code-session-memory vs cursor-memory-bank
AI coding session memory and workflow tools compared
code-session-memory indexes conversations from several coding agents for semantic search and retrieval. cursor-memory-bank structures work inside Cursor with phased commands and Markdown files that preserve task context, so one focuses on searching past sessions and the other on guiding ongoing work.
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.
cursor-memory-bank: Structure AI-Assisted Development Workflows
cursor-memory-bank adds a persistent task memory and phased workflow to Cursor, guiding projects from initialization and planning through implementation and review. It suits developers who want repeatable processes and durable context for AI-assisted coding.
| code-session-memory | cursor-memory-bank | |
|---|---|---|
| Language | TypeScript | — |
| Stars | 20 | 3.1k |
| Forks | 2 | 437 |
| Last analyzed | Oct 30, 2026 | Oct 3, 2026 |
Key differences
- code-session-memory searches conversations across OpenCode, Claude Code, Cursor, VS Code, Codex, and Gemini CLI; cursor-memory-bank is a workflow framework for Cursor.
- code-session-memory indexes messages automatically and offers semantic search through an MCP server or CLI; cursor-memory-bank guides tasks through commands for planning, design, implementation, reflection, and archiving.
- code-session-memory stores searchable session data in SQLite by default, with PostgreSQL and pgvector as an option; cursor-memory-bank records context and progress in shared Markdown files.
- code-session-memory is written in TypeScript and is MIT-licensed; the provided project details do not specify cursor-memory-bank's language or license.
- code-session-memory requires an OpenAI API key for embeddings and compaction; cursor-memory-bank requires Cursor 2.0 or higher and describes its v0.8 workflow as beta.
- cursor-memory-bank reports 3.1k stars and 437 forks and is described by its maintainer as a personal project without an actively maintained issue tracker; code-session-memory reports 20 stars and 2 forks.
Choose code-session-memory if you…
- need to search past conversations across multiple supported coding agents.
- want automatic session indexing, semantic queries, and filters by tool, project, or date.
- want a compact handoff summary or searchable memory stored locally or shared through PostgreSQL and pgvector.
Choose cursor-memory-bank if you…
- want Cursor commands to guide tasks from planning through implementation and review.
- need project and task context recorded in shared Markdown files between workflow phases.
- want the workflow and its documentation to adapt to task complexity.
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.