AI agent memory / persistent context
Captures an AI coding agent's session activity, compresses it, and injects relevant context into future sessions to give agents persistent long-term memory.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
choose when you want a benchmark-focused persistent memory library for coding agents that can be swapped into agent workflows.
#1 Persistent memory for AI coding agents based on real-world benchmarks
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose when you need a standalone local memory store shared across LLM apps instead of an agent-session capture plugin.
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
choose when you want memory bundled with harness-level performance optimization and skills rather than a dedicated memory plugin.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
choose when you want rollbackable graph-structured memory over MCP instead of AI-compressed session snapshots.
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
choose when you already use Milvus and want Markdown-backed unified memory for multiple agents.
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
choose when you want a shared local memory hub for all agents rather than per-tool session compression.
🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.
choose when you want a self-hosted knowledge-graph AI memory platform instead of session-capture compression.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
choose when you want a self-managing unbounded-context memory layer for coding agents rather than a session-capture plugin.
Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
choose when you want a local personal memory engine that works across many coding agents rather than a session-capture plugin.
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose when you only need self-correcting memory from user corrections in Claude Code, not full session capture.
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
These projects were analysed and named claude-mem among their alternatives. The relationship is not symmetric — how claude-mem rates them is a separate judgement, made when claude-mem is analysed in its own right.
calls claude-mem “Use if you prefer a lightweight JavaScript MCP memory server that compresses context and injects it into future sessions, avoiding the TypeScript engine.”
#1 Persistent memory for AI coding agents based on real-world benchmarks
calls claude-mem “choose when you need simple session-capture/compression memory for Claude or agents without a filesystem context model.”
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
calls claude-mem “if you only need persistent session memory for Claude Code and want automatic compression.”
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
calls claude-mem “Choose if you want automatic session capture and AI-compressed context injection for coding agents, rather than a programmatic memory API.”
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
calls claude-mem “Session-log compression memory for simpler history injection without a graph store.”
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
calls claude-mem “Focused only on persistent memory/context, missing the other seed features.”
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
calls claude-mem “Choose when you are building agents specifically on Claude and want session-memory injection.”
Universal memory layer for AI Agents
calls claude-mem “Choose it when you only need persistent context for Claude Code sessions and don't want a full knowledge-graph platform.”
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
calls claude-mem “Use it if you need turnkey session memory specifically for Claude Code or coding agents, not a general API.”
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
calls claude-mem “Use when you want a ready-made CLI/plugin to capture agent sessions rather than embedding a memory library.”
The best-benchmarked open-source AI memory system. And it's free.
calls claude-mem “choose it when you want a ready-made CLI that captures and reinjects context for Claude Code.”
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
calls claude-mem “Choose when you use Claude Code/Codex and want drop-in session memory capture/reinjection with no custom integration code.”
Memory library for building stateful agents