cortex-mem vs agentfs
Persistent AI agent memory and state storage compared
cortex-mem helps AI applications extract, organize, and retrieve long-term memories, using durable Markdown storage with semantic search. agentfs stores files, key-value state, and tool-call history together in a SQLite database, emphasizing queryable and portable agent state.
cortex-mem: Give AI Agents Persistent Long-Term Memory
Cortex Memory is a Rust framework for storing, extracting, and searching long-term memories for AI agents and applications. It combines durable file-based storage with semantic search, and offers CLI, REST API, and MCP access.
agentfs: Store and Audit AI Agent State in SQLite
AgentFS stores an AI agent’s files, key-value state, and tool-call history in a SQLite database. Use its SDK or CLI when you need portable, queryable agent state and filesystem-level isolation.
| cortex-mem | agentfs | |
|---|---|---|
| Language | Rust | Rust |
| License | MIT | — |
| Stars | 311 | 3.5k |
| Forks | 24 | 204 |
| Last analyzed | Oct 3, 2026 | Oct 13, 2026 |
Key differences
- cortex-mem focuses on conversation-derived memories and semantic retrieval; agentfs focuses on an agent’s files, key-value state, and tool-call history.
- cortex-mem organizes memories into abstracts, overviews, and detailed content; agentfs provides a POSIX-like filesystem backed by SQLite and supports SQL queries.
- cortex-mem relies on Qdrant and compatible LLM and embedding services for its full system; agentfs keeps its state in a SQLite database that can be copied or snapshotted.
- cortex-mem offers CLI, REST API, MCP, and Rust integration; agentfs offers TypeScript, Python, and Rust SDKs plus a CLI and filesystem mounting options.
- cortex-mem describes itself as production-ready, while agentfs is labeled beta and advises against using production data without backups.
- Both projects are Rust-based and MIT licensed; agentfs has more reported stars and forks in the supplied data.
Choose cortex-mem if you…
- need to extract, organize, and semantically retrieve memories across conversations.
- want layered memory summaries alongside detailed Markdown content.
- need CLI, REST API, MCP, or Rust options for accessing agent memory.
Choose agentfs if you…
- need files, key-value state, and tool-call history stored together in SQLite.
- want to query, copy, snapshot, or restore an agent’s state as a database.
- need TypeScript or Python SDKs, or filesystem-level isolation for agent files.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.