agent-memory-system

Agentic memory infra for AI agents

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Offline & private, auto-consolidates in its sleep (autoDream), visualized in a memory panel.

Comparison of memory systems for agents

AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.

[ICML 2026] E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent Memory

A branch-aware, dual-revision epistemic ledger and control plane for AI coding agents. From requirements and isolated work to validated changes and durable, queryable project truth.

Plasmod: An Agent-Native Database for Cognitive Objects, Event-Driven Materialization, and Structured Evidence Retrieval

DE-centralized - MARKdown - for US: Persistent memory for AI agents, shared knowledge for teams, and a second brain for you. Built on the Mark Protocol.

Neuroscience-inspired memory for AI agents — sleep cycles that rewrite and strengthen knowledge over time. TypeScript, PostgreSQL, MCP.

Open-source AI operating system for computer use agents

Context and memory management for agents to learn over time. Private and lightweight.

grep-like session search tool for coding agents with Git-backed sharing (Codex, Claude Code)

Auto consolidate all your Agent Runtimes. Share memory across your agents.Auto highly structured task analyzer.

A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.

Reverie Core is an agentic cognition layer for the Hermes ecosystem (memory plugin)

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.

Memory ecosystem bridging the DeepSeek web app and local DSH — one local memory pool shared by a browser extension (harvest/inject), a zero-dependency local service (sole writer), and a DSH adapter (pre-step injection).