code-session-memory vs cortex-mem
AI memory and search projects compared
code-session-memory indexes conversations from supported coding agents for semantic search and session handoffs. cortex-mem provides a broader memory framework for AI applications, with structured memory extraction, durable storage, and retrieval; they differ mainly in whether memory centers on coding-session history or general agent memory.
code-session-memory: Search AI Coding Sessions with OpenAI Embeddings
code-session-memory indexes sessions from OpenCode, Claude Code, Cursor, VS Code, Codex, and Gemini CLI into shared, searchable memory using OpenAI embeddings. It stores data locally with SQLite and sqlite-vec by default, with PostgreSQL and pgvector as an optional shared backend.
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.
| code-session-memory | cortex-mem | |
|---|---|---|
| Language | TypeScript | Rust |
| License | — | MIT |
| Stars | 20 | 311 |
| Forks | 2 | 24 |
| Last analyzed | Oct 30, 2026 | Oct 3, 2026 |
Key differences
- code-session-memory focuses on searching and summarizing coding sessions across supported tools, while cortex-mem extracts and organizes long-term memories for AI agents and applications.
- code-session-memory is written in TypeScript; cortex-mem is written in Rust.
- code-session-memory defaults to local SQLite and offers PostgreSQL with pgvector for shared storage; cortex-mem stores Markdown in a virtual filesystem and uses Qdrant for semantic search.
- code-session-memory offers a CLI, MCP server, and web dashboard; cortex-mem also provides a REST API, Rust integration options, and tenant-aware memory spaces.
- Both projects use the MIT license and are not archived; the supplied figures list 20 stars and 2 forks for code-session-memory, and 311 stars and 24 forks for cortex-mem.
Choose code-session-memory if you…
- need semantic search across past conversations from supported coding agents.
- want a compact handoff summary from a previous coding session.
- prefer local SQLite by default, with PostgreSQL and pgvector available for sharing memory across machines.
Choose cortex-mem if you…
- are building an AI agent or application that needs persistent, organized memories beyond coding-session transcripts.
- want layered memories with concise summaries and detailed content, stored as Markdown.
- need access through a REST API or Rust integration, alongside CLI and MCP options.
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.