ai-memory vs agent-memory
Persistent memory for coding agents compared
ai-memory and agent-memory help coding agents retain useful project knowledge across sessions. ai-memory centers on a self-hosted, git-backed wiki and cross-agent handoffs, while agent-memory organizes notes into tiers and generates AGENTS.md context using an LLM.
ai-memory: Share Long-Term Memory Across Coding Agents
A self-hosted Rust service that captures coding-agent activity into a searchable, git-backed Markdown wiki and hands work between agents. It suits developers and teams who want portable project memory without requiring LLM calls.
agent-memory: Give Coding Agents Persistent, Tiered Memory
agent-memory turns coding-session notes into organized, tiered knowledge and generates an AGENTS.md section with relevant context for new threads. It is a TypeScript tool for teams and developers who want agents to reuse knowledge without relying on manual searches.
| ai-memory | agent-memory | |
|---|---|---|
| Language | Rust | TypeScript |
| License | MIT | — |
| Stars | 9.1k | 7 |
| Forks | 632 | 0 |
| Last analyzed | Oct 10, 2026 | Oct 4, 2026 |
Key differences
- ai-memory captures agent activity through lifecycle integrations and stores sessions as Markdown pages; agent-memory collects notes in a journal queue for later consolidation.
- ai-memory provides search and handoffs, with basic operation that does not require LLM calls; agent-memory uses an LLM to consolidate and reorganize notes into hot, warm, and cold tiers.
- ai-memory is a Rust server and CLI designed to share project knowledge across machines and teammates; agent-memory is a TypeScript tool with a CLI and adapter-based integrations.
- ai-memory uses a git-backed wiki as its source of truth and offers a self-hosted server; agent-memory stores memory as files and generates an AGENTS.md section for new threads.
- ai-memory is MIT-licensed and has 8.8k stars and 608 forks; agent-memory has 7 stars and no forks in the supplied project facts.
Choose ai-memory if you…
- need a searchable, git-backed record of coding-agent activity.
- want handoffs and shared project knowledge across agents, machines, or teammates.
- prefer basic capture, search, and handoffs that work without an LLM provider.
Choose agent-memory if you…
- want LLM-consolidated notes organized into hot, warm, and cold tiers.
- need generated AGENTS.md context for new coding-agent threads.
- prefer a standalone TypeScript CLI with adapter-based integrations.
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.