewAI, LangGraph, Haystack, OpenHands, MS Agent Framework, and Google ADK
The senior who never graduates — an institutional-memory AI agent for college clubs. Ask 5 years of minutes, budgets, sponsor emails & post-mortems and get cited, cross-referenced answers. Built with Google ADK + Gemini, Qdrant hybrid retrieval, and long-term memory.
RAIL — Record & Archive Index Ledger documents the public structure, continuity, and governance of the Debbaut.Solutions Execution Ecosystem. It provides a transparent, auditable trail of updates and canonical assets under a unified Execution Framework.
Lossless compaction of session knowledge for AI coding agents — symptom-first triage, durable capture, cold-start verification
Runbooks derived from verified history, not imagined at design time. The Runbooks layer of QA Veritas.
End-of-shift knowledge capture for restaurant operators. Three fast questions at every shift change that prevent handoff failures, preserve institutional memory, and make sure urgent issues reach the next manager before they become tomorrow’s problem.
Reference implementation demonstrating trustworthy institutional memory through provenance, evidence, and Forensic Receipts.
Your codebase already knows.
Open standard for institutional decision memory
To associate your repository with the institutional-memory topic, visit your repo's landing page and select "manage topics."