perfectrecall

# PerfectRecall

**Jev-powered memory for AI agents.** Try it on Hermes. Replace Mnemosyne while keeping your existing SQLite database, memory banks, and tool calls.

An independent 120-question LongMemEval-S experiment reduced final-answer errors from **62 to 17 (72.6%)**, using the same GPT-5.6 Luna caller with high reasoning effort. Accuracy rose from **48.3% to 85.8%**. These are results for a frozen predecessor of this release, not a fresh validation of the renamed package or an official leaderboard score. [Methods, results, regressions, and reproduction](benchmarks/README.md).

PerfectRecall asks Jev to evaluate every eligible memory against short criteria supplied by the calling agent. It returns the original evidence for that agent to reason over. There is no embedding model, vector index, or hidden query-writing model in the production package.

## Install in Hermes

For Hermes versions with Git plugin installation, install the directory plugin and run the native memory setup:

```sh
hermes plugins install https://github.com/arslanr-com/perfectrecall
hermes memory setup perfectrecall
```

This installs the repository's code and declared Python dependencies without a separate PerfectRecall pip installation. The setup command backs up configuration, selects PerfectRecall, and disables legacy source plugins while keeping their files. Set `OPENROUTER_API_KEY` in the Hermes environment and restart. A catalog listing is being submitted; installation by the bare name `perfectrecall` requires its acceptance. [Installation and rollback](docs/INSTALLATION.md).

### Install as a Python package

Python 3.10 or newer is required. Install into **the same Python environment that runs Hermes**. On a standard Hermes installation:

```sh
~/.hermes/hermes-agent/venv/bin/python -m