Athena plugin
athena-public
A long-term context layer for agents portable between editors: plain Markdown on disk, the /start and /end commands. Version 10
- 612 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent reads and writes memory files
- The full version includes cloud sync
Install
- Works in
Manual install
pip install -e ".[local]"First git clone of the winstonkoh87/Athena-Public repository. The full version: pip install -e ".[full]".
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent reads and writes memory files
- The full version includes cloud sync
This is third-party code. Review the repository files before installing.
What it does
Athena is a long-term context layer for agents that moves between editors: memory is stored in plain Markdown files on disk and sessions open and close with the `/start` and `/end` commands. Installation: `git clone https://github.com/winstonkoh87/Athena-Public.git && cd Athena-Public`, then `pip install -e ".[local]"` (lightweight) or `pip install -e ".[full]"` (with cloud sync and reranking). Version 10.0.3 from 05.10.2026, MIT license.
Who it is for. For developers who need portable agent memory in Markdown that is not tied to one editor.
Good fit when
- You need long-term agent memory in plain Markdown files
- You need memory portable between editors
- You need /start and /end commands for sessions
Not a fit when
- You cannot turn on cloud sync: the full version includes it
- You need a simple installation without Python
Example request
Open a session with /start, recall the project agreements and close it with /end saving the resultsLimitations
Memory is stored in Markdown files on disk: do not publish it as it may hold personal data and work details. The full version includes cloud sync and reranking and the lightweight one works locally. Access is extended: the agent reads and writes memory files.
How to disable. Remove the skill from the agent's folder or the plugin through the plugin manager.
FAQ
Where is the memory stored?
In plain Markdown files on disk.
How do I open and close a session?
With the /start and /end commands.
How do the versions differ?
The lightweight one works locally and the full one adds cloud sync and reranking.
Discussion
No questions or reviews yet.
Related
PluginsLong-term memory for AI agents: Markdown files as the source of truth, a SQLite index as a cache, shared by Claude Code, Codex and others
Long-term agent memory in local Markdown files with a link graph, semantic search and MCP access
A plugin marketplace for agents: reflexion, code and PR review, git, TDD, DDD, specs and subagent-driven development
Hippo Memory
hippo-memory
Long-term agent memory modeled on the brain: SQLite in .hippo, markdown mirrors, an MCP server over stdio and a Slack connector. Needs Node.js 22.16+
A context database for agents: cross-session memory, documents and skills in one viking:// file tree, reachable through MCP and hooks
Context Infrastructure
context-infrastructure
A reference implementation of a context system for an agent: structure, data flows, a blueprint the author has used for a year. README in Chinese. For study
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Athena (this entry) | no | 612 | ||
| Context Infrastructure | no | 790 | a reference context system for study, a Chinese README | |
| Hippo Memory | no | not required | 777 | memory in SQLite with markdown mirrors and a Slack connector |
README in short
The README describes a long-term context layer for agents in Markdown with /start and /end commands and installation through pip. MIT license.