engram vs Athena-Public
Persistent memory for AI coding agents compared
engram and Athena-Public help AI coding agents carry project context across sessions. engram stores curated memories in SQLite and exposes them through several interfaces, while Athena-Public uses editable Markdown files and `/start` and `/end` session routines.
engram: Give AI Coding Agents Persistent Memory
Engram is a Go-based memory system that helps AI coding agents retain useful project knowledge between sessions. It stores memories locally in SQLite and makes them available through MCP, a CLI, an HTTP API, and a terminal UI.
Athena-Public: Keep AI Coding Agent Context Across Sessions
Project Athena stores coding context in Markdown on your disk and uses a session routine to carry it forward between AI coding sessions. It suits developers who switch IDEs or models and want to keep their project memory portable.
| engram | Athena-Public | |
|---|---|---|
| Language | Go | Python |
| License | MIT | MIT |
| Stars | 7k | 592 |
| Forks | 724 | 77 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- engram is written in Go and stores memory in SQLite with FTS5; Athena-Public is written in Python and stores memory as Markdown files.
- engram provides MCP, CLI, HTTP API, and terminal UI access; Athena-Public centers on `/start` and `/end` routines and generates IDE-specific instruction files.
- engram supports project-aware retrieval and offers Git Sync and optional Engram Cloud replication; Athena-Public offers hybrid keyword and optional vector search, with optional Supabase-based cloud sync.
- Athena-Public includes Claude Code hooks for checks such as secret scanning and destructive-command safeguards; outside Claude Code, its guardrails rely on instructions to the model.
- Both projects use the MIT license and are not archived. The listed GitHub counts are 7k stars and 724 forks for engram, and 592 stars and 77 forks for Athena-Public.
Choose engram if you…
- need an SQLite-backed memory store accessible through MCP, a CLI, an HTTP API, or a terminal UI.
- want to curate project knowledge for retrieval rather than keep session context primarily as Markdown files.
- want optional Git-based sharing or project-scoped Cloud replication.
Choose Athena-Public if you…
- prefer to inspect and edit project memory directly as Markdown files on disk.
- want `/start` and `/end` routines for loading context and recording session changes.
- need Claude Code hooks for checks such as secret scanning and destructive-command safeguards.
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.