shipwithjev

Catalog / Research & data

0559GitHub

Hippo Memory: rerank recalled memories with Jev

An opt-in Jev reranker scores candidate memories from a local SQLite store before selected evidence reaches a coding agent.

The public reranker and evaluation write-up were inspected on October 1, 2026. On a private 300-query store, the author reports recall at rank one rising from 0.41 to 0.62 versus a local cross-encoder. Three answer-quality tests on a 150-question LongMemEval set did not show better answer rates; two Jev-ranked memories answered as well as five locally ranked memories. The hosted reranker is optional and off by default. Results have not been independently reproduced.

kitfunso/hippo-memoryREADME ↗
# 🦛 Hippo: memory for AI agents that learns what is wrong

**Hippo learns what is wrong and ranks it down.** Good memory is knowing what to forget: what turned out wrong, what got replaced, what nobody used.

[](https://npmjs.com/package/hippo-memory)
[](https://npmjs.com/package/hippo-memory)
[](https://github.com/kitfunso/hippo-memory/actions/workflows/ci.yml)
[](https://github.com/kitfunso/hippo-memory/blob/master/LICENSE)
[](https://hippo-memory.com)

<p align="center">
  <img src="https://raw.githubusercontent.com/kitfunso/hippo-memory/master/assets/hippo-init.svg" alt="hippo init adding memory to one project" width="720">
</p>

Hippo keeps your coding agents' memories in a SQLite store on your machine, with markdown mirrors you can read and commit. Search is BM25 out of the box, with no model and no network call; embeddings are an optional install. `hippo init` installs hooks for Claude Code and OpenCode, adds 2 hooks to Codex's `hooks.json` when Codex is installed (Codex runs them once you trust them in `/hooks`), and adds instructions to an existing `AGENTS.md` for Codex, Cursor, OpenClaw and Pi. Any MCP client can connect. Mark a memory wrong and it ranks lower; run `hippo supersede` and the old fact leaves recall. Zero runtime deps.

Install it, then run `hippo init` inside one project. Init creates the project's `.hippo/` store and adds a block to the `CLAUDE.md` or `AGENTS.md` already there. On your machine it adds hooks for the agents it finds, such as Claude Code's in `~/.claude/settings.json`, and a daily 6:15am run. [What hippo init changes](#what-hippo-init-changes) lists all of it and the flags that skip each part.

```bash
npm install -g hippo-memory && hippo init
```

Setting up every git repo under a folder in one go is a second step. The [Quick st

Also filed under Research & data

  1. 0620

    Jev Score: rubrics, scores and confidence

    A worked guide to Jev's Score primitive: writing a request, defining rubric levels, reading recorded probabilities and the weighted-score math.

    Jev Trader · Research & data

  2. 0614

    Bot journey classification in WebDecoy

    Sends a detected bot's last 48 request paths to Jev, which picks what it's after (prices, articles…) and how it crawls (pagination, IDs…), or unknown.

    WebDecoy · Research & data

  3. 0610

    Fake / Real: link fact-checker with Jev as judge

    Paste an article or post link. Fake / Real extracts its claims, finds outside evidence, and has Jev judge whether the evidence supports or contradicts each one.

    @DansiDanutz · Research & data

  4. 0609

    AutoRubric: rubric-based evaluation

    Combines rubric science and LLM-as-a-judge research to grade outputs with AI judges: LLMs, decision models like Jev, or both.

    @deliprao · Research & data