ai-agents-memory

SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory

MindForge is a Python library designed to provide sophisticated memory management capabilities for AI agents and models. It combines vector-based similarity search, concept graphs, and multi-level memory structures (short-term, long-term, user-specific, session-specific, and agent-specific) to enable more context-aware and adaptive AI responses.

Epistemic Bio-Homeostatic Identity & Memory Kernel for AI Agents with Model Context Protocol (MCP) Interface

Semantic permissions for AI coding agents. Intenter remembers what commands actually do, not just what they’re called.

Open source, free, private, local, generative co-intelligence scaffold

SGM, a System for Governed Memory. Context engineering for one person's working knowledge: what earns a place in the archive, how a claim carries its evidence, and where the line sits between what a machine may decide and what a person must.

Bootstrap an AI-agentic SDLC harness around any software project — new or existing, any stack, single- or multi-repo. Dual-ecosystem plugin marketplace: se-harness for Claude Code, se-harness-copilot for GitHub Copilot CLI.

Adaptive engineering control plane for AI coding agents — the right specialist depth for every task, with project context and proof-first execution.

A graph-native memory database for AI agents

A decoupled, zero-dependency dual-track long-term memory engine for LLM AI Agents. | 经验回想与印象整合引擎

Local-first AI project memory and control runtime for evidence, privacy, model routing, human approvals and cross-harness handoffs.

Engineering OS for Web GIS, GeoAI, remote sensing, spatial data, testing, security, and persistent project memory

Kevin gives OpenCode agents memory: it learns from failures, recalls the right lesson at the right moment, curates knowledge you approve, and shares it through one git-friendly file. No planning, no orchestration, no telemetry — it only learns.

Open-source observability for AI agents. Trace prompts, responses, tool calls, latency, tokens, cost, and failures with a Python SDK and local dashboard.

Svenskspråkig kurs och guide om Claude Code, Anthropics AI-agent för mjukvaruutveckling. Steg för steg på svenska, för nybörjare och utvecklare som vill lära sig AI-assisterad kodning utan språkhinder. Skapad av Lucy Sonberg. Jag ser datastyrning, AI governance och GDPR-säkerhet som en självklar prioritet för alla som bygger med AI-agenter.

Universal Expert Skill Suite & Dual-Scope Memory Engine for AI Coding Agents (Cursor, Claude Code, Windsurf, Copilot, Antigravity)

Code Python & R du livre « Devenir Orchestrateur IA — du Débutant à l'Expert » : 19 modules, 14 cas métier, 60 activités corrigées. Ebook : da-ia-data.mychariow.co/orchestrateur-ia

A CLI-only Docker workspace for AI coding agents — Claude Code, Copilot, Codex, Gemini, Kiro — running as a non-root user behind a deny-by-default outbound firewall.

Agent Memory Operating System: typed, auditable, model-neutral memory infrastructure for long-running AI agents.