anbeime/skill / skills/awesome-jev/awesome-jev
awesome-jev
VerifiedFind and compare JEV-related GitHub projects for a user's task, language or agent workflow using the curated Awesome JEV catalogue and scenario references. Use for project discovery and implementation research, not for executing JEV API calls.
scenarios/retrieve-context.ja.md
View on GitHub<!-- Generated from data/scenarios.json + data/projects.json. -->
[← 検索入口に戻る](../README.ja.md#discovery)
# 関連文書・記憶の検索
検索済みの候補から Agent に渡す情報を絞ります。
**JEV が担当する段階**
候補を検索 → JEV が関連性を採点 → ローカルで再順位付け・フォールバック
## 参考プロジェクト
### [OpenViking · JEV Rerank](https://github.com/volcengine/OpenViking)
OpenViking は JEV を使い、Agent の記憶・コンテキスト検索結果を較正して再順位付けできます。
**参考にする部分:** 文書ごとの関連性判定とベクトルスコアへのフォールバック。
[根拠](https://github.com/volcengine/OpenViking/blob/b8bed5a1ad3a1c524b5e1fd0fa591df51ca9b7cc/openviking/models/rerank/jev_rerank.py)
### [Hindsight · TypeSafe Rerank](https://github.com/vectorize-io/hindsight)
Agent メモリに TypeSafe リランカーを追加し、無関係な検索候補を除外できます。
**参考にする部分:** 記憶検索における関連性採点と候補削減。
[根拠](https://github.com/vectorize-io/hindsight/blob/680406b3dd9cca2108c7f0e204820a09b4e30906/hindsight-api-slim/hindsight_api/engine/cross_encoder.py)
### [Hippo Memory · JEV Reranker](https://github.com/kitfunso/hippo-memory)
ローカル優先の Agent メモリライブラリで、任意で JEV リランカーを利用できます。
**参考にする部分:** 記憶の一括判定とローカル順位へのフォールバック。
[根拠](https://github.com/kitfunso/hippo-memory/blob/c9eb2c31cd307cdae78c05e1fcb3e6d062efd5c0/src/rerankers/jev.ts)
各プロジェクトはこのパターンの一部を示すもので、単一の完成アプリではありません。ソース確認は、動作・性能・BeatAPI 互換性の検証を意味しません。
[無料 JEV API を試す](https://docs.beatapi.io/decisions#free-calls) · [Agent で検索](../docs/agent-search.ja.md)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |