whereismyai
Agentmemoryrepo
Agentmemoryrepo is an open standard memory repository specification that lets agents save and retrieve learnings across sessions.
Agent Memory Repo is a specification that helps agents remember things across sessions. It works by having the agent save what it learns in real time to a separate repository, which the agent navigates like a wiki using cross-links. The memory loop involves cloning the latest memory, searching for what the task needs, updating entries, and pushing edits. It is designed for developers and teams who want their AI agents to retain context and share findings. The repository can contain Markdown notes, SQL queries, scripts, and other files. It supports tools like Devin CLI, Claude Code, and Cursor.
Agentmemoryrepo at a glance
Key features
- Save and retrieve agent learnings across sessions
- Navigate memories like a wiki using cross-links
- Organize files and folders including Markdown and SQL
- Share knowledge across agent swarms
- Maintain personal and team memory repos
- Combine multiple memory repos in a single session
Use it for
- Remember user context across different sessions
- Share findings across agents working in parallel
- Share knowledge about customers, processes, and tools
- Reuse saved SQL queries and scripts
Alternatives to Agentmemoryrepo
- ReMe — It enables local-first, file-native long-term memory sharing across multiple AI agents.
- memU — It gives every connected agent a shared and inspectable memory layer.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
- MemOS — It delivers ultra-persistent memory, hybrid-retrieval, and token savings.
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- Mem0 — It provides drop-in persistent memory for AI agents without changing pipelines.
- MuscleMemory — It cuts input tokens, tool calls, and execution time while maintaining task success.
- Playground — Persists agent memory across sessions and searches by meaning.
- MemMachine — Provides long-term persistent memory for LLM-based agents.
- TencentDB Agent Memory — It unifies cross-agent memory assets, skill libraries, wikis, and code graphs.
- EverOS — It enables agents to learn from experience and improves over time without manual coding.
All Agentmemoryrepo alternatives