cortexdb vs graphicle
Agent memory plus a knowledge graph with ontology constraints in one SQLite file: pure Go, no server, no embedding model required. Plugins for Claude Code, Codex, dsh and Obsidian. — versus — One Rust program giving coding agents a code graph plus memory of docs, decisions and past sessions, served over MCP to Claude Code, Codex, Cursor and VS Code.
Both are local, single-install memory for coding agents with structured recall. Graphicle ties memory to a code graph; CortexDB to a typed knowledge graph in SQLite.
| cortexdb | graphicle | |
|---|---|---|
| Stars | 475 | 509 |
| Forks | 27 | 36 |
| Language | Go | Rust |
| License | MIT | Apache-2.0 |
| Last activity | yesterday | yesterday |
| Topics | memory, knowledge-graphs | code-intel, memory |
| Curated connections | 5 | 5 |
cortexdb — the curator's take
Use it when you want local, inspectable memory that is more structured than notes (typed entities, ontology rules, traceable recall) but don't want to run Postgres or Neo4j. Embeds as a Go library, with clients for Rust, Python and Node. Skip it for team-scale shared memory under heavy concurrent writes, or if you just want plain Markdown you can read and edit by hand.
graphicle — the curator's take
Use it when you want code intelligence and project memory from one local install instead of a code-graph MCP plus a separate memory server. Skip it if you already run a dedicated code graph you like, or need team-shared memory. Its memory comparison against seven systems is pre-release and self-reported.